Analysis of the LCA-Emergy and Carbon Emissions Sustainability Assessment of a Building System with Coupled Energy Storage Modules

Abstract

This paper uses a perspective of life cycle ecological emergy and carbon footprint to quantitatively verify the sustainable status of building systems; it also employs a neural network model to predict and analyze their long-term ecological and carbon footprint effects. The research results show that the stages of building material production and building operation play a major role in the emergy and carbon emissions of the entire building system, and their changes show an inverse trend. As the building system operates, the greater the system loss and consumption, the environmental load rate (ELR) will gradually increase, and the sustainability parameter (ESI) will also gradually decrease. The integration of energy storage modules significantly improves the sustainability of the building system. When calculated over five time periods (5 years, 10 years, 20 years, 30 years, and 50 years), the overall carbon emission reduction rates after adding the energy storage module are 39.4%, 33.6%, 39.2%, 42.5%, and 38.8% respectively, demonstrating that the energy storage module has a significant positive effect on the sustainability of the building system. This study reveals the energy efficiency and environmental impact of the building system throughout its entire life cycle, providing a scientific basis for optimizing building design.

1. Introduction

In the context of the increasingly severe trend of environmental deterioration, building systems, as an integral part of the global ecosystem, play a significant role in mitigating environmental stress and enhancing the global ecological level through their optimization and upgrading for sustainability [1,2]. As an open system, the operation and maintenance of building systems rely on the continuous input of various resources, including material flow, energy flow, and information flow. Thus, the sustainability of building systems from an ecological perspective is fundamentally a process of dynamic progression. Evaluating this sustainability necessitates a holistic approach and detailed examination tailored to the unique environmental, social, and economic contexts [3,4]. With respect to carbon emissions, the building sector is responsible for over a third of the global emissions, which underscores the critical need to prioritize and attain sustainability in the planning, design, construction, and maintenance phases of building systems [5,6]. Consequently, an extensive investigation into the sustainability of building systems is vital not only for advancing the green transformation of the construction sector but also for significantly contributing to the management and reduction of worldwide carbon emissions.

In the present investigation, this study adopts the emergy analysis approach, an instrument rooted in ecological economics, to conduct a quantitative examination of building systems. Emergy analysis has garnered broad application across diverse fields including urban planning, agricultural advancement, industrial manufacturing, material fabrication, ecological conservation, and economics [7,8,9,10,11,12,13]. Nevertheless, the synthesis of building systems with emergy analysis is a more recent development, with scholars from across the globe exploring various research trajectories within this domain. Certain academics have endeavored to merge Building Information Modeling (BIM) technology with emergy analysis, seeking to enhance information processing and decision-making support within the construction sector [14]. Concurrently, other researchers are delving into the harnessing of clean energy, examining strategies to foster sustainable building development from this vantage point [15]. Moreover, emergy assessments offer a precise means of quantifying the ecological sustainability of construction materials [16]. Within the ecological realm, the revision of green building standards and the expansion of their scope have emerged as topics of significant scholarly interest [17]. Additionally, some studies have employed emergy analysis as a supportive tool for architects, with the goal of optimizing the sustainability performance of building systems through this analytical method [18].

There is an increasing scholarly movement toward integrating emergy analysis with Life Cycle Assessment (LCA) to perform an all-encompassing evaluation of the ecological emergy sustainability of building systems. Such research encompasses studies on the holistic ecological emergy evaluation of building systems, approaches to modernizing building design strategies, the lifecycle implications of construction materials, and the real-world operational efficacy of buildings [19,20,21]. This cross-disciplinary approach not only enriches our comprehension of the sustainability attributes of building systems but also affords novel theoretical foundations and practical insights for the field of architectural design.

Amid the backdrop of global climate warming, the reduction of carbon dioxide emissions has emerged as an acutely critical global challenge. As integral components of the global ecosystem, building systems have garnered substantial attention within the sphere of carbon emission control research. A thorough review of the literature suggests that the current research landscape is concentrated around four primary dimensions: Firstly, the incorporation and application of low-carbon design principles within architectural practice, with the objective of effecting a holistic low-carbon metamorphosis of building systems through innovative design methodologies. This research thrust places emphasis on the integration of low-carbon strategies at the design phase to meet carbon emission reduction goals across the building life cycle [22,23,24,25,26,27]. Secondly, the examination of low-carbon evaluation systems, is centered on the quantitative analysis and assessment of the carbon footprint of building systems throughout their entire life cycles. This aspect of research not only entails calculating the emissions from building systems but also encompasses a comprehensive sustainability evaluation of buildings, providing a scientific foundation for low-carbon architectural design. Thirdly, the investigation into low-carbon management strategies spans a range of issues from the development of carbon emission modeling, the incorporation of carbon emission methodologies into supply chain management, to the governmental allocation of carbon emission quotas. These management strategies are instrumental in facilitating the low-carbon operation of building systems [28,29,30]. Lastly, the study of the amalgamation of low-carbon technologies with those from other disciplines, such as the convergence of Building Information Modeling with carbon emission computations [31], the application of life cycle theory in low-carbon design [32], and energy-saving perspectives in low-carbon building design [33]. Furthermore, research into carbon capture and storage technologies within building systems offers a novel technological avenue for reducing carbon emissions in the construction sector [34]. Additionally, there is a focus on the customized development of low-carbon modules tailored to different building types to address the specific low-carbon requirements of various structures [35,36,37]. These scholarly endeavors not only advance the low-carbon transformation of the construction industry but also furnish theoretical underpinnings and practical guidance for achieving global carbon emission reduction objectives.

