A Multi-Level Collaborative Load Forecasting Method for Distribution Networks Based on Distributed Optimization

doi:10.16183/j.cnki.jsjtu.2021.296

Abstract

Abstract:

At present, new elements such as distributed new energy and electric vehicles have emerged in the distribution network, which changes the composition of loads, enriches the connotation of loads, and poses severe challenges to load forecasting. In fact, loads are aggregated in a bottom-up manner in multiple voltage levels of the distribution network, but such hierarchical characteristics are rarely considered in current load forecasting researches. Therefore, a multi-level load collaborative forecasting method based on the distributed optimization algorithm is proposed aimed at ensuring the bottom-up aggregation consistency of loads and jointly improving the performance of load forecasting at all levels. First, the distributed optimization concept based on the alternating direction method of multipliers is adopted to construct a multi-level load collaborative forecasting framework which adapts to the hierarchical characteristics of distribution network and has less data interaction. Then, a specific forecasting method based on the long short term-memory neural network and federated learning is proposed. By aggregating the bottom load forecasting results step by step, the bottom-up integrated load forecasting of distribution network can be realized. The results of calculation examples show that the proposed method has a high accuracy and a great application prospect.

Key words: multi-level load forecasting, alternating direction method of multipliers, long short-term memory neural network, federated learning

CLC Number:

TM715

TAN Jia, LI Zhiyi, YANG Huan, ZHAO Rongxiang, JU Ping. A Multi-Level Collaborative Load Forecasting Method for Distribution Networks Based on Distributed Optimization[J]. Journal of Shanghai Jiao Tong University, 2021, 55(12): 1544-1553.

