Search Results (59)

Wind power output sequences exhibit strong randomness and intermittency characteristics; traditional single forecasting models struggle to capture the internal features of sequences and are highly susceptible to interference from high-frequency noise and predictive accuracy is still notably poor at the peaks where the power curve undergoes abrupt changes. To address the poor fitting at peaks, a short-term wind power forecasting method based on the improved Informer model is proposed. First, the temporal convolutional network (TCN) is introduced to enhance the model’s ability to capture regional segment features along the temporal dimension, enhancing the model’s receptive field to address wind power fluctuation under varying environmental conditions. Next, a discrete cosine transform (DCT) is employed for adaptive modeling of frequency dependencies between channels, converting the time series data into frequency domain representations to extract its frequency features. These frequency domain features are then weighted using a channel attention mechanism to improve the model’s ability to capture peak features and resist noise interference. Finally, the Informer generative decoder is used to output the power prediction results, this enables the model to simultaneously leverage neighboring temporal segment features and long-range inter-temporal dependencies for future wind-power prediction, thereby substantially improving the fitting accuracy at power-curve peaks. Experimental results validate the effectiveness and practicality of the proposed model; compared with other models, the proposed approach reduces MAE by 9.14–42.31% and RMSE by 12.57–47.59%. Full article

We explored the stationarity, trend, and seasonality of the hive weight and in-hive temperature of ten managed honey bee (Apis mellifera) colonies at a research apiary of the Carl Hayden Bee Research Center in Tucson, Arizona, USA. The hives were monitored with electronic scales and in-hive temperature sensors from June to October 2022. The weight and temperature were recorded every five minutes around the clock. The collected data were curated into 2160 timestamped weight and 2160 timestamped temperature observations. We performed a systematic autoregressive integrated moving average (ARIMA) time series analysis to answer three fundamental questions: (a) Does seasonality matter in the ARIMA forecasting of hive weight and in-hive temperature? (b) To what extent do the best forecasters of one hive generalize to other hives? and (c) Which time series type (i.e., hive weight or in-hive temperature) is better predictable? Our principal findings were as follows: (1) The hive weight and in-hive temperature series were not white noise, were not normally distributed, and, for most hives, were not difference- or trend-stationary; (2) Seasonality matters, in that seasonal ARIMA (SARIMA) forecasters outperformed their ARIMA counterparts on the curated dataset; (3) The best hive weight and in-hive temperature forecasters of the ten monitored colonies appeared to be colony-specific; (4) The accuracy of the hive weight forecasts was consistently higher than that of the in-hive temperature forecasts; (5) The weight and temperature forecasts exhibited common qualitative patterns. Full article

Accurate multivariate time series forecasting remains a major challenge in various real-world applications, primarily due to the limitations of existing models in capturing multiscale temporal dependencies and effectively integrating external data. To address these issues, we propose MSP-EDA, a novel multivariate time series forecasting framework that integrates multiscale patching and external data enhancement. Specifically, MSP-EDA utilizes the Discrete Fourier Transform (DFT) to extract dominant global periodic patterns and employs an adaptive Continuous Wavelet Transform (CWT) to capture scale-sensitive local variations. In addition, multiscale patches are constructed to capture temporal patterns at different resolutions, and a specialized encoder is designed for each scale. Each encoder incorporates temporal attention, channel correlation attention, and cross-attention with external data to capture intra-scale temporal dependencies, inter-variable correlations, and external influences, respectively. To fuse information from different temporal scales, we introduce a trainable global token that serves as a variable-wise aggregator across scales. Extensive experiments on four public benchmark datasets and three real-world vector database datasets that we collect demonstrate that MSP-EDA consistently outperforms state-of-the-art methods, achieving particularly notable improvements on vector database workloads. Ablation studies further confirm the effectiveness of each module and the adaptability of MSP-EDA to complex forecasting scenarios involving external dependencies. Full article

An analysis of the possibilities of using alternative energy to solve the problem of electricity shortages in developing countries shows that solar energy can potentially play an essential role in the fuel and energy complex. The geographical location, on the one hand, and the global development of solar energy technologies, on the other, create an opportunity for a fairly complete and rapid solution to problems of insufficient energy supply. An autonomous solar installation is expensive; 50% of the cost is solar modules, 45% of the cost consists of other elements (battery, inverter, charge controller), and 5% is for other materials. This work proposes the most efficient PV system, based on the technical characteristics of the SB and AB. It has a direct connection between the SB and AB and provides almost full use of the solar panel’s installed power with a variable orientation to the Sun. The development of a small solar photovoltaic (PV) installation, operating both in parallel with the grid and in autonomous mode, can improve the power supply of household consumers more efficiently and faster than the development of a large energy system. It is suggested that two minimized criteria be used to create a model for forecasting FOU. This model can be used with a genetic algorithm to make a prediction that fits a specific case, such as a time series representation based on discrete fuzzy sets of the second type. The goal is to make decisions that are more valid and useful by creating a forecast model and algorithms for analyzing small PV indicators whose current values are shown by short time series and automating the processes needed for forecasting and analysis. Full article