As artificial intelligence computing technology continues to progress, Artificial Neural Networks (ANNs) have arisen as a novel computational approach, garnering growing interest and adoption across a multitude of sectors. Specifically, within the domain of building systems, the integration and utilization of ANNs have introduced fresh perspectives and instrumental tools for the sustainable progression of the construction sector [38]. The predictive models of ANNs, equipped with self-learning, adaptive, and generalization properties, have demonstrated distinctive strengths in addressing intricate challenges inherent in building systems.

In building systems, ANN predictive models can handle large amounts of data, providing accurate predictions across various aspects such as building energy consumption, structural performance, and indoor environmental quality. This process involves calculating errors for various parameters within the building system and then adjusting the weights layer by layer in the opposite direction of network propagation based on the magnitude of these errors, a process known as the backpropagation algorithm. Through continuous iterative optimization, the network can gradually reduce prediction errors and improve accuracy, thereby providing more reliable decision support for architectural design [39]. In terms of sustainable building analysis, the application of ANN can delve deeper into the environmental impact, energy efficiency, and economic benefits of buildings throughout their entire life cycle. By constructing multi-parameter predictive models of building sustainability, this paper can assess the impact of different design strategies and building materials on building performance, thereby promoting the construction industry’s development towards greater greenery and efficiency. Additionally, ANN can be combined with intelligent technologies to achieve intelligent management and optimization of building systems from design to operation, providing strong technical support for the digital transformation of the construction industry. In summary, the application of ANN predictive models in building systems not only enhances the level of intelligence in architectural design but also opens up new possibilities and pathways for the sustainable development of the construction industry.

The core novelty of this study lies in the meticulous examination of an advanced building system equipped with integrated energy storage modules, alongside the application of a merged ecological emergy and low-carbon evaluation framework, informed by life cycle theory, to gauge the sustainability of the system quantitatively. The methodological ingenuity of this research is evident in its comprehensive approach, which not only accounts for energy consumption and carbon emissions during the design and operational phases but also underscores the significance of energy storage modules. This exploration aims to harness the modules’ potential to bolster energy efficiency and curtail carbon emissions. Through a lifecycle analysis that encompasses the calculation of ecological emergy and carbon emissions for the building system, the research delivers a more precise determination of its sustainability quotient. This method surmounts the confines of conventional evaluations that typically zero in on the operational phase’s energy consumption alone, expanding to include the environmental ramifications of the building across its entire existence. Moreover, the study employs neural network models to forecast and analyze the evolutionary trends of the building system’s ecological emergy and carbon emissions. These models, equipped with robust data processing skills and the ability to perform non-linear fittings, adeptly track the system’s dynamic evolution, uncovering shifts in its sustainability over an extended period. The pioneering aspect of this approach is its capacity to equip architects and decision-makers with a dynamic, proactive assessment instrument that enhances their understanding and optimization of building systems’ sustainability performance. It also affords a solid scientific foundation and technical underpinning for the construction sector’s shift toward sustainability and green practices.

2. Material and Methods

2.1. Research Framework

Figure 1 presents the research framework of this paper, which clearly defines the research boundaries. Focusing on the building system as the object of study, the framework considers the changes before and after the coupling of energy storage modules in the building system. By examining the inputs of renewable and non-renewable resources, it utilizes lifecycle-based emergy and carbon emission methods to evaluate the sustainability changes before and after the integration of energy storage modules. Additionally, the framework employs neural network methods to conduct predictive analysis on the dynamic emergy and carbon emissions, and proposes improvement measures based on the results.

2.2. LCA-Emergy Method

2.2.1. LCA Approach

Life Cycle Assessment (LCA), also known as Life Cycle Analysis, is a systematic and comprehensive assessment method designed to evaluate the environmental impacts of a product or service throughout its entire life cycle. This involves examining every stage from the extraction of raw materials, through processing, production, use, to the eventual disposal, or recycling [40,41]. A specific LCA analysis model is illustrated in Figure 2.

LCA focuses on the environmental impacts of products or services, including aspects such as resource consumption, energy use, and pollutant emissions. Through LCA, it is possible to identify the stages in the product life cycle that may have the most significant environmental impacts and then take corresponding measures for optimization and improvement.

The LCA method used in this paper complies with the international standard ISO 14040:2006. According to this standard, the specific calculation of LCA can be divided into the following steps: goal definition and scope definition, inventory analysis, impact assessment, and result interpretation. Goal definition and scope definition clarify the object and boundary of the assessment, inventory analysis collects the input and output data of the product or service throughout its entire life cycle, impact assessment evaluates the environmental impact of these data, and result interpretation analyzes and explains the assessment results.

