基于改进人工鱼群-蛙跳算法优化LSSVM参数短期负荷预测

doi:10.16180/j.cnki.issn1007-7820.2020.12.013

摘要/Abstract

摘要：

短期电力负荷预测在电力系统安全调度、经济运行方面起到关键作用。在用最小二乘支持向量机进行负荷预测时,参数选择将直接影响预测精度。为了提高LSSVM负荷预测精度,文中提出一种基于Levy变异自适应视野人工鱼群-蛙跳算法对LSSVM进行参数优化的方法。以某县负荷、天气等历史数据对LSSVM进行训练,建立LAVAFSA-SFLA-LSSVM、AFSA-LSSVM、LAFSA-SFLA-LSSVM共3种预测模型,对该地区某日24 h的电力负荷进行预测。算例结果表明,LAVAFSA-SFLA-LSSVM预测精度比AFSA-LSSVM和LAFSA-SFLA-LSSVM更高,预测误差更小。

关键词: 短期负荷预测, 电力系统调度, 预测精度, 最小二乘支持向量机, 改进人工鱼群-蛙跳算法, 优化参数

Abstract:

Short-term load forecasting plays a key role in safe dispatching and economic operation of power system.The parameters of the LSSVM directly affect the prediction effect during the load forecasting accuracy. In order to improve LSSVM load prediction accuracy, a method based on levy adaptive vision artificial fish swarm-shuffled frog leaping algorithm for parameter optimization of LSSVM is proposed. LSSVM is trained by historical data such as load and weather in a certain area. The LAFSA-SFLA-LSSVM forecasting model, the LAVAFSA-SFLA-LSSVM forecasting model and the AFSA-LSSVM forecasting model are established for power load forecasting in a certain area within 24 hours of a certain day. The results show that the accuracy of the LAVAFSA-SFLA-LSSVM forecasting model is higher than the AFSA-LSSVM forecasting model and the LAFSA-SFLA-LSSVM forecasting model, and the prediction error is smaller.

Key words: short-term load forecasting, power system scheduling, prediction accuracy, least squares support vector machine, improve artificial fish swarm-shuffled frog leaping algorithm, optimization parameter

中图分类号:

TP13

杨海柱,江昭阳,李梦龙,康乐. 基于改进人工鱼群-蛙跳算法优化LSSVM参数短期负荷预测[J]. 电子科技, 2020, 33(12): 67-74.

YANG Haizhu,JIANG Zhaoyang,LI Menglong,KANG Le. Parameters Selection for LSSVM Based on Artificial Fish Swarm-Shuffled Frog Jump Algorithms Optimization in Short-Term Load Forecasting[J]. Electronic Science and Technology, 2020, 33(12): 67-74.

