Load Forecasting Research Articles

Enhanced Sequence-to-Sequence Deep Transfer Learning for Day-Ahead Electricity Load Forecasting

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. Among the research challenges on a global scale, the investigation of deep transfer learning (DTL) in the field of electricity load forecasting represents a fundamental effort that can inform artificial intelligence applications in general. In this paper, a comprehensive study is reported regarding day-ahead electricity load forecasting. For this purpose, three sequence-to-sequence (Seq2seq) deep learning (DL) models are used, namely the multilayer perceptron (MLP), the convolutional neural network (CNN) and the ensemble learning model (ELM), which consists of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL, emphasizing the way the datasets are trained and fine-tuned for higher forecasting accuracy. In order to implement the forecasting strategies using deep learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1–24 h) for each month of the year for the Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. Four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only the Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for the Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) involves the training of the DL models using the Lesvos dataset, and the testing period is performed directly on the Chios dataset without fine-tuning. The fourth strategy is a multi-task deep learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. The results obtained demonstrate that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, DTL Case 1 and 2 outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it is concluded that the MLP model presents the best monthly forecasts with MAPE values of 6.24% and 6.01% for the first two cases, the CNN model presents the best monthly forecasts with MAPE values of 5.57% and 5.60%, respectively, and the ELM model achieves the best monthly forecasts with MAPE values of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve.

Peak shaving at system level with a large district heating substation using deep learning forecasting models

The decarbonisation of urban district heating (DH) systems requires increased heating grid flexibility. Therefore, this article examines the optimised operation of a tank thermal energy storage (TTES) on the secondary side of a new DH substation for an industrial site in a German city, in order to shave the peaks of the whole DH system and thus reduce the need for heat-only boilers (HOB). The accuracy of heat load and return temperature forecasts for both the industrial consumer and the DH grid is critical to the performance of the optimisation-based operating strategy of the TTES. Therefore, long short-term memory neural networks are used in combination with continuous model updates through incremental learning to create two forecasting scenarios, one using only preceding data for the forecasts and the other including future weather data. The results show that high forecasting accuracy is most relevant for reducing the annual maximum peak, with a reduction of 2.8% in the preceding data scenario, 4% with future weather data and 7% in a benchmark with perfect forecasts. The economic viability of the storage through HOB heat savings is primarily affected by lower forecasting accuracy when the additional cost of HOB heat is less than 60 €/MWh.

Performance investigation and operation optimization of an innovative hybrid renewable energy integration system for commercial building complex and hydrogen vehicles

With the increasing in energy demands and carbon emissions of building and transport sectors, improving the penetration of renewable resources in these areas are inevitable trends. To further develop the theoretical method of energy integrated system in building/transportation area, load forecasting of commercial building complex and hydrogen vehicles are determined, a novel hybrid renewable energy integration system is presented and studied. Thermal, economic and environmental performances for poly-generation system are performed and optimized, optimal performance and configuration are obtained by NSGA-II algorithm and TOPSIS-Shannon entropy weight method. In addition, operating performance characteristics of integration system during typical weekday and weekend in different seasons are analyzed, the influences of critical parameters on comprehensive performances of integrated system are also conducted. The results showed that optimal exergetic efficiency, levelized cost of product (LCOP) and levelized CO2 emissions of product (LCEP) are 12.61 %, 0.0711 $/kWh and 0.0185 kg/kWh. Furthermore, thermodynamic performances of proposed system decreases while LCOP and LCEP rise with the increasing in HVs stock. Biomass and purchased electricity prices have different impacts on system comprehensive performances. In general, this study provides a new alternative for multiple renewable energy integrated system optimization in building and transportation sectors.

