| 17 | 0 | 762 |
| 下载次数 | 被引频次 | 阅读次数 |
为进一步提升预测效果，从权重和聚类的维度考虑，提出了一种AHP-K-Means-LSTM组合模型的短期负荷预测方法，首先，利用层次分析法（Analytic Hierarchy Process，AHP）计算出影响负荷预测的因素权重，结合改进K-Means（K均值）聚类算法选取样本中效果最好的一组聚类结果，然后，将该样本代入到长短期记忆（Long Short-Term Memory，LSTM）神经网络模型中进行训练，将输出结果与真实负荷进行对比分析。以辽宁省沈阳地区2022年电力负荷数据集为例进行仿真实验验证，结果表明，所提方法在不同季节的工作日和节假日中的负荷预测精度较其他预测方法均有所提升。
Abstract：In order to further improve the prediction performance, this paper proposes a short-term load forecasting method using the AHP-K-Means-LSTM combination model from the dimensions of weight and clustering. Firstly, the Analytic Hierarchy Process(AHP) is used to calculate the weights of factors that affect load forecasting. The improved K-Means clustering algorithm is combined to select the most effective clustering results from the samples. Then, the sample is brought into the Long Short-Term Memory(LSTM) neural network model for training, and the output results are compared and analyzed with the actual load. Taking the 2022 electricity load dataset in Shenyang of Liaoning Province as an example for simulation verification, the results of which show that the proposed method has improved load forecasting accuracy compared to traditional methods in working days and holidays in different seasons.
[1] 葛磊蛟，范延赫，来金钢，等.面向低碳经济的人工智能赋能微电网优化运行技术[J].高电压技术，2023，49（6）：2219-2238． GE Leijiao, FAN Yanhe, LAI Jingang, et al. Artificial Intelligence Empowered Microgrid Optimization Operation Technology for Low Carbon Economy[J]. High Voltage Engineering, 2023, 49(6): 2219-2238.
[2] 任子俊，曲小慧，王敏之，等.新型电力系统中电化学储能应用与关键技术综述[J].东北电力大学学报，2023，43（6）：1-7，78. REN Zijun, QU Xiaohui, WANG Minzhi, et al. A Review of Electrochemical Energy Storage Applications and Key Technologies in New-type Power Systems[J]. Journal of Northeast Dianli University(Natural Science Edition), 2023, 43(6): 1-7, 78.
[3] 崔杨，朱晗，王议坚，等.基于CNN-SAEDN-Res的短期电力负荷预测方法[J].电力自动化设备，2024，44（4）：164-170. CUI Yang, ZHU Han, WANG Yijian, et al. Short term power load forecasting method based on CNN-SAEDN Res[J]. Electric Power Automation Equipment, 2024, 44(4): 164-170.
[4] 邹智，吴铁洲，张晓星，等.基于贝叶斯优化CNN-BiGRU混合神经网络的短期负荷预测[J].高电压技术，2022，48（10）：3935-3945. ZOU Zhi, WU Tiezhou, ZHANG Xiaoxing, et al. Short term load forecasting based on Bayesian optimized CNN BiGRU hybrid neural network[J]. High Voltage Engineering, 2022, 48(10): 3935-3945.
[5] 蒋敏，顾东健，孔军，等.基于在线序列极限支持向量回归的短期负荷预测模型[J].电网技术，2018，42（7）：2240-2247． JIANG Min, GU Dongjian, KONG Jun, et al. Short term load forecasting model based on online sequence extreme support vector regression[J]. Power System Technology, 2018, 42(7): 2240-2247.
[6] 孙辉，杨帆，高正男，等.考虑特征重要性值波动的MI-BILSTM短期负荷预测[J].电力系统自动化，2022，46（8）：95-103. SUN Hui, YANG Fan, GAO Zhengnan, et al. Short term load forecasting of MI-BILSTM considering fluctuations in feature importance values[J]. Automation of Electric Power Systems, 2022, 46(8): 95-103.
[7] 邹鹏辉.微电网中的光伏储能控制策略研究[J].电力大数据， 2021，24（12）：1-8. ZOU Penghui. Research on photovoltaic energy storage control strategy in micro-grid[J]. Power Systems and Big Data, 2021, 24(12): 1-8.
[8] 叶剑华，曹旌，杨理，等.基于变分模态分解和多模型融合的用户级综合能源系统超短期负荷预测[J].电网技术，2022，46（7）：2610- 2622． YE Jianhua, CAO Jing, YANG Li, et al. User level comprehensive energy system ultra short term load forecasting based on variational mode decomposition and multi model fusion[J]. Power System Technology, 2022, 46(7): 2610-2622.