图/表 7

图1

图2

图3

表1

表2

图4

图5

参考文献 22

[1]	廖旎焕, 胡智宏, 马莹莹, 等. 电力系统短期负荷预测方法综述[J]. 电力系统保护与控制, 2011,39(1):147-152. doi: 10.7667/j.issn.1674-3415.2011.01.028
	Liao Nihuan, Hu Zhihong, Ma Yingying, et al. Review of the short-term load forecasting methods of electric power system[J]. Power System Protection and Control, 2011,39(1):147-152. doi: 10.7667/j.issn.1674-3415.2011.01.028
[2]	蒋小亮, 蒋传文, 彭明鸿, 等. 基于时间连续性及季节周期性的风速短期组合预测方法[J]. 电力系统自动化, 2010,34(15):75-79.
	Jiang Xiaoliang, Jiang Chuanwen, Peng Minghong, et al. A short-term combination wind speed forecasting method considering seasonal periodicity and time-continuity[J]. Automation of Electric Power Systems, 2010,34(15):75-79.
[3]	张健美, 周步祥, 林楠, 等. 灰色Elman神经网络的电网中长期负荷预测[J]. 电力系统及其自动化学报, 2013,25(4):145-149.
	Zhang Jianmei, Zhou Buxiang, Lin Nan, et al. Prediction of mid-long term load based on gray elman neural networks[J]. Proceedings of the CSU-EPSA, 2013,25(4):145-149.
[4]	万昆, 柳瑞禹. 区间时间序列向量自回归模型在短期电力负荷预测中的应用[J]. 电网技术, 2012,36(11):77-81.
	Wan Kun, Liu Ruiyu. Application of interval time-series vector autoregressive model in short-term load forecasting[J]. Power System Technology, 2012,36(11):77-81.
[5]	周德强, 武本令. 灰色BP神经网络模型的优化及负荷预测[J]. 电力系统保护与控制, 2011,39(21):65-69.
	Zhou Deqiang, Wu Benling. Optimization and power load forecasting of gray BP neural network model[J]. Power System Protection and Control, 2011,39(21):65-69.
[6]	房乐楠, 何腾鹏, 刘宇红. 一种改进型PSO算法在SVM参数寻优种的应用[J]. 电子科技, 2018,31(6):17-19,31.
	Fang Lenan, He Tengpeng, Liu Yuhong. Application of an improved PSO algorithm in SVM parameter optimization[J]. Electronic Science and Technology, 2018,31(6):17-19,31.
[7]	王奔, 冷北雪, 张喜海. 支持向量机在短期负荷预测中的应用概况[J]. 电力系统及其自动化学报, 2011,23(4):115-121.
	Wang Ben, Leng Beixue, Zhang Xihai. Application profiles of support vector machine in short-term load forecasting[J]. Procceedings of the CSU-EPSA, 2011,23(4):115-121.
[8]	傅美平, 马红伟, 毛建容. 基于相似日和最小二乘支持向量机的光伏发电短期预测[J]. 电力系统保护与控制, 2012,40(16):65-69. doi: 10.7667/j.issn.1674-3415.2012.16.011
	Fu Meiping, Ma Hongwei, Mao Jianrong. Short-term photovoltaic power forecasting based on similar days and least square support vector machine[J]. Power System Protection and Control, 2012,40(16):65-69. doi: 10.7667/j.issn.1674-3415.2012.16.011
[9]	陈刚, 闫飞, 王烨, 等. 基于参数优化的最小二乘支持向量机状态估计方法[J]. 电力系统保护与控制, 2011,39(19):83-88. doi: 10.7667/j.issn.1674-3415.2011.19.014
	Cheng Gang, Yan Fei, Wang Ye, et al. State estimate based on parameter-optimized least square support vector machines[J]. Power System Protection and Control, 2011,39(19):83-88. doi: 10.7667/j.issn.1674-3415.2011.19.014
[10]	李霄, 王昕, 郑益慧, 等. 基于改进最小二乘支持向量机和预测误差校正的短期风电负荷预测[J]. 电力系统保护与控制, 2015,43(11):63-69. doi: 10.7667/j.issn.1674-3415.2015.11.010
	Li Xiao, Wang Xin, Zheng Yihui, et al. Short-term wind load forecasting based on improved LSSVM and error forecasting correction[J]. Power System Protection and Control, 2015,43(11):63-69. doi: 10.7667/j.issn.1674-3415.2015.11.010
[11]	吴景龙, 杨淑霞, 刘承水. 基于遗传算法优化参数的支持向量机短期负荷预测方法[J]. 中南大学学报(自然科学版), 2009,40(1):180-184.
	Wu Jinglong, Yang Shuxia, Liu Chengshui. Parameter selection for support vector machines based on genetic alrorithms to short-term power load forecasting[J]. Journal of Central South University(Science and Technology Edition), 2009,40(1):180-184.
[12]	Wang W C, Xu D M, Chau K W, et al. Improved annual rainfall-runoff forecasting using PSO-SVM model based on EEMD[J]. Journal of Hydroinformatics, 2013,15(4):1377-1390. doi: 10.2166/hydro.2013.134
[13]	龙文, 梁昔明, 龙祖强, 等. 基于改进蚁群算法优化LSSVM短期负荷预测[J]. 中南大学学报(自然科学版), 2011,42(11):3408-3414.
	Long Wen, Liang Ximing, Long Zuqiang, et al. Parameters selection for LSSVM based on modified ant colony optimization in short-term load forecasting[J]. Journal of Central South University(Science and Technology), 2011,42(11):3408-3414.
[14]	费腾, 张立毅, 陈雷. 混合Levy变异与混沌变异的改进人工鱼群算法[J]. 计算机工程, 2016,42(7):146-152,158. doi: 10.3969/j.issn.1000-3428.2016.07.025
	Fei Teng, Zhang Liyi, Chen Lei. Improved artificial fish-swarm algorithm mixing Levy mutation and chaotic mutation[J]. Computer Engineering, 2016,42(7):146-152,158. doi: 10.3969/j.issn.1000-3428.2016.07.025
[15]	景坤雷, 赵小国, 张新雨, 等. 具有levy变异和精英自适应竞争机制的蚁狮优化算法[J]. 智能系统学报, 2018,13(2):236-242.
	Jing Kunlei, Zhao Xiaoguo, Zhang Xinyu, et al. Ant lion optimizer with levy variation and adaptive elite competition mechanism[J]. CAAI Transactions on Intelligent Systems, 2018,13(2):236-242.
[16]	张晓博, 彭进业, 刘恬. 自适应视野和步长的混沌人工鱼群算法[J]. 微电子学与计算机, 2019,36(6):5-9,14.
	Zhang Xiaobo, Peng Jinye, Liu Tian. Adaptive visual field and step length of chaotic artificial fish swarm algorithm[J]. Microelectronics and Computer, 2019,36(6):5-9,14.
[17]	马宪民, 刘妮. 自适应视野的人工鱼群算法求解最短路径问题[J]. 通信学报, 2014,35(1):1-6.
	Ma Xianmin, Liu Ni. Improved artificial fish-swarm algorithm based on adaptive vision for solving the shortest path problem[J]. Journal on Communications, 2014,35(1):1-6.
[18]	朱旭辉, 倪志伟, 程美英. 变步长自适应的改进人工鱼群算法[J]. 计算机科学, 2015,42(2):210-216,246.
	Zhu Xuhui, Ni Zhiwei, Cheng Meiying. Self-adaptive improved artificial fish swarm algorithm with changing step[J]. Computer Science, 2015,42(2):210-216,246.
[19]	王波. 基于自适应t分布混合变异的人工鱼群算法[J]. 计算机工程与科学, 2013,35(4):120-124.
	Wang Bo. Artificial fish-school algorithm based on adaptive t distribution mixed mutation[J]. Computer Engineering and Science, 2013,35(4):120-124.
[20]	崔文华, 刘晓冰, 王伟, 等. 混合蛙跳算法研究综述[J]. 控制与决策, 2012,27(4):481-486,493.
	Cui Wenhua, Liu Xiaobing, Wang Wei, et al. Survey on shuffed frog leaping algorithm[J]. Control and Decision, 2012,27(4):481-486,493.
[21]	张沈习, 陈楷, 龙禹, 等. 基于混合蛙跳算法的分布式风电源规划[J]. 电力系统自动化, 2013,37(13):76-82. doi: 10.7500/AEPS201207219
	Zhang Shenxi, Chen Kai, Long Yu, et al. Distributed wind generator planning based on shuffled frog leaping algorithm[J]. Automation of Electric Power Systems, 2013,37(13):76-82. doi: 10.7500/AEPS201207219
[22]	代永强, 王联国, 施秋红, 等. 改进的混合蛙跳算法性能分析及其在电力系统经济调度中的应用[J]. 电力系统保护与控制, 2012,40(10):77-83.
	Dai Yongqiang, Wang Lianguo, Shi Qiuhong, et al. Performance analysis of improved SFLA and the application in economic dispatchof power system[J]. Power System Protection and Control, 2012,40(10):77-83.