Short-Term Electrical Load Forecasting Using an Enhanced Extreme Learning Machine Based on the Improved Dwarf Mongoose Optimization Algorithm

Accurate short-term electrical load forecasting is crucial for the stable operation of power systems. Given the nonlinear, periodic, and rapidly changing characteristics of short-term power load forecasts, this paper introduces a novel forecasting method employing an Extreme Learning Machine (ELM) enhanced by an improved Dwarf Mongoose Optimization Algorithm (Local escape Dwarf Mongoose Optimization Algorithm, LDMOA). This method addresses the significant prediction errors of conventional ELM models and enhances prediction accuracy. The enhancements to the Dwarf Mongoose Optimization Algorithm include three key modifications: initially, a dynamic backward learning strategy is integrated at the early stages of the algorithm to augment its global search capabilities. Subsequently, a cosine algorithm is employed to locate new food sources, thereby expanding the search scope and avoiding local optima. Lastly, a “madness factor” is added when identifying new sleeping burrows to further widen the search area and effectively circumvent local optima. Comparative analyses using benchmark functions demonstrate the improved algorithm’s superior convergence and stability. In this study, the LDMOA algorithm optimizes the weights and thresholds of the ELM to establish the LDMOA-ELM prediction model. Experimental forecasts utilizing data from China’s 2016 “The Electrician Mathematical Contest in Modeling” demonstrate that the LDMOA-ELM model significantly outperforms the original ELM model in terms of prediction error and accuracy.

How to better match predicted loads of district heating system: A novel control approach focused on coupling source and network by data-driven methods

Deconstructing the load forecast into appropriate control parameters is essential for effective intelligent heating control. Drawing from the predicted load, a novel heating control approach is proposed, emphasizing the integration of source and network. The heating regulation of the energy station is achieved through controlling the supply water temperature, while the thermal entrance of the heating network is regulated by adjusting the flow rate using valve control. The heat transfer mechanism influencing the regulation of District Heating Systems (DHSs) operation and the alignment of supply and demand are analyzed to deconstruct the four key factors: load, flow, load-flow ratio, and supply water temperature. Multiple Linear Regression (MLR) method is employed to formulate the parameter equations relating to supply water temperature and valve opening. Given the uncertainty interference in DHS in practice, the model undergoes periodic dynamic revisions. The model’s validity is confirmed by the empirical data from three different heating seasons. The average absolute deviation of the calculated supply water temperature and valve opening from the actual DHS is 0.42℃ and 1.12%, respectively. When implemented in an actual system, the approach effectively decreased gas consumption by 29.3% while effectively fulfilling heating requirements.

Building heating load forecasting based on the theory of transient heat transfer and deep learning

Reliable and accurate heating load forecasting can provide comprehensive information for the monitoring and control of Heating, Ventilation, and Air Conditioning (HVAC) in buildings, which reduce uncertainty on the load demand of energy effectively. Data-driven method has demonstrated a potential to forecast heating load, but current methods generally lack the consideration of features on model forecasting performance and applicability. Based on the theory of transient heat transfer and conduction transfer function for building hourly heating load calculation, this study proposes an idea that comprehensively selects physical variables affecting the hourly dynamic changes of the building heating load as features, which enhances the persuasiveness of selecting datasets features. Then we use the deep learning method to build short-term heating load forecasting models, and explore the influence of different feature combinations and time steps on the model forecasting performance. Combining the physical property of building heat gains, we divide the features into external heat gains, internal heat gains and historical heating load and then show their performance of models at different time steps. It is shown that the two-hour data of external heat gains and internal heat gains, the three-hour data of past heat load have the highest value. The best model can achieve a mean absolute error of 0.153 kW and a mean absolute percentage error of 6.2 %. These findings are helpful for researchers to select more relevant features to forecast heating load in buildings and improve their models through physical aspect.