Figures/Tables 9

Fig.1

Fig.2

Fig.3

Fig.4

Tab.1

Tab.2

Tab.3

Fig.5

Fig.6

References 33

[1]	谢小荣, 贺静波, 毛航银, 等. “双高”电力系统稳定性的新问题及分类探讨[J]. 中国电机工程学报, 2021, 41(2):461-475.
	XIE Xiaorong, HE Jingbo, MAO Hangyin, et al. New issues and classification of power system stability with high shares of renewables and power electronics[J]. Proceedings of the CSEE, 2021, 41(2):461-475.
[2]	韦善阳, 黎静华, 黄乾, 等. 考虑多重因素耦合的广义负荷特征曲线的模式分析[J]. 电力系统自动化, 2021, 45(1):114-122.
	WEI Shanyang, LI Jinghua, HUANG Qian, et al. Pattern analysis of generalized load characteristic curve considering coupling of multiple factors[J]. Automation of Electric Power Systems, 2021, 45(1):114-122.
[3]	陈海文, 王守相, 王绍敏, 等. 基于门控循环单元网络与模型融合的负荷聚合体预测方法[J]. 电力系统自动化, 2019, 43(1):65-72.
	CHEN Haiwen, WANG Shouxiang, WANG Sh-aomin, et al. Aggregated load forecasting method based on gated recurrent unit networks and model fusion[J]. Automation of Electric Power Systems, 2019, 43(1):65-72.
[4]	孔祥玉, 李闯, 郑锋, 等. 基于经验模态分解与特征相关分析的短期负荷预测方法[J]. 电力系统自动化, 2019, 43(5):46-52.
	KONG Xiangyu, LI Chuang, ZHENG Feng, et al. Short-term load forecasting method based on empirical mode decomposition and feature correlation analysis[J]. Automation of Electric Power Systems, 2019, 43(5):46-52.
[5]	赵兵, 王增平, 纪维佳, 等. 基于注意力机制的CNN-GRU短期电力负荷预测方法[J]. 电网技术, 2019, 43(12):4370-4376.
	ZHAO Bing, WANG Zengping, JI Weijia, et al. A short-term power load forecasting method based on attention mechanism of CNN-GRU[J]. Power System Technology, 2019, 43(12):4370-4376.
[6]	GOIA A, MAY C, FUSAI G. Functional clustering and linear regression for peak load forecasting[J]. International Journal of Forecasting, 2010, 26(4):700-711. doi: 10.1016/j.ijforecast.2009.05.015 URL
[7]	TRUDNOWSKI D J, MCREYNOLDS W L, JOHNSON J M. Real-time very short-term load prediction for power-system automatic generation control[J]. IEEE Transactions on Control Systems Technology, 2001, 9(2):254-260. doi: 10.1109/87.911377 URL
[8]	张帆, 张峰, 张士文. 基于提升小波的时间序列分析法的电力负荷预测[J]. 电气自动化, 2017, 39(3):72-76.
	ZHANG Fan, ZHANG Feng, ZHANG Shiwen. Power load forecasting in the time series analysis method based on lifting wavelet[J]. Electrical Automation, 2017, 39(3):72-76.
[9]	肖白, 聂鹏, 穆钢, 等. 基于多级聚类分析和支持向量机的空间负荷预测方法[J]. 电力系统自动化, 2015, 39(12):56-61.
	XIAO Bai, NIE Peng, MU Gang, et al. A spatial load forecasting method based on multilevel clustering analysis and support vector machine[J]. Automation of Electric Power Systems, 2015, 39(12):56-61.
[10]	SINGH P, DWIVEDI P. Integration of new evolutionary approach with artificial neural network for solving short term load forecast problem[J]. Applied Energy, 2018, 217:537-549. doi: 10.1016/j.apenergy.2018.02.131 URL
[11]	孔祥玉, 郑锋, 鄂志君, 等. 基于深度信念网络的短期负荷预测方法[J]. 电力系统自动化, 2018, 42(5):133-139.
	KONG Xiangyu, ZHENG Feng, E Zhijun, et al. Short-term load forecasting based on deep belief network[J]. Automation of Electric Power Systems, 2018, 42(5):133-139.
[12]	房龙江. 多尺度空间分辨率下的多级负荷预测方法研究[D]. 吉林: 东北电力大学, 2018.
	FANG Longjiang. Study on the predition method of multi-stage load in multi-scale spatial resolution[D]. Jilin: Northeast Dianli University, 2018.
[13]	顾洁, 孟璐, 郑睿程, 等. 考虑集群辨识的海量用户负荷分层概率预测[J]. 电力系统自动化, 2021, 45(5):71-78.
	GU Jie, MENG Lu, ZHENG Ruicheng, et al. Load-stratified probability forecasting for massive users considering cluster identification[J]. Automation of Electric Power Systems, 2021, 45(5):71-78.
[14]	肖峻, 张璇, 张婷, 等. 应用信息熵原理的多路径负荷预测协同方法[J]. 电力系统及其自动化学报, 2013, 25(2):42-47.
	XIAO Jun, ZHANG Xuan, ZHANG Ting, et al. Method of multi-path load forecasting collaboration using maximum entropy principle[J]. Proceedings of the Chinese Society of Universities for Electric Power System and Its Automation, 2013, 25(2):42-47.
[15]	LLOYD J R. GEFCom2012 hierarchical load forecasting: Gradient boosting machines and Gaussian processes[J]. International Journal of Forecasting, 2014, 30(2):369-374. doi: 10.1016/j.ijforecast.2013.07.002 URL
[16]	BEN TAIEB S, HYNDMAN R J. A gradient boosting approach to the Kaggle load forecasting competition[J]. International Journal of Forecasting, 2014, 30(2):382-394. doi: 10.1016/j.ijforecast.2013.07.005 URL
[17]	PANG Y, YAO B, ZHOU X D, et al. Hierarchical electricity time series forecasting for integrating consumption patterns analysis and aggregation consistency[C]// Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2018: 3506-3512.
[18]	SPILIOTIS E, ABOLGHASEMI M, HYNDMAN R J, et al. Hierarchical forecast reconciliation with machine learning[J]. Applied Soft Computing, 2021, 112:107756.
[19]	亢良伊, 王建飞, 刘杰, 等. 可扩展机器学习的并行与分布式优化算法综述[J]. 软件学报, 2018, 29(1):109-130.
	KANG Liangyi, WANG Jianfei, LIU Jie, et al. Survey on parallel and distributed optimization algorithms for scalable machine learning[J]. Journal of Software, 2018, 29(1):109-130.
[20]	BOYD S. Distributed optimization and statistical learning via the alternating direction method of multipliers[M]. San Francisco, CA, USA: Now Publishers Inc, 2010.
[21]	CHAMIKARA M A P, BERTOK P, KHALIL I, et al. Privacy preserving distributed machine learning with federated learning[J]. Computer Communications, 2021, 171:112-125. doi: 10.1016/j.comcom.2021.02.014 URL
[22]	MCMAHAN H B, MOORE E, RAMAGE D, et al. Communication-efficient learning of deep networks from decentralized data[EB/OL]. [2021-06-20]. https://arxiv.org/abs/1602.05629.
[23]	康重庆, 牟涛, 夏清. 电力系统多级负荷预测及其协调问题: (一)研究框架[J]. 电力系统自动化, 2008, 32(7):34-38.
	KANG Chongqing, MU Tao, XIA Qing. Power system multilevel load forecasting and coordinating: Part one. Research framework[J]. Automation of Electric Power Systems, 2008, 32(7):34-38.
[24]	沈泉江, 郭乃网, 郑作梁. 基于用电模式聚类的层级电力时序预测方法[J]. 计算机应用与软件, 2020, 37(11):73-78.
	SHEN Quanjiang, GUO Naiwang, ZHENG Zuoliang. Hierarchical electricity time series forecasting method based on clustering of electricity consumption patterns[J]. Computer Applications and Software, 2020, 37(11):73-78.
[25]	张世旭, 苗世洪, 杨炜晨, 等. 基于自适应步长ADMM的配电网分布式鲁棒优化调度策略[J]. 高电压技术, 2021, 47(1):81-93.
	ZHANG Shixu, MIAO Shihong, YANG Weichen, et al. Distributed robust optimal dispatch for active distribution networks based on alternative direction method of multipliers with dynamic step size[J]. High Voltage Engineering, 2021, 47(1):81-93.
[26]	HU L, YAN H Y, LI L, et al. MHAT: An efficient model-heterogenous aggregation training scheme for federated learning[J]. Information Sciences, 2021, 560:493-503. doi: 10.1016/j.ins.2021.01.046 URL
[27]	HEGEDÜS I, DANNER G, JELASITY M. Decentralized learning works: An empirical comparison of gossip learning and federated learning[J]. Journal of Parallel and Distributed Computing, 2021, 148:109-124. doi: 10.1016/j.jpdc.2020.10.006 URL
[28]	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780. doi: 10.1162/neco.1997.9.8.1735 URL
[29]	陈纬楠, 胡志坚, 岳菁鹏, 等. 基于长短期记忆网络和LightGBM组合模型的短期负荷预测[J]. 电力系统自动化, 2021, 45(4):91-97.
	CHEN Weinan, HU Zhijian, YUE Jingpeng, et al. Short-term load prediction based on combined model of long short-term memory network and light gradient boosting machine[J]. Automation of Electric Power Systems, 2021, 45(4):91-97.
[30]	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.
[31]	姚子麟, 张亮, 邹斌, 等. 含高比例风电的电力市场电价预测[J]. 电力系统自动化, 2020, 44(12):49-55.
	YAO Zilin, ZHANG Liang, ZOU Bin, et al. Electricity price prediction for electricity market with high proportion of wind power[J]. Automation of Electric Power Systems, 2020, 44(12):49-55.
[32]	HONG T, XIE J R, BLACK J. Global energy forecasting competition 2017: Hierarchical probabilistic load forecasting[J]. International Journal of Forecasting, 2019, 35(4):1389-1399. doi: 10.1016/j.ijforecast.2019.02.006 URL
[33]	孙庆凯, 王小君, 张义志, 等. 基于LSTM和多任务学习的综合能源系统多元负荷预测[J]. 电力系统自动化, 2021, 45(5):63-70.
	SUN Qingkai, WANG Xiaojun, ZHANG Yizhi, et al. Multiple load prediction of integrated energy system based on long short-term memory and multi-task learning[J]. Automation of Electric Power Systems, 2021, 45(5):63-70.