Background: This study addresses the challenge of predicting data sequences characterized by a mix of partial linearity and partial nonlinearity. Traditional forecasting models often struggle to accurately capture the complex patterns of change within the data. Methods: To this end, this study introduces a novel polynomial-driven discrete grey power model (PFDPGM(1,1)) that includes time perturbation parameters, enabling a flexible representation of complex variation patterns in the data. The model aims to determine the accumulation order, nonlinear power exponent, time perturbation parameter, and polynomial degree to minimize the fitting error under various criteria. The estimation of unknown parameters is carried out by leveraging a hybrid optimization algorithm, which integrates Particle Swarm Optimization (PSO) and the Grey Wolf Optimization (GWO) algorithm. Results: To validate the effectiveness of the proposed model, the annual total renewable energy consumption in the BRICS countries is used as a case study. The results demonstrate that the newly constructed polynomial-driven discrete grey power model can adaptively fit and accurately predict data series with diverse trend change characteristics. Conclusions: This study has achieved a significant breakthrough by successfully developing a new forecasting model. This model is capable of handling data sequences with mixed trends effectively. As a result, it provides a new tool for predicting complex data change patterns. Full article

Influenced by the hydrogeological structure and other factors, the change in groundwater depth shows seasonal fluctuation characteristics. Human activities have disrupted the long-term stable pattern of groundwater change, which makes the short-term prediction of groundwater depth important. To cope with the emergence of short-term groundwater prediction scenarios, for the first time, a discrete grey seasonal model with fractional order accumulation is proposed in this paper (FDGSM(1,1)). First, the DGM(1,1) model, which has a relative advantage over fluctuating data, was chosen as the basis for the transformation of the proposed model. Then, the fractional order accumulation operator is used to reduce the seasonal fluctuations in the data series. Finally, grey seasonal variables are introduced to construct the time response function. The proposed model has the basic properties of the traditional grey forecasting model, which is proven to be stable and seasonal. Additionally, the prediction performance of the proposed model is verified in a real scenario of Handan groundwater. This paper expands the seasonal prediction field of the grey prediction model, enriches the research system of the grey system theory and fractional order, and has a positive influence on the short-term prediction of groundwater depth. Full article

Forecasting of time series data presents some challenges because the data’s nature is complex and therefore difficult to accurately forecast. This study presents the design and development of a novel forecasting system that integrates efficient data processing techniques with advanced machine learning algorithms to improve time series forecasting across the sustainability domain. Specifically, this study focuses on solar irradiation forecasting in Riyadh, Saudi Arabia. Efficient and accurate forecasts of solar irradiation are important for optimizing power production and its smooth integration into the utility grid. This advancement supports Saudi Arabia in Vision 2030, which aims to generate and utilize renewable energy sources to drive sustainable development. Therefore, the proposed forecasting system has been developed to the parameters characteristic of the Riyadh region environment, including high solar intensity, dust storms, and unpredictable weather conditions. After the cleaning and filtering process, the filtered dataset was pre-processed using the standardization method. Then, the Discrete Wavelet Transform (DWT) technique has been applied to extract the features of the pre-processed data. Next, the extracted features of the solar dataset have been split into three subsets: train, test, and forecast. Finally, two different machine learning techniques have been utilized for the forecasting process: Support Vector Machine (SVM) and Gaussian Process (GP) techniques. The proposed forecasting system has been evaluated across different time horizons: one-day, five-day, ten-day, and fifteen-day ahead. Comprehensive evaluation metrics were calculated including accuracy, stability, and generalizability measures. The study outcomes present the proposed forecasting system which provides a more robust and adaptable solution for time-series long-term forecasting and complex patterns of solar irradiation in Riyadh, Saudi Arabia. Full article