2.2.2. Emergy Concept

Emergy theory is a theoretical framework for measuring the contributions of natural resources to the economic development of human society. It uses solar emergy as the benchmark and converts the energy consumed by a product or service throughout its life cycle into emergy units to evaluate the equivalent value among different types of energy and resources. Emergy theory emphasizes the importance and finiteness of natural resources, positing that all matter and energy originate from nature, and that the development of human society should follow natural laws to achieve effective resource utilization and sustainable development. Through emergy analysis, the essence of resource consumption and environmental pollution in economic activities can be revealed, providing a scientific basis for policymakers and enterprises to promote the development of a green economy and a circular economy [42].

The Life Cycle Assessment Emergy (LCAE) method is a theoretical framework that combines Life Cycle Assessment (LCA) with emergy theory to evaluate the ecological sustainability of buildings. This method comprehensively considers the environmental impacts of the energy, materials, and resources required throughout the entire life cycle of a building, from design, construction, operation, maintenance, to demolition. In the LCAE method, all energy and resource consumption related to the building are converted into emergy units (solar emjoules), taking into account the quality, scarcity, and source of the resources. By calculating the emergy flows at each stage of the building’s life cycle, the overall environmental impact of the building can be quantified, and the stages with the greatest environmental impact can be identified. This method provides a comprehensive perspective to assess the ecological efficiency of buildings and guide the design of more environmentally friendly and energy-efficient building schemes. It helps decision-makers understand the resource dependence and environmental footprint of buildings throughout their life cycle, thus promoting the sustainable development of the construction industry. Through the LCAE method, building designs can be optimized, resource consumption reduced, environmental impact lowered, and a scientific basis provided for the green transformation of the construction industry.

Figure 3 delineates a comprehensive emergy analysis model tailored for building systems, which can be elaborated into four distinct components for a thorough understanding. The model begins with the far left section, which emblemizes renewable energy sources that are pivotal to sustainable building practices. This segment encompasses a variety of natural and perpetual energy forms such as solar radiation, wind power, rainwater harvesting, and geothermal energy, all of which contribute to reducing the ecological footprint of buildings.

The upper section of the model is dedicated to non-renewable energy and resources, which are integral to the construction and operation of building systems. This includes conventional energy sources like fossil fuels, diverse materials that are extracted from the earth, electricity generated from non-renewable sources, and various services that are dependent on these resources. These elements are crucial for understanding the total emergy input and the associated environmental burdens.

Moving to the far left section, this segment of the model highlights the intricate interaction between the building system and the external environment. It accounts for market transactions, which involve the exchange of goods and services, and the associated emergy flow. This interaction is critical for assessing the economic and environmental implications of the building system’s integration within the broader market economy.

The innermost part of the research boundary contains the core of the model, which is the flow of materials, information, and energy between the building system and the natural system. It also encompasses a feedback system that captures the dynamic and reciprocal relationship between the two entities. This section is essential for understanding the cyclic nature of emergy flow and how the building system impacts and is impacted by its surrounding natural environment.

Figure 3, thus, provides a clear and detailed visualization of the entire life cycle-based emergy calculation model for building systems. It not only encapsulates the various stages of energy flow but also offers a profound insight into the complex interplay of renewable and non-renewable resources, market dynamics, and the feedback mechanisms that define the sustainability of building systems. This model serves as a robust framework for policymakers, designers, and researchers to evaluate and enhance the environmental performance of buildings, moving towards a more sustainable and efficient built environment.

2.3. LCA-Carbon Footprint Method

Building carbon footprint refers to the total amount of direct and indirect carbon dioxide emissions generated by a building throughout its entire life cycle, from the collection of raw materials, processing and manufacturing, transportation, construction, use and maintenance, to demolition, and waste disposal. It is a significant indicator for measuring the environmental performance of buildings, reflecting their impact on climate change. By reducing the building carbon footprint, the green and low-carbon development of the construction industry can be promoted [43].

The full life cycle carbon footprint calculation model is a systematic evaluation method designed to quantify the carbon emissions produced throughout the entire process of a product or service, from the collection of raw materials, production and manufacturing, transportation and distribution, use and maintenance, to final disposal, and treatment. This model, based on international standards [44], achieves its calculations through the following steps: first, defining the research scope, which includes all relevant processes and stages. Next, collecting and analyzing activity data at each stage of the life cycle, such as energy consumption and material use. Then, applying carbon emission factors to convert these activity data into carbon emissions, constructing a detailed carbon footprint inventory. This model considers both direct and indirect carbon emissions, not only including energy use in the production process but also covering energy consumption in the production of raw materials, transportation, product use, and carbon emissions from waste treatment. By comparing the carbon footprints of different products or services, the model helps enterprises identify reduction potential, optimize product design, and achieve low-carbon transformation. Ultimately, through comprehensive analysis, the model provides a scientific basis for decision-makers, promoting green consumption and sustainable development. Figure 4 presents a carbon footprint assessment framework, which provides a calculation model for the material flow, energy flow, and information flow at each stage of the full life cycle of the building system. For specifics, see Figure 4.