Short-term power load forecasting for integrated energy system based on a residual and attentive LSTM-TCN hybrid network

In the context of Integrated Energy System (IES), accurate short-term power demand forecasting is crucial for ensuring system reliability, optimizing operational efficiency through resource allocation, and supporting effective real-time decision-making in energy management. However, achieving high forecasting accuracy faces significant challenges due to the inherent complexity and stochastic nature of IES’s short-term load profiles, resulting from diverse consumption patterns among end-users and the intricate coupling within the network of interconnected energy sources. To address this issue, a dedicated Short-Term Power Load Forecasting (STPLF) framework for IES is proposed, which relies on a newly developed hybrid deep learning architecture. The framework seamlessly combines Long Short-Term Memory (LSTM) with Temporal Convolutional Network (TCN), enhanced by an attention mechanism module. By merging these methodologies, the network leverages the parallel processing prowess of TCN alongside LSTM’s ability to retain long-range temporal information, thus enabling it to dynamically concentrate on relevant sections of time series data. This synergy leads to improved prediction accuracy and broader applicability. Furthermore, the integration of residual connections within the network structure serves to deepen its learning capabilities and enhance overall performance. Ultimately, results from a real case study of a user-level IES demonstrate that the Mean Absolute Percentage Error (MAPE) of the proposed framework on the test set is 2.35%. This error rate is lower than the averages of traditional methods (3.43%) and uncombined single submodules (2.80%).

Optimization research on short-term load forecasting method for electric vehicles based on SSA-SVM

In order to improve the accuracy of short-term electric vehicle load forecasting, a combined forecasting model based on Sparrow Search Algorithm (SSA) and Support Vector Machine (SVM) is constructed. Using SVM model to predict electric vehicle load, accelerating the convergence speed of the prediction model through sparrow search algorithm, conducting global optimization in the solution space, expressing the impact of calculated parameters on the model through fitness, searching for the optimal model parameter data, and improving the overall accuracy of the prediction model. Through simulation experiments, comparing the prediction results of SVM models, and SSA-SVM shows better performance in electric vehicle load prediction.

Improved Autuoformer Electricity load forecasting based on model fusion

The development of the power system is undergoing rapid changes. The future direction of power system development is inevitably smart grids. This paper proposes an optimization of the Autoformer model based on model fusion to improve the accuracy of electricity load forecasting. By incorporating the predictive results of traditional statistical multivariate linear regression (MLR) and machine learning method LightGBM into the Autoformer model, we aim to fully leverage the strengths of both traditional statistical and machine learning approaches to enhance the predictive accuracy of the Autoformer model. Experimental results, using mean MAE and MSE as the evaluation metrics, demonstrate that the algorithm proposed in this paper exhibits better performance in the prediction results.

Technical and economic study of renewable-energy-powered system for a newly constructed city in China

The power and transportation sectors are major carbon emission sources of cities in China, meanwhile, urbanization and industrialization remain the most important impetus for the Chinese economy. Thus, urban-level carbon mitigation is critical for China to realize a low carbon development strategy. This study designs two renewable-energy power-generation dominated power systems for a totally newly built Chinese city, Xiongan, considering emerging technologies, such as vehicle-to-grid as an energy storage facility and geothermal as a local renewable energy resource. The new energy systems are assessed from both economic and carbon emission aspects based on short &long terms power load forecasts. The simulation results shows that the optimal short-term system is a photovoltaic (PV)/geothermal generator/grid purchase/100 Li battery/converter. For the short term, the system's net present cost (NPC) is approximately $8.26B, and the average cost of valuable electrical energy (COE) produced by the system is approximately $0.0942/kWh. The optimal long-term system is a PV/geothermal generator /V2G/ converter, the NPC of the optimal system is approximately $47.7B, and the COE of the system is approximately $0.078/kWh. Energy bill and carbon emissions can both be cut sharply for the city if it adopts these new types of renewable energy dominated systems.

Deriving Input Variables through Applied Machine Learning for Short-Term Electric Load Forecasting in Eskilstuna, Sweden