To develop agricultural risk management strategies, the early identification of water deficits during the growing cycle is critical. This research proposes a deep learning hybrid approach for multi-step soil moisture forecasting in the Bundaberg region in Queensland, Australia, with predictions made for 1-day, 14-day, and 30-day, intervals. The model integrates Geospatial Interactive Online Visualization and Analysis Infrastructure (Giovanni) satellite data with ground observations. Due to the periodicity, transience, and trends in soil moisture of the top layer, time series datasets were complex. Hence, the Maximum Overlap Discrete Wavelet Transform (moDWT) method was adopted for data decomposition to identify the best correlated wavelet and scaling coefficients of the predictor variables with the target top layer moisture. The proposed 3-phase hybrid moDWT-Lasso-LSTM model used the Least Absolute Shrinkage and Selection Operator (Lasso) method for feature selection. Optimal hyperparameters were identified using the Hyperopt algorithm with deep learning LSTM method. This proposed model’s performances were compared with benchmarked machine learning (ML) models. In total, nine models were developed, including three standalone models (e.g., LSTM), three integrated feature selection models (e.g., Lasso-LSTM), and three hybrid models incorporating wavelet decomposition and feature selection (e.g., moDWT-Lasso-LSTM). Compared to alternative models, the hybrid deep moDWT-Lasso-LSTM produced the superior predictive model across statistical performance metrics. For example, at 1-day forecast, The moDWT-Lasso-LSTM model exhibits the highest accuracy with the highest $R^2\approx 0.92469$ and the lowest RMSE $\approx 0.97808$, MAE $\approx 0.76623$, and SMAPE $\approx 4.39700$%, outperforming other models. The moDWT-Lasso-DNN model follows closely, while the Lasso-ANN and Lasso-DNN models show lower accuracy with higher RMSE and MAE values. The ANN and DNN models have the lowest performance, with higher error metrics and lower R2 values compared to the deep learning models incorporating moDWT and Lasso techniques. This research emphasizes the utility of the advanced complementary ML model, such as the developed moDWT-Lasso-LSTM 3-phase hybrid model, as a robust data-driven tool for early forecasting of soil moisture. Full article

From June to October, 2022, we recorded the weight, the internal temperature, and the hive entrance video traffic of ten managed honey bee (Apis mellifera) colonies at a research apiary of the Carl Hayden Bee Research Center in Tucson, AZ, USA. The weight and temperature were recorded every five minutes around the clock. The 30 s videos were recorded every five minutes daily from 7:00 to 20:55. We curated the collected data into a dataset of 758,703 records (280,760–weight; 322,570–temperature; 155,373–video). A principal objective of Part I of our investigation was to use the curated dataset to investigate the discrete univariate time series forecasting of hive weight, in-hive temperature, and hive entrance traffic with shallow artificial, convolutional, and long short-term memory networks and to compare their predictive performance with traditional autoregressive integrated moving average models. We trained and tested all models with a 70/30 train/test split. We varied the intake and the predicted horizon of each model from 6 to 24 hourly means. Each artificial, convolutional, and long short-term memory network was trained for 500 epochs. We evaluated 24,840 trained models on the test data with the mean squared error. The autoregressive integrated moving average models performed on par with their machine learning counterparts, and all model types were able to predict falling, rising, and unchanging trends over all predicted horizons. We made the curated dataset public for replication. Full article

In the dynamic and uncertain stock market, precise forecasting and decision-making are crucial for profitability. Traditional deep neural networks (DNN) often struggle with capturing long-term dependencies and multi-scale features in complex financial time series data. To address these challenges, we introduce CMR-DQN, an innovative framework that integrates discrete wavelet transform (DWT) for multi-scale data analysis, temporal convolutional network (TCN) for extracting deep temporal features, and a GRU–LSTM–Attention mechanism to enhance the model’s focus and memory. Additionally, CMR-DQN employs the Rainbow DQN reinforcement learning strategy to learn optimal trading strategies in a simulated environment. CMR-DQN significantly improved the total return rate on six selected stocks, with increases ranging from 20.37% to 55.32%. It also demonstrated substantial improvements over the baseline model in terms of Sharpe ratio and maximum drawdown, indicating increased excess returns per unit of total risk and reduced investment risk. These results underscore the efficiency and effectiveness of CMR-DQN in handling multi-scale time series data and optimizing stock market decisions. Full article