函数	算法	全局最优解	最优解平均值
f₁(x)	AFSA	1.638 1	1.720 7
	LAFSA-SFLA	0.871 0	0.925 0
	LAVAFSA-SFLA	0.054 1	0.064 6
f₂(x)	AFSA	1.943 5	2.186 4
	LAFSA-SFLA	0.064 6	0.184 8
	LAVAFSA-SFLA	0.033 9	0.104 5

时段	负荷实际值 /MW	AFSA- LSSVM	LAFSA-SFLA- LSSVM	LAVAFSA-SFLA -LSSVM
1	812.97	778.55	780.58	800.99
2	760.08	712.10	715.31	732.15
3	731.84	701.89	708.88	712.98
4	686.69	652.36	663.59	671.71
5	652.28	625.56	628.27	630.19
6	619.81	590.21	595.78	599.61
7	608.22	571.01	579.36	582.98
8	580.51	548.15	550.23	558.31
9	622.92	595.93	596.58	599.78
10	670.84	630.59	633.13	650.84
11	737.49	705.89	709.21	712.89
12	825.60	775.70	780.67	800.90
13	843.53	803.98	809.87	817.37
14	837.21	802.11	810.86	825.41
15	824.04	780.39	785.26	800.03
16	813.45	765.82	769.43	795.24
17	802.63	747.69	765.57	789.79
18	778.18	733.89	741.56	753.85
19	739.08	700.82	710.12	723.99
20	722.38	675.36	688.15	700.98
21	769.04	735.81	739.53	744.04
22	822.65	780.69	786.84	800.67
23	860.68	806.81	812.41	842.64
24	822.05	788.03	792.96	810.34