Explore the vast range of titles available.

In this research, our main goal was to improve power load forecasting accuracy by considering the impact of meteorological factors on the total power of the electrical system, examining existing load data, local weather, wind direction, and other parameters affecting total power load. We divided the data from the past three years into a training dataset, comprising 75% of the data, and a testing dataset with the remaining 25%. We employed a basic machine learning technique (Support Vector Machine) and three distinct neural network approaches (Artificial Neural Network, Convolutional Neural Network, and Long-Short Term Memory Network) to develop analytical models. Through experimentation, the LSTM model achieved a loss value of 0.0034 and required 1426.78 seconds of training time across 100 epochs. Considering the time expense and model complexity, we chose the LSTM model to forecast power load at 15-minute intervals for the subsequent ten days, achieving a satisfactory prediction and fitting outcome. Our results suggest that the LSTM model is a promising method for optimizing performance and reliability in electrical power systems.

Precise anticipation of electrical demand holds crucial importance for the optimal operation of power systems and the effective management of energy markets within the domain of energy planning. This study builds on previous research focused on the application of artificial neural networks to achieve accurate electrical load forecasting. In this paper, an improved methodology is introduced, centering around bidirectional Long Short-Term Memory (LSTM) neural networks (NN). The primary aim of the proposed bidirectional LSTM network is to enhance predictive performance by capturing intricate temporal patterns and interdependencies within time series data. While conventional feed-forward neural networks are suitable for standalone data points, energy consumption data are characterized by sequential dependencies, necessitating the incorporation of memory-based concepts. The bidirectional LSTM model is designed to furnish the prediction framework with the capacity to assimilate and leverage information from both preceding and forthcoming time steps. This augmentation significantly bolsters predictive capabilities by encapsulating the contextual understanding of the data. Extensive testing of the bidirectional LSTM network is performed using multiple datasets, and the results demonstrate significant improvements in accuracy and predictive capabilities compared to the previous simpleRNN-based framework. The bidirectional LSTM successfully captures underlying patterns and dependencies in electrical load data, achieving superior performance as gauged by metrics such as root mean square error (RMSE) and mean absolute error (MAE). The proposed framework outperforms previous models, achieving a remarkable RMSE, attesting to its remarkable capacity to forecast impending load with precision. This extended study contributes to the field of electrical load prediction by leveraging bidirectional LSTM neural networks to enhance forecasting accuracy. Specifically, the BiLSTM’s MAE of 0.122 demonstrates remarkable accuracy, outperforming the RNN (0.163), LSTM (0.228), and GRU (0.165) by approximately 25%, 46%, and 26%, in the best variation of all networks, at the 24-h time step, while the BiLSTM’s RMSE of 0.022 is notably lower than that of the RNN (0.033), LSTM (0.055), and GRU (0.033), respectively. The findings highlight the significance of incorporating bidirectional memory and advanced neural network architectures for precise energy consumption prediction. The proposed bidirectional LSTM framework has the potential to facilitate more efficient energy planning and market management, supporting decision-making processes in power systems.

Demand response plays a pivotal role in modern smart grid systems, aiding in balancing energy consumption. However, the increasing energy demands of contemporary society have placed a significant burden on power systems. To simulate the interaction between electricity supply and demand, this paper introduces the concept of Deep Q-Network (DQN) to the domain of demand response. Additionally, a novel multivariate forecasting model, referred to as PreAttention-CNN-GRU (PACG), is proposed to predict in real time the impact of electricity prices on consumer electricity usage behavior. Finally, a load control method, denoted as DQN-PreAttention-CNN-GRU (DQN-PACG), is presented to achieve price-based demand response. The performance of PACG was tested on a real-world German dataset, demonstrating superior predictive accuracy compared to traditional forecasting models such as Long Short-Term Memory Networks. Furthermore, the test results of DQN-PACG on the same dataset contribute to alleviating the load and stress on the power grid. This paper also includes a case study of southern provinces in China, where the model was able to reduce electricity consumption by 1.64% and electricity cost by 5.42%, both of which outperform the current electricity pricing policies.

An important issue for the growth and management of grid-connected photovoltaic (PV) systems is the possibility to forecast the power output over different horizons. In this work, statistical methods based on multiregression analysis and the Elmann artificial neural network (ANN) have been developed in order to predict power production of a 960 kWP grid-connected PV plant installed in Italy. Different combinations of the time series of produced PV power and measured meteorological variables were used as inputs of the ANN. Several statistical error measures are evaluated to estimate the accuracy of the forecasting methods. A decomposition of the standard deviation error has been carried out to identify the amplitude and phase error. The skewness and kurtosis parameters allow a detailed analysis of the distribution error.

The penetration of offshore wind farms (OWFs) in city‐close power systems is rapidly increasing. System inertia will be further reduced. Active frequency support of wind power is essential to solve the load frequency control (LFC) problem. Here, the dynamic virtual inertia control (VIC) method is employed to enhance frequency stability within the permitted operating states of OWFs. An adaptive distributed model predictive control (DMPC) method is proposed and applied to an interconnected power system. The dynamic VIC‐based LFC model is derived and used to construct the predictive model of DMPC. To expand the adaptation of the analytical linearized model of OWFs in different operating points, the adaptive law is further designed to dynamically adjust the parameters of DMPC. The simulation results demonstrate the effectiveness of the proposed control method. The frequency fluctuations can be well‐restrained under different disturbances. An adaptive distributed model predictive control (DMPC) method is proposed and applied to an interconnected power system. The dynamic VIC‐based frequency regulation model of OWFs is derived to constitute the predictive model of LFC. The adaptive law is designed to adjust the parameters of DMPC with different wind speeds.

