UniLF: A novel short-term load forecasting model uniformly considering various features from multivariate load data

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 4, 2025

Язык: Английский

Real Time Electrical Load Prediction and Management through Deep Learning and Reinforcement Learning Techniques

Engineering Technology & Applied Science Research, Год журнала: 2025, Номер 15(2), С. 21061 - 21067

Опубликована: Апрель 3, 2025

Real-time electrical load prediction and management are critical to ensuring the stability reliability of modern power systems, especially as global energy demand continues grow. This research presents a groundbreaking solution by combining hybrid deep learning approach with reinforcement address challenges accurate forecasting adaptive distribution. The proposed framework integrates Convolutional Neural Networks (CNNs) Long Short-Term Memory (LSTM) networks, leveraging their strengths capture both spatial temporal patterns in data. model delivers highly forecasts effectively handles complex nonlinear consumption that traditional methods fail address. In addition forecasting, employs Soft Actor-Critic (SAC) algorithm, which enables decision-making for real-time management. By dynamically adapting fluctuating grid conditions, SAC algorithm optimizes distribution, reduces peak stress, enhances overall system efficiency. integrated ensures resources allocated more effectively, improving minimizing waste. methodology is validated through rigorous experimentation using real-world datasets, such PJM dataset, performance metrics, including Mean Absolute Error (MAE), Root Square (RMSE), not only advances predictive analytics management, but also provides utilities consumers scalable practical optimize consumption, integrate renewable sources, promote sustainability. serves vital tool future paving way smarter, resilient grids.

Язык: Английский

SP-RF-ARIMA: A sparse random forest and ARIMA hybrid model for electric load forecasting

Global Energy Interconnection, Год журнала: 2025, Номер unknown

Опубликована: Май 1, 2025

Язык: Английский