What question did this study set out to answer?

This research aims to enhance power system load forecasting accuracy using advanced deep learning techniques.

June 20, 2026Open Access

An optimisation of power system load forecasting driven by deep learning model

Key Points

This research aims to enhance power system load forecasting accuracy using advanced deep learning techniques.
Proposes an LSTM model with attention mechanism for feature enhancement.
Utilizes Bayesian optimisation combined with grid search for hyperparameter tuning and regularisation.
Analyzes historical load, meteorological, and calendar features for forecasting.
The proposed model shows lower MAE/RMSE than ARIMA and SVM benchmarks.
Demonstrated stronger cross-seasonal adaptability and stability in forecasting performance.
Improvements indicate a feasible approach for high-precision forecasting in modern power systems.

Abstract

Power system load forecasting is core to grid safety and economic operation.With diversified power consumption and high-proportion renewable energy grid connection, load sequences show strong nonlinearity, time-variability and volatility, making traditional statistical methods inadequate for high-precision forecasting.This paper proposes an LSTM model integrating attention mechanism and multi-strategy optimisation: it enhances key time-step feature weights via attention, fuses historical load, meteorological and calendar features, and adopts Bayesian optimisation + grid search hyperparameter tuning plus regularisation to suppress overfitting.Experiments on southern China regional grid data show the model outperforms ARIMA, SVM and other benchmarks in short/medium-term forecasting, with lower MAE/RMSE, stronger cross-seasonal adaptability and stability, providing a feasible path for high-precision forecasting in new power systems.

Mark Helpful

Bookmark

Relay

View Full Paper