Author(s)

WenLi Tang^1*, YiZhou Fang²

Affiliation(s)

¹State Grid Xinyuan Anhui Xiangshuijian Pumped Storage Co.Ltd., WuHu, 241070, China.

²Xiaoxiang College of Hunan University of science and technology, Xiangtan, 411201, China.

Corresponding Author

WenLi Tang

ABSTRACT

Accurate power load forecasting is pivotal in modern power systems, as it underpins efficient energy management, resource allocation, and grid stability. This paper introduces a novel hybrid forecasting model that integrates Particle Swarm Optimization (PSO) with Bidirectional Gated Recurrent Unit (Bi-GRU) networks to enhance predictive performance. The PSO algorithm is employed to systematically optimize the hyperparameters of the Bi-LSTM model, addressing challenges such as overfitting, convergence speed, and model complexity. By leveraging Bi-GRU's ability to capture bidirectional temporal dependencies and PSO's strength in global optimization, the proposed approach achieves significant improvements in forecasting accuracy. Experimental evaluations conducted on real-world power load datasets demonstrate the model's robustness and superior performance compared to standalone Bi-LSTM, PSO, and other traditional algorithms. The results highlight the potential of the PSO- Bi-GRU framework as a reliable and efficient tool for power load forecasting in complex and dynamic energy systems.

KEYWORDS

Bidirectional gated recurrent unit; Particle Swarm Optimization; Load forecasting; Parameter optimization

CITE THIS PAPER

WenLi Tang, YiZhou Fang. Power load forecasting based on the Particle Swarm Optimization with bidirectional gated recurrent unit networks. Journal of Computer Science and Electrical Engineering. 2025, 7(1): 11-15. DOI: https://doi.org/10.61784/jcsee3033.

REFERENCES

[1] Wang, C, Liu, C, Chen, J, et al. Cooperative planning of renewable energy generation and multi-timescale flexible resources in active distribution networks. Applied Energy, 2024, 356, 122429.

[2] Aeggegn, D B, Nyakoe, G N, Wekesa, C. A state of the art review on energy management techniques and optimal sizing of DERs in grid-connected multi-microgrids. Cogent Engineering, 2024, 11(1): 2340306.

[3] Zhong, W, Zhai, D, Xu, W, et al. Accurate and efficient daily carbon emission forecasting based on improved ARIMA. Applied Energy, 2024, 376, 124232.

[4] Sapnken, F E, Tazehkandgheshlagh, A K, Diboma, B S, et al. A whale optimization algorithm-based multivariate exponential smoothing grey-holt model for electricity price forecasting. Expert Systems with Applications, 2024, 255, 124663.

[5] Kashiri, S, Siahbalaee, J, Koochaki, A. Stochastic management of electric vehicles in an intelligent parking lot in the presence of hydrogen storage system and renewable resources. International Journal of Hydrogen Energy, 2024, 50, 1581-1597.

[6] Eren, Y, Kücükdemiral, I. A comprehensive review on deep learning approaches for short-term load forecasting. Renewable and Sustainable Energy Reviews, 2024, 189, 114031.

[7] Alruqimi, M, Di Persio, L. Enhancing multi-step brent oil price forecasting with ensemble multi-scenario Bi-GRU networks. International Journal of Computational Intelligence Systems, 2024, 17(1): 225.

[8] Michael, N E, Bansal, R C, Ismail, A A A, et al. A cohesive structure of Bi-directional long-short-term memory (BiLSTM)-GRU for predicting hourly solar radiation. Renewable Energy, 2024, 222, 119943.

[9] Daviran, M, Maghsoudi, A, Ghezelbash, R. Optimized AI-MPM: Application of PSO for tuning the hyperparameters of SVM and RF algorithms. Computers & Geosciences, 2025, 195, 105785.

[10] Ullah, J, Li, H, Soupios, P, et al. Optimizing geothermal reservoir modeling: A unified bayesian PSO and BiGRU approach for precise history matching under uncertainty. Geothermics, 2024, 119, 102958.

[11] Y, Su, M, Tan, J, Teh, Short-Term Transmission Capacity Prediction of Hybrid Renewable Energy Systems Considering Dynamic Line Rating Based on Data-Driven Model. IEEE Transactions on Industry Applications, (early access). 2025. DOI: 10.1109/TIA.2025.3529824.

[12] Weerakody, P B, Wong, K W, Wang, G, et al. A review of irregular time series data handling with gated recurrent neural networks. Neurocomputing, 2021, 441, 161-178.

[13] Nayak, J, Swapnarekha, H, Naik, B, et al. 25 years of particle swarm optimization: Flourishing voyage of two decades. Archives of Computational Methods in Engineering, 2023, 30(3): 1663-1725.

[14] Liu, Y, Cao, Y, Wang, L, et al. Prediction of the durability of high-performance concrete using an integrated RF-LSSVM model. Construction and Building Materials, 2022, 356, 129232.

[15] Liu, F, Liang, C. Short-term power load forecasting based on AC-BiLSTM model. Energy Reports, 2024, 11, 1570-1579.

[16] Du, B, Huang, S, Guo, J, et al. Interval forecasting for urban water demand using PSO optimized KDE distribution and LSTM neural networks. Applied Soft Computing, 2022, 122, 108875.