Saltwater intrusion is an essential problem in estuaries that can threaten the ecological environment, especially in high-salinity situations. Therefore in this paper, traditional multiple linear regression (MLR) and artificial neural network (ANN) modeling are applied to forecast overall and high salinity in the Lower Scheldt Estuary, Belgium. Mutual information (MI) and conditional mutual information (CMI) are used to select optimal driving forces (DFs), with the daily discharge (Q), daily water temperature (WT), and daily sea level (SL) selected as the main DFs. Next, we analyze whether applying a discrete wavelet transform (DWT) to remove the noise from the original time series improves the results. Here, the DWT is applied in Signal-hybrid (SH) and Within-hybrid (WH) frameworks. Both the MLR and ANN models demonstrate satisfactory performance in daily overall salinity simulation over the Scheldt Estuary. The relatively complex ANN models outperform MLR because of their capabilities of capturing complex interactions. Because the nonlinear relationship between salinity and DFs is variable at different locations, the performance of the MLR models in the midstream region is far inferior to that in the downstream region during spring and winter. The results reveal that the application of DWT enhances simulation of both overall and high salinity in this region, especially for the ANN model with the WH framework. With the effect of Q decline or SL rise, the salinity in the middle Scheldt Estuary increases more significantly, and the ANN models are more sensitive to these perturbations. Full article

The literature on discrete valued time series is expanding very fast. Very often we see new models with very similar properties to the existing ones. A natural question that arises is whether the multitude of models with very similar properties can really have a practical purpose or if they mostly present theoretical interest. In the present paper, we consider four models that have negative binomial marginal distributions and are autoregressive in order 1 behavior, but they have a very different generating mechanism. Then we try to answer the question whether we can distinguish between them with real data. Extensive simulations show that while the differences are small, we still can discriminate between the models with relatively moderate sample sizes. However, the mean forecasts are expected to be almost identical for all models. Full article

Accurate and reliable medium- and long-term load forecasting is crucial for the rational planning and operation of power systems. However, existing methods often struggle to accurately extract and capture long-term dependencies in load data, leading to poor predictive accuracy. Therefore, this paper proposes a medium- and long-term residential load forecasting method based on FEDformer, aiming to capture long-term temporal dependencies of load data in the frequency domain while considering factors such as electricity prices and temperature, ultimately improving the accuracy of medium- and long-term load forecasting. The proposed model employs Discrete Cosine Transform (DCT) for frequency domain transformation of time-series data to address the Gibbs phenomenon caused by the use of Discrete Fourier Transform (DFT) in FEDformer. Additionally, causal convolution and attention mechanisms are applied in the frequency domain to enhance the model’s capability to capture long-term dependencies. The model is evaluated using real-world load data from power systems, and experimental results demonstrate that the proposed model effectively learns the temporal and nonlinear characteristics of load data. Compared to other baseline models, DCTformer improves prediction accuracy by 37.5% in terms of MSE, 26.9% in terms of MAE, and 26.24% in terms of RMSE. Full article

Neural networks have become widely employed in streamflow forecasting due to their ability to capture complex hydrological processes and provide accurate predictions. In this study, we propose a framework for monthly runoff prediction using antecedent monthly runoff, water level, and precipitation. This framework integrates the discrete wavelet transform (DWT) for denoising, variational modal decomposition (VMD) for sub-sequence extraction, and gated recurrent unit (GRU) networks for modeling individual sub-sequences. Our findings demonstrate that the DWT–VMD–GRU model, utilizing runoff and rainfall time series as inputs, outperforms other models such as GRU, long short-term memory (LSTM), DWT–GRU, and DWT–LSTM, consistently exhibiting superior performance across various evaluation metrics. During the testing phase, the DWT–VMD–GRU model yielded RMSE, MAE, MAPE, NSE, and KGE values of 245.5 m³/s, 200.5 m³/s, 0.033, 0.997, and 0.978, respectively. Additionally, optimal sliding window durations for different input combinations typically range from 1 to 3 months, with the DWT–VMD–GRU model (using runoff and rainfall) achieving optimal performance with a one-month sliding window. The model’s superior accuracy enhances water resource management, flood control, and reservoir operation, supporting better-informed decisions and efficient resource allocation. Full article

Non-neural machine learning (ML) and deep learning (DL) are used to predict system failures in industrial maintenance. However, only a few studies have assessed the effect of varying the amount of past data used to make a prediction and the extension in the future of the forecast. This study evaluates the impact of the size of the reading window and of the prediction window on the performances of models trained to forecast failures in three datasets of (1) an industrial wrapping machine working in discrete sessions, (2) an industrial blood refrigerator working continuously, and (3) a nitrogen generator working continuously. A binary classification task assigns the positive label to the prediction window based on the probability of a failure to occur in such an interval. Six algorithms (logistic regression, random forest, support vector machine, LSTM, ConvLSTM, and Transformers) are compared on multivariate time series. The dimension of the prediction windows plays a crucial role and the results highlight the effectiveness of DL approaches in classifying data with diverse time-dependent patterns preceding a failure and the effectiveness of ML approaches in classifying similar and repetitive patterns preceding a failure. Full article