方法	MAPE/%				聚合一致性
方法	L1	L2	L3	平均值	聚合一致性
独立预测	2.54	2.39	2.17	2.36	×
传统方法	2.54	2.58	3.14	2.75	?
本文方法(LSTM)	1.61	1.36	1.03	1.33	?
本文方法(ANN)	2.07	1.76	1.71	1.84	?
本文方法(线性回归)	3.27	2.92	2.78	2.99	?

方法	RMSE/MW				聚合一致性
方法	L1	L2	L3	平均值	聚合一致性
独立预测	70.06	127.54	234.77	144.12	×
传统方法	70.06	154.41	337.45	187.30	?
本文方法(LSTM)	41.35	61.91	112.02	71.76	?
本文方法(ANN)	56.31	97.11	184.57	112.66	?
本文方法(线性回归)	103.14	196.01	361.39	220.18	?

方法	MA/%				聚合一致性
方法	L1	L2	L3	平均值	聚合一致性
独立预测	97.46	97.60	97.83	97.55	×
传统方法	97.46	97.42	96.86	97.36	?
本文方法(LSTM)	98.40	98.63	98.97	98.54	?
本文方法(ANN)	97.93	98.24	98.29	98.06	?
本文方法(线性回归)	96.73	97.08	97.22	96.89	?