As the demand for electricity, electrification, and renewable energy rises, accurate forecasting and flexible energy management become imperative. Distribution network operators face capacity limits set by regional grids, risking economic penalties if exceeded. This study examined data-driven approaches of load forecasting to address these challenges on a city scale through a use case study of Eskilstuna, Sweden. Multiple Linear Regression was used to model electric load data, identifying key calendar and meteorological variables through a rolling origin validation process, using three years of historical data. Despite its low cost, Multiple Linear Regression outperforms the more expensive non-linear Light Gradient Boosting Machine, and both outperform the “weekly Naïve” benchmark with a relative Root Mean Square Errors of 32–34% and 39–40%, respectively. Best-practice hyperparameter settings were derived, and they emphasize frequent re-training, maximizing the training data size, and setting a lag size larger than or equal to the forecast horizon for improved accuracy. Combining both models into an ensemble could the enhance accuracy. This paper demonstrates that robust load forecasts can be achieved by leveraging domain knowledge and statistical analysis, utilizing readily available machine learning libraries. The methodology for achieving this is presented within the paper. These models have the potential for economic optimization and load-shifting strategies, offering valuable insights into sustainable energy management.

Energy Load Forecasting Techniques in Smart Grids: A Cross-Country Comparative Analysis

Energy management systems allow the Smart Grids industry to track, improve, and regulate energy use. Particularly, demand-side management is regarded as a crucial component of the entire Smart Grids system. Therefore, by aligning utility offers with customer demand, anticipating future energy demands is essential for regulating consumption. An updated examination of several forecasting techniques for projecting energy short-term load forecasts is provided in this article. Each class of algorithms, including statistical techniques, Machine Learning, Deep Learning, and hybrid combinations, are comparatively evaluated and critically analyzed, based on three real consumption datasets from Spain, Germany, and the United States of America. To increase the size of tiny training datasets, this paper also proposes a data augmentation technique based on Generative Adversarial Networks. The results show that the Deep Learning-hybrid model is more accurate than traditional statistical methods and basic Machine Learning procedures. In the same direction, it is demonstrated that more comprehensive datasets assisted by complementary data, such as energy generation and weather, may significantly boost the accuracy of the models. Additionally, it is also demonstrated that Generative Adversarial Networks-based data augmentation may greatly improve algorithm accuracy.

Short-term industrial load forecasting based on error correction and hybrid ensemble learning

Accurate industrial load forecasting is a prerequisite for ensuring the smooth operation of the power system. Due to the strong fluctuation and complex characteristics of industrial loads, it is difficult to accurately predict short-term power demand. To address this issue, this paper proposes a deep learning prediction model based on hybrid ensemble and error correction. The proposed model is divided into two phases: in the first phase, deep power features are extracted from multivariate data through a hybrid ensemble strategy consisting of Random Subspace, Boosting, Ensemble Pruning, and Multi-Objective Molecular Dynamics Theory Optimization Algorithm (MMDTOA). First, the strategy splits high-dimensional industrial data into multiple sub-datasets. Subsequently, for the features of each sub-dataset, the proposed MMDTOA is applied to perturb the parameters of GRU to generate base learning machines that balance accuracy and diversity. Finally, these base learning machines are integrated by kernel ridge regression stacking. Among them, the two-stage selection strategy and co-evolutionary strategy are embedded into the MMDTOA to enhance the optimization searching effect; in the second stage, a combined error correction strategy is proposed by utilizing the residual information in the prediction results. By combining the dynamic Gaussian error correction function and GRU error correction model, the prediction accuracy of the ensemble model is further improved; Experimental results on real Korean datasets show that the proposed method achieves a minimum value of 3.684% and 7.266% in NMAE and NRMSE, which outperforms eight comparative models, such as SVM, ELM, and CNN, with higher accuracy and robustness.

Short-term power load forecasting using SSA-CNN-LSTM method

ABSTRACT The short-term power load forecasting provides an essential foundation for the dispatching management of the power system, which is crucial for enhancing economy and ensuring operational stability. To enhance the precision of the short-term power load forecasting, this paper proposes a hybrid prediction algorithm based on sparrow search algorithm (SSA), convolutional neural network (CNN) and long short-term memory (LSTM). First, feature datasets are constructed based on date information, meteorological data, similar days. The CNN performs effective feature extraction on the data and feeds the results into the LSTM for time series data analysis. Second, eight key parameters are optimized by SSA for improving the prediction precision of the CNN-LSTM prediction model. Simulation results show that the R2 of the proposed model exhibits a substantial enhancement in comparison to other models, reaching 0.9919 and presents a remarkable decrease in MAPE resulting in a value of 1.2%. Furthermore, RMSE and MAE have decreased to 1.17MW and 0.97MW respectively. Therefore, the proposed method has the ability to improve the prediction accuracy, due to the advantages in data mining of CNN, good time series data fitting ability of LSTM, and excellent optimization ability of SSA.