2.4. Neural Network Method

Neural network models have significant advantages in predicting the trends of emergy and carbon footprint in building systems. Firstly, they are capable of handling large amounts of nonlinear data, accurately capturing the complex internal relationships within building systems and the influence of external environmental factors. Secondly, neural networks possess self-learning and adaptive capabilities, which allow them to improve prediction accuracy through continuous training. Moreover, neural network models can handle multi-dimensional input variables, making the predictions more comprehensive and detailed. Finally, the generalization ability of neural network models enables them to cope with new data, predict future trends of emergy and carbon footprint, and provide a scientific basis for the optimization and sustainable development of building systems.

Figure 5 illustrates the design of the neural network model, where Figure 5a represents the standalone building system model; and Figure 5b shows the prediction model with the addition of an energy storage module. By comparing the differences in results between the two, the characteristics of the time-series-based energy storage model can be analyzed, which in turn provides a reference for the research and development of new energy-saving building systems.

(1)

Model Training Process:

The training process of the model includes data preprocessing, model architecture design, parameter optimization, and training strategies. Data preprocessing involves cleaning, standardizing, or normalizing the raw data to ensure the quality and consistency of the input data. Model architecture design determines the number of layers, the number of neurons, activation functions, etc., in the network. Parameter optimization involves adjusting the learning rate, batch size, optimization algorithms, etc., to improve the training effectiveness of the model. Training strategies may include transfer learning, data augmentation, regularization techniques, etc., to prevent overfitting and enhance the generalization ability of the model.

(2)

Test Dataset:

To evaluate the generalization ability of the model, the dataset needs to be divided into training, validation, and test sets. The training set is used for model training, the validation set is used for adjusting model parameters and preventing overfitting, and the test set is used to evaluate the final performance of the model. The test dataset should be independently drawn from real-world application scenarios and should represent the true data distribution that the model will face.

(3)

Model Evaluation Metrics:

Accuracy: The proportion of correctly predicted samples out of the total number of samples.

Precision: The proportion of correctly identified positive samples out of the total number of samples predicted to be positive.

Coefficient of Determination: The degree to which the model explains the variability of the data, with values closer to 1 indicating better model fitting.

3. Case Situation

Basic Introduction and Date Collection

The case study in this paper is an industrial building with a total area of 50,000 square meters, constructed with a reinforced concrete frame structure and designed for a total service life of 50 years. The building is an integrated type combining office and production spaces. Due to the characteristics of industrial building forms, the roof is equipped with a photovoltaic matrix for power generation, and an energy storage module is also set up to recover excess energy for use in the office area’s electricity needs.

The parameters of the energy storage module used are presented in

Table 1. Energy Storage Module Parameter Settings.

No.	Parameter Type	Specific Data
1	Energy Storage System Total Capacity	1000 kWh
2	Battery Type	LiFePO₄
3	Number of Battery Modules	20
4	Maximum Discharge Power	500 kW
5	Conversion Efficiency	Approximately 90%
6	Battery Management System	Monitoring, diagnosis, and protection functions
7	Environmental Adaptability	Operational from −10 °C to 50 °C
8	Floor Area	Approximately 100 square meters
9	Energy Storage Medium	Lithium-ion Battery
10	Single Battery Module Capacity	50 kWh
11	System Voltage	480 V DC
12	Maximum Charging Power	500 kW
13	Battery Cycle Life	≥4000 cycles (at 80% Depth of Discharge)
14	System Redundancy Design	N + 1 Redundancy
15	Safety Features	Protection against overcharging, overdischarging, short circuit, and overtemperature
16	Service Life	10 years

.

The types of data collected include basic data of the building system, emergy conversion rate data, carbon emission factor data, and basic data of energy storage modules. Data source channels include data provided by enterprises, adoption of national standard data, selection of emergy conversion rate data from authoritative journals, and carbon emission factor data from the Intergovernmental Panel on Climate Change (IPCC), which includes three types of carbon emission factors: fossil fuel carbon emission factors, electricity carbon emission factors, and building material carbon emission factors.

4. Results and Discussion

4.1. LCA-Emergy Analysis

The lifecycle emergy research includes three parts: a comparative analysis of the main emergy quantities, changes in emergy sustainability parameters before and after adding the energy storage module, and a sensitivity analysis of the data.

4.1.1. Dominated Contributor of Building System

Figure 6 vividly depicts the emergy profile of an individual building system throughout five distinct phases of its lifecycle, contrasting the emergy values across five separate time intervals from 5 to 50 years. The graph reveals that the building materials phase and the building operation phase are pivotal in shaping the total emergy of the system, with their respective contributions exhibiting an opposing pattern. At the 5-year mark, the emergy from the building materials phase constituted 57% of the system’s total, with the operation phase contributing 32%. Over time, these proportions shift: by the respective data points, they stand at 36.5% and 47%, 21% and 69%, and finally 8.7% and 83.9%. As the usage cycle lengthens, the emergy from the building operation stage increasingly becomes the predominant factor.

