Article: An optimisation of power system load forecasting driven by deep learning model Journal: International Journal of Business Intelligence and Data Mining (IJBIDM) 2026 Vol.28 No.9 pp.194 - 210 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. Inderscience Publishers - linking academia, business and industry through research

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

Authors: Honghui Li; Huifeng Wang; Zhiyong Huang; Jiahui Zhang; Detao Zou; Pengyuan Zhao

Addresses: China Three Gorges Construction Engineering Corporation, Zhangye, 734034, Gansu, China ' China Three Gorges Construction Engineering Corporation, Zhangye, 734034, Gansu, China ' China Three Gorges Construction Engineering Corporation, Zhangye, 734034, Gansu, China ' China Three Gorges Construction Engineering Corporation, Zhangye, 734034, Gansu, China ' China Three Gorges Construction Engineering Corporation, Zhangye, 734034, Gansu, China ' Changdian (Zhangye) Energy Development Co., Ltd, Zhangye, 734034, Gansu, China

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.

Keywords: deep learning; load forecasting; LSTM; attention mechanism; hyperparameter optimisation; power system; high-precision forecasting.

DOI: 10.1504/IJBIDM.2026.154245

International Journal of Business Intelligence and Data Mining, 2026 Vol.28 No.9, pp.194 - 210

Received: 04 Feb 2026
Accepted: 17 Apr 2026
Published online: 17 Jun 2026 *

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

Keep up-to-date