Elevating sustainability with a multi-renewable hydrogen generation system empowered by machine learning and multi-objective optimization

The global energy landscape is rapidly shifting toward cleaner, lower-carbon electricity generation, necessitating a transition to alternate energy sources. Hydrogen, particularly green hydrogen, looks to be a significant solution for facilitating this transformation, as it is produced by water electrolysis with renewable energy sources such as solar irradiations, wind speed, and biomass residuals. Traditional energy systems are costly and produce energy slowly due to unpredictability in resource supply. To address this challenge, this work provides a novel technique that integrates a multi-renewable energy system using multi objective optimization algorithm to meets the machine learning-based forecasted load model. Several forecasting models, including Autoregressive Integrated Moving Average (ARIMA), Random Forest and Long Short-Term Memory Recurrent Neural Network (LSTM-RNN), are assessed for develop the statistical metrics values such as RMSE, MAE, and MAPE. The selected Non-Sorting Moth Flame Optimization (NSMFO) algorithm demonstrates technological prowess in efficiently achieving global optimization, particularly when handling multiple objective functions. This integrated method shows enormous promise in technological, economic, and environmental terms, emphasizing its ability to promote energy sustainability targets.

Power Load Forecast Based on CS-LSTM Neural Network

Load forecast is the foundation of power system operation and planning. The forecast results can guide the power system economic dispatch and security analysis. In order to improve the accuracy of load forecast, this paper proposes a forecasting model based on the combination of the cuckoo search (CS) algorithm and the long short-term memory (LSTM) neural network. Load data are specific data with time series characteristics and periodicity, and the LSTM algorithm can control the information added or discarded through the forgetting gate, so as to realize the function of forgetting or memorizing. Therefore, the use of the LSTM algorithm for load forecast is more effective. The CS algorithm can perform global search better and does not easily fall into local optima. The CS-LSTM forecasting model, where CS algorithm is used to optimize the hyper-parameters of the LSTM model, has a better forecasting effect and is more feasible. Simulation results show that the CS-LSTM model has higher forecasting accuracy than the standard LSTM model, the PSO-LSTM model, and the GA-LSTM model.

Multi-level optimal energy management strategy for a grid tied microgrid considering uncertainty in weather conditions and load

Microgrids require efficient energy management systems to optimize the operation of microgrid sources and achieve economic efficiency. Bi-level energy management model is proposed in this paper to minimize the operational cost of a grid-tied microgrid under load variations and uncertainties in renewable sources while satisfying the various technical constraints. The first level is day ahead scheduling of generation units based on day ahead forecasting of renewable energy sources and load demand. In this paper, a recent meta-heuristic algorithm called Coronavirus Herd Immunity Optimizer (CHIO) is used to solve the problem of day-ahead scheduling of batteries, which is a complex constrained non-linear optimization problem, while the Lagrange multiplier method is used to determine the set-point of the Diesel Generator (DG). The second level of the proposed EMS is rescheduling and updating the set-points of sources in real-time according to the actual solar irradiance, wind speed, load, and grid tariff. In this paper, a novel real-time strategy is proposed to keep the economic operation during real-time under uncertainties. The obtained results show that the CHIO-based bi-level EMS demonstrates an optimal economic operation for a grid-connected microgrid in real-time when there are uncertainties in weather, utility tariffs, and load forecasts.