Figure 7 provides a further breakdown of these proportions across the five time periods, reaffirming the preeminence of the building operation and materials stages. Refer to the literature [19] for the unit emergy value benchmarks.

4.1.2. Comparison of Emergy Parameters Before and After Adding the Energy Storage Module

To investigate the sustainability of the building system, this study approached from the perspective of emergy and utilized three key indicators for evaluation: Emergy Yield Ratio (EYR), Environmental Load Ratio (ELR), and Emergy Sustainability Index (ESI). Moreover, three different types of feedback subsystems have respective impacts on the variation of sustainability parameters of the building system. This section focuses on a comparative analysis of the effects of these three feedback subsystems and presents their trends of change through Figure 8.

Figure 8a shows the trends in changes of three types of sustainable evaluation indicators after 5 years, while Figure 8b illustrates the differences in the three indicators turning into ranges after a 50-year cycle.

Based on the current linear trend calculations, taking the three types of emergy sustainability parameters for industrial buildings—EYR (Emergy Yield Ratio), ELR (Environmental Load Ratio), and ESI (Emergy Sustainability Index)—as examples, Figure 8 provides a quantitative analysis of the sustainable state of industrial buildings after 5 and 50 years of use. As the building system operates, the greater the system losses and the more consumption, the Environmental Load Ratio (ELR) will gradually increase, and the Sustainability Index (ESI) will also decrease gradually. As shown in Figure 8, after 5 years of use, the differences in the three parameters are 4.1%, 9.2%, and 4.4% respectively, while after 50 years, the parameter differences for the entire building system are 39%, 10%, and 33% respectively. Analyzing the ESI parameter, the decrease is more than 50%, indicating that the sustainability of the entire building system is significantly decreasing. If the building is to continue being used, it must undergo thorough repair and improvement.

4.1.3. Sensitivity Analysis

Sensitivity analysis is of great significance for building systems, primarily manifesting in the following points: Firstly, it can test the accuracy and robustness of the building model by evaluating the model’s performance through the analysis of the impact of parameter changes on indicators; secondly, it provides decision-makers with critical information, helping them to develop more effective strategies based on the impact of parameters on sustainability; finally, it assists design teams in making more sustainable decisions at various stages of the building project, optimizing the sustainability performance of the building system by adjusting design options.

Figure 9 reveals the sensitivity of emergy data across five periods based on the current linear change calculation. The red line in Figure 9 represents the changes within a uniform range across different time periods; the blue line indicates the spatial variation of the uniform characteristics over time. The graph shows that within the analysis range of the 25–75% data segment, there is significant sensitivity change during the period from the 5th to the 20th year. Whether starting from the 25% segment or the middle segment, sensitivity fluctuations are observed. This indicates that for the first 20 years of the building system’s use, it is in a non-equilibrium state, while it reaches an equilibrium state after 20 years. The reason for this phenomenon may also be that the current data calculation relies on linear prediction, which could lead to a relatively stable state in the sensitivity analysis of the later data.

4.2. LCA-Carbon Footprint Analysis

Examining the sustainability of building systems extends beyond emergy analysis to also include the critical dimension of carbon emissions, which has become an indispensable component of the assessment. This investigation concentrates on the five pivotal phases of a building system’s life cycle, conducting meticulous carbon emissions calculations at each stage to provide a holistic view of the system’s carbon footprint across its operational lifespan. Such an analysis enables the precise identification of the primary emission sources, a key step in formulating effective emission reduction tactics.

Moreover, the study will examine three distinct types of feedback effects that could substantially influence carbon emissions. Following these analytical steps, the research will also explore the sensitivity of the results to ensure that the findings offer a robust theoretical and applied foundation for the sustainable progression of building systems. For the carbon emission factors in this section, please consult reference [45].

4.2.1. LCA-Carbon Footprint Analysis of Entire Life Cycle

The comprehensive carbon emissions analysis of a building system’s entire life cycle is segmented into five pivotal stages for detailed examination. The initial stage involves the building materials phase, where the carbon emissions from nine primary construction materials, such as cement and steel, are meticulously calculated. The subsequent stage, construction and transportation, addresses six critical subsystems, including carbon emissions stemming from labor services, water supply and sewage treatment, HVAC systems, electrical installation systems, and communication engineering.

During the building operation stage, the analysis concentrates on the carbon emissions from electricity, heating, and water supply, which are the principal energy consumers in a building’s day-to-day operations and directly influence carbon emissions. The final stage, building demolition, accounts for the carbon emissions related to the recycling and reuse of materials post-demolition, including cement, steel, glass, and diesel, which have a considerable environmental impact.

Through this thorough examination of the five stages, this paper can more precisely evaluate the carbon footprint of the building system across its entire life cycle, thus providing a solid scientific foundation for advancing sustainable practices within the construction industry.