In response to the ‘zero carbon’ goal, the development of renewable energy has become a global consensus. Among the array of renewable energy sources, wind energy is distinguished by its considerable installed capacity on a global scale. Accurate wind power prediction provides a fundamental basis for power grid dispatching, unit combination operation, and wind farm operation and maintenance. This study establishes a framework to bridge theoretical innovations with practical implementation challenges in wind power prediction. This work uses a narrative method to synthesize and discuss wind power prediction methods. Common classification angles of wind power prediction methods are outlined. By synthesizing existing approaches through multi-time scales, from the ultra-short term and short term to mid-long term, the review further deconstructs methods by model characteristics, input data types, spatial scales, and evaluation metrics. The analysis reveals that the data-driven prediction model dominates ultra-short-term predictions through rapid response to volatility, while the hybrid method enhances short-term precision. Mid-term predictions increasingly integrate climate dynamics to address seasonal variability. A key contribution lies in unifying fragmented methodologies into a decision support framework that prioritizes the time scale, model adaptability, and spatial constraints. This work enables practitioners to systematically select optimal strategies and advance the development of forecasting systems that are critical for highly renewable energy systems.

Day-ahead residential load forecasting is important for power system demand response. Considering the fluctuation of the residential electricity load and the small accumulation of electricity consumption data in some households, the prediction accuracy of the residential electricity consumption load is significantly challenging. In this study, a scenario prediction scheme for residential electricity consumption load using a transferable flow-based generation model was proposed. First, to make full use of the source domain data, different source domain families were selected to form multi-source domain families according to the association index of the source and target domains by introducing grey correlation analysis. Thereafter, the method of model transfer was adopted, and the pretraining model was established using multi-source household electrical load data. The network parameters of part of the step of flow structure were frozen in the pretraining model, the structural parameters of the unfrozen step of flow structure were fine-tuned and trained by household electrical load data in the target domain, and the day-ahead electricity load prediction model under a small sample was constructed. The experimental results show that the algorithm combined with model transfer performs well in solving the residential load-forecasting effect for small samples.

With the increasing demand for electricity, the power system is facing enormous challenges. To ensure the equilibrium between supply and demand in the electricity market and the safety and stability of the power grid, a source load uncertainty economic dispatch model based on distributed robust opportunity constraints is proposed to cope with the uncertainty of sustainable energy resources such as wind power and photovoltaics. By introducing an improved Elman network and grey wolf optimization algorithm, high-precision prediction of short-term loads is achieved, providing data support for scheduling models. The experiment outcomes indicate that the prediction model grounded on the improved Elman network and grey wolf optimization algorithm performs the best in scheduling performance on both the training and testing sets, with the lowest cost, the highest utilization rates of wind and solar power, and the lowest probability of constraint default. In addition, the economic dispatch model proposed by the research has significant advantages in reducing total dispatch costs, improving wind and photovoltaic utilization rates, and constraining default probability control. In typical load scenarios, the total scheduling cost of the model is $1,308,469, with wind and photovoltaic utilization rates reaching 90.5% and 86.1% respectively, and a default probability of only 0.9%. The research results indicate that the model exhibits superiority in real-time response time, especially suitable for scenarios with high load fluctuations. The research provides important theoretical basis and application value for the economic dispatch of power systems.

The paper presents the application of recurrent LSTM neural networks for short-time load forecasting in the Polish Power System (PPS) and a small region of a power system in Central Poland. The objective of the present work was to develop an efficient and accurate method of forecasting the 24-h pattern of power load with a 1-h and 24-h horizon. LSTM showed effectiveness in predicting the irregular trends in time series. The final forecast is estimated using an ensemble consisted of five independent predictions. Numerical experiments proved the superiority of the ensemble above single predictor resulting in a reduction of the MAPE the RMSE error by more than 6% in both forecasting tasks.

Power load prediction is fundamental for ensuring the reliability of power grid operation and the accuracy of power demand forecasting. However, the uncertainties stemming from power generation, such as wind speed and water flow, along with variations in electricity demand, present new challenges to existing power load prediction methods. In this paper, we propose an improved Convolutional Neural Network–Bidirectional Long Short-Term Memory (CNN-BILSTM) model for analyzing power load in systems affected by uncertain power conditions. Initially, we delineate the uncertainty characteristics inherent in real-world power systems and establish a data-driven power load model based on fluctuations in power source loads. Building upon this foundation, we design the CNN-BILSTM model, which comprises a convolutional neural network (CNN) module for extracting features from power data, along with a forward Long Short-Term Memory (LSTM) module and a reverse LSTM module. The two LSTM modules account for factors influencing forward and reverse power load timings in the entire power load data, thus enhancing model performance and data utilization efficiency. We further conduct comparative experiments to evaluate the effectiveness of the proposed CNN-BILSTM model. The experimental results demonstrate that CNN-BILSTM can effectively and more accurately predict power loads within power systems characterized by uncertain power generation and electricity demand. Consequently, it exhibits promising prospects for industrial applications.