引用本文: | 张 丽,李世情,艾恒涛,张 涛,张宏伟.基于改进Q学习算法和组合模型的超短期电力负荷预测[J].电力系统保护与控制,2024,52(9):143-153.[点击复制] |
ZHANG Li,LI Shiqing,AI Hengtao,ZHANG Tao,ZHANG Hongwei.Ultra-short-term power load forecasting based on an improved Q-learningalgorithm and combination model[J].Power System Protection and Control,2024,52(9):143-153[点击复制] |
|
摘要: |
单一模型在进行超短期负荷预测时会因负荷波动而导致预测精度变差,针对此问题,提出一种基于深度学习算法的组合预测模型。首先,采用变分模态分解对原始负荷序列进行分解,得到一系列的子序列。其次,分别采用双向长短期记忆网络和优化后的深度极限学习机对每个子序列进行预测。然后,利用改进Q学习算法对双向长短期记忆网络的预测结果和深度极限学习机的预测结果进行加权组合,得到每个子序列的预测结果。最后,将各个子序列的预测结果进行求和,得到最终的负荷预测结果。以某地真实负荷数据进行预测实验,结果表明所提预测模型较其他模型在超短期负荷预测中表现更佳,预测精度达到98%以上。 |
关键词: Q学习算法 负荷预测 双向长短期记忆 深度极限学习机 灰狼算法 |
DOI:10.19783/j.cnki.pspc.231357 |
投稿时间:2023-10-20修订日期:2024-02-25 |
基金项目:国家自然科学基金项目资助(52177039);河南省高等学校重点科研项目资助(24A470006);河南省科技攻关项目(242102241027) |
|
Ultra-short-term power load forecasting based on an improved Q-learningalgorithm and combination model |
ZHANG Li1,2,LI Shiqing1,AI Hengtao1,ZHANG Tao1,ZHANG Hongwei3 |
(1. School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454003, China;
2. Henan Key Laboratory of Intelligent Detection and Control of Coal Mine Equipment, Jiaozuo 454003, China;
3. Linfen Power Supply Company, State Grid Shanxi Electric Power Company, Linfen 041000, China) |
Abstract: |
The prediction accuracy of a single model will deteriorate because of load fluctuations when making ultra-short-term load forecasting. To solve this problem, this paper proposes a combinatorial prediction model based on a deep learning algorithm. First, variational mode decomposition is used to decompose the original load sequence to obtain a series of sub-sequences. Secondly, a bidirectional long short-term memory network and an optimized deep extreme learning machine are used to predict each sub-sequence. Thirdly, the improved Q-learning algorithm is used to weight the prediction results of the bidirectional long short-term memory network and of the deep extreme learning machine to obtain those of each sub-sequence. Finally, the prediction results of each subseries are summed to obtain the final load prediction results. The results show that the prediction model proposed in this paper performs better than other models in ultra-short-term load forecasting, with a prediction accuracy of more than 98%. |
Key words: Q-learning algorithm load forecasting bi-directional long short-term memory deep extreme learning machine grey wolf optimization algorithm |