Figure 10 shows a comparison of carbon emissions calculations for the full life cycle of a building system, with a clear trend of carbon emissions increasing at each stage from 5 to 50 years. Overall, the material stage, construction stage, and building operation stage account for the dominant share of emissions. As the usage cycle increases, the carbon emissions from the building operation stage significantly rise, reaching approximately 1193.06 t, 2795.1 t, 4794.02 t, 6633.22 t, and 12,100 t, respectively. The carbon emissions from building materials also gradually increase, at rates of 739.5 t, 1732.5 t, 2971.5 t, 4111.5 t, and 7500 t, respectively. This is due to the inclusion of building material quantities for the maintenance and renovation of industrial buildings in the calculations.

4.2.2. Energy Storage Unit Efficiency Analysis

The photovoltaic energy storage unit in a building system can effectively reduce the building’s energy consumption and carbon emissions. By converting solar energy into electricity through photovoltaic panels and then storing it in the energy storage unit, it provides a stable power supply for the building, reducing reliance on traditional energy sources. Additionally, the photovoltaic energy storage unit increases the building’s energy self-sufficiency, enhancing its energy independence and resilience to risks, especially in situations where there is unstable power supply or emergencies, the energy storage unit can ensure the building’s normal power supply. Moreover, the introduction of photovoltaic energy storage units also helps to alleviate the pressure on the power grid by regulating energy within the building and reducing the impact on the public grid. At the same time, it can enhance the overall intelligence level of the building, optimizing energy distribution and dispatching through an intelligent control system to improve energy utilization efficiency. Figure 11 provides a schematic diagram of the photovoltaic energy storage module in this study.

To calculate the specific values of energy savings, carbon emission reductions, and electricity cost savings provided by a photovoltaic energy storage system for a building system, it is necessary to obtain the energy consumption level of the building, the carbon emission factor of the local power grid, electricity prices, and other information. Here is a specific estimation:

 A. 

Basic Conditions:

• The average electricity price for the industrial building is 1 yuan/kWh.
• The carbon emission factor of the local power grid is 0.5 kg CO₂/kWh (i.e., 0.5 kg of carbon emissions are produced for every kilowatt-hour of electricity consumed).
• The average daily electricity consumption of the building is 5000 kWh.

 B. 

Specific Calculation Results:

(1)

Energy Savings (Electricity Cost Savings):

Annual electricity cost savings = Total capacity of the energy storage system × Number of days in use × Electricity price

Annual electricity cost savings = 1000 kWh × 365 days × 1 yuan/kWh = 365,000 yuan

The electricity cost savings over 5, 10, 20, 30, and 50 years of use are: 1,825,000 yuan, 3,650,000 yuan, 7,300,000 yuan, 10,950,000 yuan, and 18,250,000 yuan, respectively.

(2)

Carbon Emission Reduction:

Annual reduction in carbon emissions = Total capacity of the energy storage system × Number of days in use × Carbon emission factor

Annual reduction in carbon emissions = 1000 kWh × 365 days × 0.5 kg CO₂/kWh = 182,500 kg CO₂

The reduction in carbon emissions over 5, 10, 20, 30, and 50 years of use are: 912,500 kg CO₂, 1,825,000 kg CO₂, 3,650,000 kg CO₂, 5,475,000 kg CO₂, and 9,125,000 kg CO₂, respectively.

(3)

Electricity Cost Savings:

Electricity cost savings refer to the amount of electricity provided by the energy storage system, assuming that the energy storage system can fully utilize its capacity.

Annual electricity savings = Total capacity of the energy storage system × Number of days in use

Annual electricity savings = 1000 kWh × 365 days = 365,000 kWh

The electricity savings over 5, 10, 20, 30, and 50 years of use are: 1,825,000 kWh, 3,650,000 kWh, 7,300,000 kWh, 10,950,000 kWh, and 18,250,000 kWh, respectively.

Calculating the carbon emission reduction rate for building operations over 5, 10, 20, 30, and 50 years, the overall reduction rate is 39.4%, 33.6%, 39.2%, 42.5%, and 38.8%, respectively. It can be seen that the energy storage module has a significant impact on the sustainability of the building system.

It should be noted that the energy storage module in this paper does not consider the maintenance and replacement of the energy storage system and the building, which, to some extent, affects the accuracy of the results. Subsequent research needs to account for these additional costs.

4.2.3. Sensitivity Analysis from Carbon Footprint View

Sensitivity analysis of the basic data for carbon footprint plays a crucial role in the study of carbon emissions in building systems. This type of analysis can reveal the extent to which changes in different parameters affect carbon emissions, thereby providing key information for decision-makers. By conducting sensitivity analysis on the basic data, this paper can identify the variables that have the most significant impact on carbon emissions, which is vital for developing effective carbon emission control and reduction strategies. Moreover, sensitivity analysis can also help the carbon emission behavior of building systems under different conditions, enhancing the reliability of model predictions and thereby providing solid support for the low-carbon transformation and sustainable development of the construction industry. Figure 12 illustrates the trend of sensitivity changes from the perspective of building carbon emission data.