A Comprehensive Review of Modern Methods for Load Prediction in the Smart Grid

: Load forecasting plays a crucial role in mitigating risks for utilities by predicting future usage of commodity markets transmission or supplied by the utility. To achieve this, various techniques such as price elastic demand, climate and consumer response, load analysis, and sustainable energy generation predictive modelling are used. As both supply and demand fluctuate, and weather and power prices can rise significantly during peak periods, accurate load forecasting becomes critical for utilities. By providing brief demand forecasts, load forecasting can assist in estimating load flows and making decisions that prevent overloading. Therefore, load forecasting is crucial in helping electric utilities make informed decisions related to power, load switching, voltage regulation, switching, and infrastructure development. Forecasting is a methodology used by electricity companies to forecast the amount of electricity or power production needed to maintain constant supply as well as load demand balance. It is required for the electrical industry to function properly. The smart grid is a new system that enables electricity providers and customers to communicate in real-time. The precise energy consumption sequence of the consumers is required to enhance the demand schedule. This is where predicting the future comes into play. Forecasting future power system load (electricity consumption) is a critical task in providing intelligence to the power grid. Accurate forecasting allows utility companies to allocate resources and assume system control in order to balance the same demand and availability for electricity. In this article, a study on load forecasting algorithms based on deep learning, machine learning, hybrid methods, bio-inspired techniques, and other techniques is carried out. Many other algorithms based on load forecasting are discussed in this study. Different methods of load forecasting were compared using three performance indices: RMSE (Root Mean Square Error), MAE (Mean Absolute Error), MAPE (Mean Absolute Percentage Error), and Accuracy. Machine learning-based techniques showed a reduction of 9.17% in MAPE, 0.0429% in RMSE, and 5.23% in MSE, and achieved 90% accuracy. Deep learning-based techniques resulted in a 9.61% decrease in MAPE and achieved 91% accuracy. Bioinspired techniques provided a reduction of 9.66% in MAPE, 0.026% in RMSE, and 5.24% in MSE, and achieved 95% accuracy. These findings concluded that optimization techniques are more encouraging in predicting load demand and, as a result, can represent a reliable decision-making tool.

Research on short-term load forecasting based on clustering and deep learning

In power systems, power load forecasting is essential to ensure the reliability and efficiency of power supply. Since power load is affected by many factors, including weather, seasonality, and social activities, its patterns and changes are complex and diverse, and traditional forecasting methods may make it difficult to meet demand. In this background, this study combines the K-means clustering algorithm and deep learning model. First, through K-means clustering, we grouped historical load data, dates, and temperatures to identify different load patterns. This grouping helps adapt to different load changes, thereby improving the adaptability of the forecast. Then, a deep learning model is applied, combining a convolutional neural network (CNN) and a two-layer bidirectionally gated recurrent unit (BIGRU). These two models are used to deal with spatiotemporal characteristics and sequence dependence in load data respectively. CNN is used to capture the spatial features in the load data, while BIGRU processes the time series information in the data to effectively capture the complex dynamic nature of the load. K-means clustering information is entered as additional data into the CNN and BIGRU models. The experimental results of the study show that by fully considering different load patterns and data characteristics. Reducing load demand and providing more reliable short-term load forecasts improve the efficiency of the power supply, reduce energy waste, and reduce the burden on the power system.

Research on optimization of improved short-term load composite forecasting model based on AM–CNN–Bi–LSTM

Accurate load prediction is a prerequisite for the design, operation, scheduling, and management of energy systems. In the context of the development of smart grids, the extensive integration of highly volatile distributed energy generation into the power system has brought new challenges to the accuracy, reliability, real-time performance, and intelligence of short-term load forecasting. Therefore, this article proposes a novel short-term power load composite prediction model based on AM–CNN–Bi–LSTM. First, CNN is used to extract relevant feature quantities of power load coupling characteristics. Then, AM is used to evaluate the importance of the feature data, highlighting the features that have a greater impact on the prediction results. Finally, the Bi-LSTM network captures bidirectional temporal information from multiple time steps for prediction. Taking one year of measured data as an example, the error comparison of the prediction results of the composite prediction model overlay shows that compared with other models, the composite prediction model has improved prediction accuracy, feature extraction, generalization ability, and other aspects. The research results improve the accuracy of short-term power load forecasting while providing effective model references for decision-making in power system optimization scheduling, safe operation, and reasonable pricing.