[9] 陆继翔，张琪培，杨志宏，等.基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J].电力系统自动化，2019，43（8）：131-137． LU Jixiang, ZHANG Qipei, YANG Zhihong, et al. Short term load forecasting method based on CNN LSTM hybrid neural network model[J]. Automation of Electric Power Systems, 2019, 43(8): 131-137.
[10] 史佳琪，马丽雅，李晨晨，等.基于串行—并行集成学习的高峰荷预测方法[J].中国电机工程学报，2020，40（14）：4463-4472. SHI Jiaqi, MA Liya, LI Chenchen, et al. Peak load prediction method based on serial parallel ensemble learning [J]. Proceedings of the CSEE, 2020, 40(14): 4463-4472.
[11] 金航.基于改进深度循环神经网络的短期电力系统负荷预测方法[D].北京：华北电力大学，2021.
[12] 韩雪源.基于LSTM算法的高压交联电缆线路振荡波局部放电检测方法[J].电机与控制应用，2022，49（12）：41-46，80． HAN Xueyuan. Partial discharge detection method for oscillation waves in high-voltage cross-linked cable lines based on LSTM algorithm[J]. Electric Machines & Control Application, 2022, 49(12): 41-46, 80.
[13] 祁兵，李鹏云，李彬.基于边缘计算的台区负荷可调节潜力研究[J].内蒙古电力技术，2022（6）：29-36. QI Bing, LI Pengyun, LI Bin. Study on Load A djustable Potential of Platform Based on Edge Calculation[J]. Inner Mongolia Electric Power, 2022(6): 29-36.
[14] 程明，翟金星，马骏，等.基于迁移学习的CNN-GRU短期电力负荷预测方法[J].武汉大学学报（工学版），2024，57（6）：812-820. CHENG Ming, ZHAI Jinxing, MA Jun, et al. A CNN GRU Short Term Power Load Forecasting Method Based on Transfer Learning[J]. Engineering Journal of Wuhan University, 2024, 57(6): 812-820.
[15] 乔石，王磊，张鹏超，等.基于模态分解及注意力机制长短时间网络的短期负荷预测[J].电网技术，2022，46（10）：3940-3951. QIAO Shi, WANG Lei, ZHANG Pengchao, et al. Short term load forecasting based on modal decomposition and attention mechanism in long short-term networks[J]. Power System Technology, 2022, 46(10): 3940-3951.
[16] 任建吉，位慧慧，邹卓霖，等.基于CNN-BiLSTM-Attention的超短期电力负荷预测[J].电力系统保护与控制，2022，50（8）：108- 116. REN Jianji, WEI Huihui, ZOU Zhuolin, et al. Ultra Short Term Power Load Forecasting Based on CNN BiLSTM Attention[J]. Power System Protection and Control, 2022, 50(8): 108-116.
[17] 封钰，宋佑斌，金晟，等.基于随机森林算法和粗糙集理论的改进型深度学习短期负荷预测模型[J].发电技术，2023，44（6）：889- 895. FENG Yu, SONG Youbin, JIN Sheng, et al. Transient Characteristics of Rogowski Coil Based Current Transformers [J]. Power Generation Technology, 2023, 44(6): 889-895.
[18] 赖添城，徐康康，朱成就，等.一种基于改进CNN-GRU的建筑冷负荷单步预测方法[J].机电工程技术，2024，53（1）：119-122. LAI Tiancheng, XU Kangkang, ZHU Chengjiu, et al. A One- step Prediction Method of Building Cooling Load Based on Improved CNN-GRU[J]. Mechanical & Electrical Engineering Technology, 2024, 53(1): 119-122.
[19] 张异殊，李宜伦，姚志远，等.基于VMD-GWO-SVR的短期电力负荷预测方法[J].东北电力技术，2024，45（7）：27-31，37. ZHANG Yishu, LI Yilun, YAO Zhiyuan, et al. Short-Term Power Load Forecasting Method Based on VMD-GWO-SVR [J]. Northeast Electric Power Technology，2024, 45(7): 27-31， 37.
基本信息:
DOI：10.19929/j.cnki.nmgdljs.2024.0080
中图分类号:
引用信息:
[1]章家栋1,张永庆2,陈修鹏2等.基于AHP-K-Means-LSTM模型的短期电力负荷预测研究[J],2024,42(06):56-63.DOI:10.19929/j.cnki.nmgdljs.2024.0080.
基金信息:
国网辽宁省电力有限公司科技项目“基于大数据分析的用电负荷结构特征及稳定性态势感知技术研究”（2024YF-02）