Figure 12 shows the trend of change in the five groups of carbon footprint data. With the use of the building system and the increase in the volume of data, the overall trend is presenting an open-ended pattern. Although the data has not exceeded the lower and upper percentiles, the gap between the reference line and the expected value is increasingly widening. This indicates that the sensitivity is gradually increasing and the level of inaccuracy is rising. Therefore, the increase in data volume needs special attention, and it is necessary to accurately enumerate the source of the data to ensure the accuracy of the research results.

4.3. Neural Network Predictive Analysis

In this segment, the study developed and refined a neural network model designed to forecast the energy performance and carbon emissions of the building system. Considering both the Emergy Sustainable Index (ESI) and carbon emissions, the research performed an in-depth examination of the projected trends for these two pivotal metrics over the upcoming three decades. This analytical process enables the assessment of the building system’s sustainability trajectory over time.

Figure 13 illustrates the projected trajectory of the Emergy Index and carbon emissions over the next 30 years, offering insights into the energy efficiency and environmental implications of the building system. This graphical representation serves as a valuable resource for understanding the system’s future sustainability performance.

Figure 13 reveals the predictive analysis of the trend of changes in the Emergy Sustainable Index (ESI) and the life cycle carbon footprint from two perspectives within the building system. Figure 13A,B show the trend analysis for a 30-year period, while Figure 13C,D present the trend for a 50-year calculation period.

Taking the 30-year cycle trend as an example, from the perspective of ESI, as the usage cycle of the industrial building increases, the ESI index gradually decreases, indicating an increase in the aging of the entire building system. Despite regular maintenance and repairs, the system’s state is still moving towards a less sustainable level from an eco-energy perspective. The trend of carbon footprint change shows an increasing pattern, with a faster increase in carbon emissions in the first 20 years and a gradual stabilization in the last 10 years. Looking at the 50-year usage cycle, the overall trend is similar to that of the 30-year cycle, which also verifies the consistency of the trend changes from the dual perspectives of eco-energy ESI and carbon. The difference is that the ESI’s downward trend is slower in the first 15 years and then becomes rapid in the subsequent 35 years. This is also due to the gradual aging of the building system; despite regular repairs and maintenance, it is still unable to mitigate the trend of a lower ESI state.

To date, the application of neural network models for predictive analysis of the sustainability shifts in building systems has been complemented by research from various other perspectives. Some scholars have utilized linear time series neural networks to assess dynamic state models of Heating, Ventilation, and Air Conditioning (HVAC) systems [46]. Simultaneously, other studies have leveraged statistical analysis techniques to construct neural network models that forecast the electricity demands of buildings equipped with solar power [47]. Additionally, neural network methodologies have been applied to formulate predictive control strategies and to investigate the interplay between heating systems and buildings using artificial neural networks [48]. Recognizing the significance of hot water systems in building energy consumption, neural network-based predictive algorithms have also been developed for water heating applications [49]. Neural network technology has seen extensive deployment across various building subsystems, including electricity supply, heating, and lighting, among others. However, predictive analysis research focused on the sustainability of the entire building system is still relatively scarce. This section concentrates on discussing predictive technologies within the realms of eco-energy and low-carbon emissions.

In conclusion, neural networks are adept at elucidating intricate data patterns, enabling precise forecasts for the shifts in building sustainability. By conducting a thorough analysis of the interconnections between critical metrics like the emergy of building systems and carbon emissions, this study can discern the trends in sustainability and the elements that influence them. Such insights are invaluable to decision-makers, facilitating the optimization of building system design and operation, and advancing the pursuit of sustainable development objectives.

5. Improvement Discussion

To ensure the stability and continuous operation of the entire building system, it is essential to maintain a dynamic balance of material flows, energy flows, and information flows within the system. As an open complex system, the building system relies on external resource inputs and energy supplies to maintain its normal functions. These inputs include, but are not limited to, material supplies, energy supplies, and information technology support. To ensure the continuity of these inputs and the stability of the building system’s state, a comprehensive feedback monitoring system must be established.

This paper proposes a feedback system based on a dual perspective of emergy and carbon emissions, aiming to monitor and evaluate the performance of the building system from different dimensions. The system collects and analyzes the emergy consumption and carbon emission data during the operation of the building, providing real-time monitoring of the system’s environmental impact and energy efficiency. The feedback information is processed and corrected by the control module, where the information control module is responsible for the collection, processing, and decision-making of information, while the robotic repair module is tasked with implementing specific repair and maintenance work. These two modules work in synergy to ensure the accuracy and timeliness of the feedback information, thereby allowing for real-time adjustments to the operation state of the building system. Through this feedback mechanism, the system can promptly address potential issues, providing prompts for energy consumption optimization, carbon emission reduction, structural safety, and more. These prompts not only help in predicting and preventing system failures but also provide decision-making support for building managers, effectively maintaining the balance and efficient operation of the entire building system, ensuring long-term stability and sustainable development of the building system.

