**1. Introduction**

With the rapid growth of economy and the increasing consumption of fossil resources, China is facing problems of resource shortage, climate change and environmental governance [1], showing an increasing contradiction between social development and unsustainable energy structure. The overdose of coal combustion, large number of automotive exhaust emissions and improper treatment of pollutants are all leading to serious atmospheric pollution, which seriously threatens the quality of people's lives and has an irreversible impact overall on the ecological environment [2]. In order to mitigate the effects of pollution emissions, it is urgent to develop and promote highly efficient and green energy technologies in order to reach social sustainability. According to China Energy Statistical Yearbook (2017), 50% to 60% of particulate matter 2.5 (PM 2.5) air pollution comes from coal combustion and 20% to 30% from oil combustion. Meanwhile, the National Development and Reform Commission and the National Energy Administration of China has proposed that, by 2020, the total amount of electricity replacing coal and oil combustion is estimated to reach 130 million tons of standard coal, and the proportion of electric energy in the end-stage energy consumption should be 27%, increasing by about 1.5%. The additional consumption of electricity in the "13th Five-Year Plan" is set to be

450 billion kWh [3]. Under the global trend of low-carbon green development, "Two substitutions", which includes both clean-energy substitution and electric power substitution, is meant to guide the energy structure optimal reform [4]. Therefore, studies on electric power substitution potential will give suggestions and guidance for its further sustainable development.

As an energy consumption pattern [5], electric power substitution can make further use of the environmental capacity in different regions, in order to reach the balance of pollutants emissions and optimal resources allocation [6,7]. By replacing coal and fuel with electric power, pollutions can be effectively cut down and energy efficiency improved [8]. With the development of energy technology revolution, electric power substitution can be applied into transportations, electric boilers, electric kilns, electric heating and electric cookers, replacing fossil resources such as oil and coal. At present, the industrial energy efficiency is relatively low. Clean energy substitution would effectively improve the efficiency of energy utilization [9]. The market potential for promoting electric power substitution in China is about 22 trillion kWh. The potential of substituting coal and oil with electricity is prospectively 18 trillion and 400 billion kWh, showing huge potential of the substitution market. Presently, electric power substitution is gradually becoming a research focus both in China and globally. Scholars have made achievements regarding electric power substitution with two different approaches: one is the technical and economic research of the power substitution, and the other is related to methods used for forecasting.

By analyzing the technical and economic efficiency of energy substitutions, Wu et al. [10] proposed that the sustainable use of energy would be the main direction of future development. Based on the system dynamics model, Song et al. [11] analyzed the emission reduction effect of the renewable energy substitution in China. Besides, while researching energy substitution, many scholars achieved energy substitutions on the power supply side by combining multiple renewable energy resources [12]. He et al. [13] introduced the environmental utility in the environmental consumption (EUEC) model to discuss the relationship between urban energy consumption and environmental utility changes. Barreto [14] demonstrated the dynamic substitution effect of renewable energy replacing fossil fuel by building a theoretical framework that incorporates alternative energy and traditional fossil energy into the endogenous growth model. Liu et al. [15] established a dynamic system model combining multiple renewable energy sources and made an empirical analysis. By changing the proportion of electric vehicles in the power system, André et al. [16] compared and analyzed the emission reduction benefits of the system under multiple scenarios. Kumar et al. [17] discussed the innovative capabilities that enterprises need to adopt, such as pollution prevention and clean technology strategies, in order to achieve sustainable development.

The development of electric power substitution is influenced by many factors, such as technology, economy, environmental protection requirements, policy measures, demand response, etc. Wu et al. [18] pointed out that the initial investment was high; therefore, promoting the projects is facing greater resistance. Similarly, Shaligram [19] argued that the current barriers to substitution mainly contained the high cost of substitute technology. By summarizing the practical experience in the Jiangsu Province, Li [20] found that there were some problems in the promotion work, such as insufficient policy support, less response from users and lower technology level. Combined with various factors, Liang et al. [21] constructed the evaluation index model of power substitution scheme and analyzed its substitution potential. Lu and Xie [22] empirically analyzed the intensity of enterprises conducting clean substitution under the pressure of carbon emission reduction. Faced with the carbon emission reduction, the sense of conducting cleaner production will increasingly rise.

For forecasting methods, many scholars have made many achievements. Common methods include single forecasting models and combined forecasting models, such as Support Vector Machine (SVM), artificial neural network, genetic algorithm, grey forecasting model, and a combination of forecasting methods. Wei et al. [23] combined a neural network and statistical linear model to predict wind power output. Michael et al. [24] incorporated the forecasting model based on machine learning to predict the household energy consumption. Zhang et al. [25] proposed a forecasting model for building demand response with random forest and ensemble learning method. Wu et al. [26] forecasted the short-term load of a power system based on generalized regression neural network method. Based on artificial neural network method, Xia et al. [27] combined a virtual instrument and radial basis function neural network and created long-term, medium-term and short-term load forecasting. Shan et al. [28] used the extremum learning machine (ELM) method based on Back Propagatio (BP) and SVM to forecast photovoltaic (PV) generation. Chen and Yu [29] used SVM on wind signal prediction. Lee and Tong [30] combined grey model and incorporating genetic algorithm together to forecast and analyze the demand for electric power. A hybrid model composed by SVM and a Seasonal Auto Regressive Integrated Moving Average was proposed for short-term PV generation forecasting [31]. Yu and Xu [32] used an optimized genetic algorithm and improved BP neural network (BPNN) to forecast the load of natural gas. In the actual implementation process of power substitution work, an accurate forecast on power consumption and the changing trend can provide data support and policy guidance for further power substitution work promoting [33,34]. Sun et al. [35] forecasted the potential of power substitution using particle swarm optimization (PSO)-SVM. Yin [36] established a grey energy demand-forecasting model to forecast the terminal energy demand in Beijing. Zheng [37] constructed the potential forecasting model on rural electric power substitution, and made middle and long-term analysis of electricity consumption. Li [38] used the improved TOPSIS method to analyze the potential of regional power substitution.

Above all, scholars have made achievements in presenting electric power substitution, promoting methods and digging related influencing factors [39]. However, few have mentioned the developing potential forecast of the substitution works. Most existing works on potential analysis used the comprehensive evaluation method, which cannot show the future developing trend of the power substitutions. Therefore, in order to make up for the deficiencies of the existing research on the potential analysis of power substitution, a CSO-ELM model based on the Pearson correlation test is constructed to forecast the market potential of electric power substitution projects. The main contributions of this work are summarized as follows.


The paper is organized as follows: Section 2 presents the structures and features of the forecasting method. Section 3 introduces the current situation of the electric power substitution in China and gives summary of all influencing factors. In Section 4, specific data is used to verify the effectiveness of the proposed method, and four scenarios are given to address further discussion of the future development of the substitution work. Finally, the conclusion is given in Section 5.
