基于遗传模拟退火算法改进BP神经网络的中长期电力负荷预测

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (988 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Aiming at the problems of over-fitting, low accuracy and low efficiency in current medium and long-term load forecasting methods, a novel model, which is based on improved BP neural network (BP-GSA), is proposed. Firstly, a standard three-layer neural network including the input layer, the hidden layer and the output layer is established. The paper selects GDP, secondary industry GDP, urban resident population, monthly average temperature as input variables, and monthly load as the output variable. Secondly, the genetic simulated annealing algorithm is used to continuously modify the network node connection weights until the optimal network node connection weight distribution is achieved according to the optimal fitness standard. Finally, with the optimal solution of weights substituted, the paper obtains the model that has the minimum mean square error through the training of the data. The calculation example compares the BP-GSA model proposed in the paper with the other four types of traditional methods by predicting one city's monthly load in 2020. The error analysis shows that the BP-GSA provides the best prediction. Then the model is applied to other different years. The error remains stable, which verifies the robustness of the algorithm.

Key words： load forecasting genetic algorithm (GA) simulated annealing BP neural network

Received: 11 March 2021

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	XU Yang
	ZHANG Zitao

Cite this article:

XU Yang,ZHANG Zitao. Medium and long-term power load forecasting based on BP neural network improved by genetic simulated annealing algorithm[J]. Electrical Engineering, 2021, 22(9): 70-76.

URL:

http://dqjs.cesmedia.cn/EN/Y2021/V22/I9/70

[1] 魏华栋, 陶媛, 蔡昌春, 等. 基于改进长短期记忆神经网络的短期负荷预测[J]. 电测与仪表, 2020, 57(19): 93-98.
[2] 张帅, 杨晶显, 刘继春, 等. 基于多尺度时序建模与估计的电力负荷数据恢复[J]. 电工技术学报, 2020, 35(13): 2736-2746.
[3] 张敏, 钱霜秋, 吴仲麒, 等. 基于数据挖掘技术的中长期负荷预测方法[J]. 电气技术, 2021, 22(6): 43-48.
[4] 陈毅波, 郑玲, 姚建刚. 基于粗糙集理论与D-S证据理论改进的多元回归负荷预测方法研究[J]. 电力系统保护与控制, 2016, 44(6): 62-67.
[5] 李滨, 覃芳璐, 吴茵, 等. 基于模糊信息粒化与多策略灵敏度的短期日负荷曲线预测[J]. 电工技术学报, 2017, 32(9): 149-159.
[6] 潘文虎, 夏友斌, 宋铭敏, 等. 基于累积平均气温模型的气象负荷预测[J]. 电气技术, 2020, 21(4): 67-70.
[7] 陈先飞, 何山, 王杰, 等. 基于MGM(1, n, r)的主动配电网中长期负荷预测[J]. 太阳能学报, 2020, 41(2): 189-193.
[8] 徐源, 程潜善, 李阳, 等. 基于大数据聚类的电力系统中长期负荷预测[J]. 电力系统及其自动化学报, 2017, 29(8): 44-48.
[9] 吴耀武, 娄素华, 卢斯煜, 等. 基于改进的D-S证据理论的中长期负荷预测方法[J]. 电工技术学报, 2012, 27(8): 158-162.
[10] 林天祥, 张宇. 灰色Verhulst与等维新息组合模型在中长期负荷预测中的研究[J]. 电气技术, 2017, 18(3): 42-46.
[11] 龙金莲, 卢家暄, 张玉. 基于GMDH-PSO-LSSVM中长期电力负荷预测[J]. 贵州大学学报(自然科学版), 2017, 34(6): 50-53.
[12] 尹星露, 肖先勇, 孙晓璐. 基于预测有效度和马尔科夫-云模型的母线负荷预测模型筛选与变权重组合预测[J]. 电力自动化设备, 2015, 35(3): 114-119.
[13] 宋建, 束洪春, 董俊, 等. 基于GM(1, 1)与BP神经网络的综合负荷预测[J]. 电力建设, 2020, 41(5): 75-80.
[14] 蒋美云. 基于模拟退火算法优化的BP神经网络预测模型[J]. 软件工程, 2018(7): 36-38.
[15] 郭彩杏, 郭晓金, 柏林江. 改进遗传模拟退火算法优化BP算法研究[J]. 小型微型计算机系统, 2019, 40(10): 2063-2067.
[16] 张巨林. 基于模拟退火优化BP神经网络的变形监测数据预测方法[J]. 测控技术, 2020, 39(11): 57-62.