Figure 14 presents the design of the intelligent improvement model for this study. Currently, this system has been preliminarily applied to the building system and has improved the sustainability of the entire building system to a certain extent. After operating for 4 years, the system has learned about two instances of building envelope damage through the intelligent feedback system, particularly in the window system, which was caused by anomalies in the power and thermal supplies. These anomalies translated into emergy and carbon footprint values exceeding normal levels, thus saving the entire building system approximately 1000 kWh of electricity and reducing carbon emissions by about 0.5 tCO₂. With the long-term operation of this system, it can be predicted to provide even better monitoring effects for the entire building system.

The overall design of the photovoltaic energy storage system should be optimized, including the selection of high-efficiency photovoltaic cells and energy storage units, as well as a reasonable system configuration, to enhance the efficiency of energy conversion and storage. By adopting the latest photovoltaic technology and high-performance energy storage materials, the carbon emissions per unit of energy can be reduced. Secondly, the intelligent management of the system should be strengthened, utilizing big data and cloud computing technology to monitor and optimize the photovoltaic power generation and energy storage processes in real-time. Through intelligent dispatching, the energy storage strategy can be dynamically adjusted according to actual power demand and photovoltaic power generation, reducing unnecessary energy waste. Furthermore, the life cycle management of the photovoltaic energy storage system should be emphasized, with a commitment to low-carbon principles from the collection of raw materials, through manufacturing, installation, and operation, to the final recycling, and disposal. For example, using recyclable materials, optimizing manufacturing processes, and reducing energy consumption and waste emissions. Through these comprehensive measures, efforts can be made from the four levels of technology, management, policy, and society to effectively reduce the carbon emissions of building systems coupled with photovoltaic energy storage modules, promoting the green and low-carbon development of the construction industry.

6. Conclusions

This article revolves around sustainable building practices. To locate the sustainability of the building system, this study conducts quantitative analysis from two perspectives: the life cycle eco-energy and carbon footprint. It is particularly noteworthy that the case of the building system used in this paper incorporates a battery energy storage module, which is a type of new energy.

The main research findings are as follows:

• The entire building system’s emergy is primarily influenced by the building material stage and the building operation stage, and the changes in both present an inverse trend. In the fifth year, the emergy proportion of the building material stage accounted for 57% of the total, while the operation stage accounted for 32%; as the usage time extends, the respective figures become 36.5% and 47%, 21% and 69%, and 8.7% and 83.9%.
• With the operation of the building system, the system’s losses and consumption increase, leading to a gradual increase in the Environmental Load Rate (ELR), while the Sustainable Parameter (ESI) decreases progressively.
• Overall, the building material stage, construction stage, and building operation stage dominate. As the usage cycle increases, the carbon emissions in the building operation stage significantly increase, reaching 1193.06 t, 2795.1 t, 4794.02 t, 6633.22 t, and 12,100 t, respectively.
• Calculating for building operation periods of 5, 10, 20, 30, and 50 years, the overall carbon emission reduction rates after adding an energy storage module are 39.4%, 33.6%, 39.2%, 42.5%, and 38.8%, respectively. It can be observed that the energy storage module has a significant impact on the sustainability of the building system.
• Taking the 30-year cycle trend as an example, from the ESI perspective, as the usage cycle of industrial buildings increases, the ESI index gradually decreases, indicating an aging increase in the entire building system. The system’s state is still moving towards a less sustainable level. The trend of carbon footprint change shows an increasing pattern, with a faster increase in carbon emissions in the first 20 years, and a more stable increase in the latter 10 years.

The investigation underscores the energy efficiency and environmental implications of a building system across its entire lifecycle, establishing a scientific foundation for the enhancement of building design. Additionally, the integration of coupled energy storage modules has the potential to augment building energy efficiency, curtail energy wastage, and foster the green and low-carbon evolution of buildings. Furthermore, by evaluating carbon emissions, the research aids in promoting a reduction in greenhouse gas emissions within the construction sector and in addressing the challenges posed by climate change. In aggregate, this study not only elevates the sustainability standard within the construction industry but also exerts a positive influence on propelling the societal shift toward a low-carbon economy.

The study is significant in assessing the sustainability of building systems with coupled energy storage modules, but it still has certain shortcomings. Firstly, it may not have fully considered the carbon emissions of the energy storage modules throughout their entire lifecycle, particularly in the manufacturing and disposal stages. Secondly, the research might lack a comprehensive comparison of different types of energy storage technologies, which could result in an incomplete assessment. Moreover, the methods and parameter settings for emergy analysis may be subjective, affecting the accuracy of the assessment.

Future research directions should include: refining the calculation of carbon emissions at each stage of the lifecycle, especially in manufacturing and disposal; comparing the environmental impact of different energy storage technologies; introducing more diverse evaluation indicators; and considering the comprehensive impact of policy, economic, and social factors on sustainability. This will help to assess the sustainability of building systems with coupled energy storage modules more comprehensively and accurately.