改进粒子群算法优化回声状态网络的电力需求预测研究

计算机工程与科学 ›› 2022, Vol. 44 ›› Issue (08): 1457-1466.

改进粒子群算法优化回声状态网络的电力需求预测研究

王林，王燕丽，安泽远

（华中科技大学管理学院，湖北武汉 430074）

收稿日期:2021-01-21 修回日期:2021-05-06 接受日期:2022-08-25 出版日期:2022-08-25 发布日期:2022-08-25
基金资助:
国家自然科学基金(71771095);中央高校基本科研业务费专项资金（HUST:2019kfyRCPY038）

Echo state networks with improved particle swarm optimization algorithm for electricity demand forecasting

WANG Lin,WANG Yan-li,AN Ze-yuan

(School of Management,Huazhong University of Science & Technology,Wuhan 430074,China)

Received:2021-01-21 Revised:2021-05-06 Accepted:2022-08-25 Online:2022-08-25 Published:2022-08-25

摘要/Abstract

摘要： 首先引入自适应算子对标准粒子群优化算法PSO的惯性权重和学习因子进行改进，以提高其探索当前空间和开发未知空间之间的平衡性。同时，采用非线性函数来构建回声状态网络ESN储备池内部状态之间的非线性关系。接着利用改进的粒子群优化算法APSO对非线性回声状态网络NESN的关键参数进行优化，以构建APSO-NESN组合预测模型。最后运用该模型进行电力需求预测。实验结果表明,相比自回归移动平均模型、多元线性回归、标准ESN及其他预测模型,APSO-NESN模型具有更高的预测精度。

关键词: 电力需求预测, 回声状态神经网络, 粒子群优化算法

Abstract: Firstly, an adaptive operator is introduced to improve the inertial weights and learning factors of the standard particle swarm optimization algorithm (PSO) to improve the balance between the exploration of the current space and the unknown space. At the same time, a nonlinear function is used to construct the nonlinear relationship between the internal states of the Echo State Networks (ESN). Then the improved PSO (APSO) is used to optimize the key parameters of Nonlinear ESN (NESN) to propose an assembled prediction model named APSO-NESN. Finally, the model is used to solve electricity demand forecasting problems. The experimental results show that the APSO-NESN model has higher prediction accuracy than the ARIMA, MLR, standard ESN, and other models.

Key words: electricity consumption forecasting, echo state network (ESN), particle swarm optimization algorithm (PSO)

王林, 王燕丽, 安泽远. 改进粒子群算法优化回声状态网络的电力需求预测研究[J]. 计算机工程与科学, 2022, 44(08): 1457-1466.

WANG Lin, WANG Yan-li, AN Ze-yuan. Echo state networks with improved particle swarm optimization algorithm for electricity demand forecasting[J]. Computer Engineering & Science, 2022, 44(08): 1457-1466.

参考文献［16］

［1］	Sarkodie S A.Estimating Ghana’s electricity consumption by 2030:An ARIMA forecast［J］.Energy Sources,Part B:Economics,Planning,and Policy,2017,12(10):936-944.
［2］	Wang Z X,Hao P.An improved grey multivariable model for predicting industrial energy consumption in China ［J］.Applied Mathematical Modeling,2016,40(11-12):5745-5758.
［3］	Kialashaki A,Reisel J R.Development and validation of artificial neural network models of the energy demand in the industrial sector of the United States ［J］.Energy,2014,76:749-760.
［4］	Rahman A, Srikumar V,Smith A D.Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks［J］.Applied Energy,2018,212:372-385.
［5］	Ma Yu,Huang Zhe-zhu,Zhong Li-bo,et al.Analysis of power load forecasting based on CNN and SVR［J］.Northeast Electric Power Technology,2020,41(2):37-41.(in Chinese)
［6］	Jaeger H,Haas H.Harnessing nonlinearity:Predicting chaotic systems and saving energy in wireless communication［J］.Science,2004,304(5667):78-80.
［7］	Zhang Ya-li,Hu Bo-xuan,Li Sha-sha,et al.The short-term power load forecasting model of combing ILMD and ESN based on similar days searching ［J］.Journal of Zhengzhou University (Natural Science Edition),2017,49(2):121-127.(in Chinese)
［8］	Li X, Zhong L, Xue F, et al. A priori data-driven multi- clustered reservoir generation algorithm for echo state network［J］.PLOS One,2015,10(4):e0120750.
［9］	Hu H,Wang L,Lü S X.Forecasting energy consumption and wind power generation using deep echo state network［J］.Renewable Energy,2020,154:598-613.
［10］	Wang L,Hu H L,Ai X Y,et al.Effective electricity energy consumption forecasting using echo state network improved by differential evolution algorithm［J］.Energy,2018,153:801-815.
［11］	Eberhart R,Kennedy J.Particle swarm optimization［C］∥Proc of the IEEE International Conference on Neural Networks,1995:1942-1948.
［12］	Zhu Xiao-ming,Zhang Hui-bin. Stability analysis of particle swarm optimization algorithm and its improved algorithm［J］.Computer Science,2013,40(3):275-278.(in Chinese)
［13］	Zhang X W,Liu H,Zhang T,et al.Terminal crossover and steering-based particle swarm optimization algorithm with disturbance［J］.Applied Soft Computing,2019,85:105841.
［14］	Rehman O U,Yang J Q,Zhou Q,et al.A modified QPSO algorithm applied to engineering inverse problems in electromagnetics［J］.International Journal of Applied Electromagnetics and Mechanics,2017,54(1):107-121.
［15］	Shi Y,Eberhart R.Empirical study of particle swarm optimizer［C］∥Proc of IEEE International Conference on Evolutionary Computation,1999:1948-1950.
［16］	Ju Yao,Qi Lin,Liu Shuai.Short-term wind power forecasting based on improved crow search algorithm and ESN neural network［J］.Power System Protection and Control,2019,47(4):58-64.(in Chinese)
［17］	Ardakani F J,Ardehali M M.Novel effects of demand side management data on accuracy of electrical energy consumption modeling and long-term forecasting［J］.Energy Conversion and Management,2014,78:745-752.
［18］	Ardakani F J, Ardehali M M.Long-term electrical energy consumption forecasting for developing and developed economies based on different optimized models and historical data types ［J］.Energy,2014,65:452-461.
［19］	Zeng Y R,Zeng Y,Choi B,et al. Multifactor-influenced energy consumption forecasting using enhanced back-propagation neural network［J］.Energy,2017,127:381-396.
［20］	Shi Y,Eberhart R.A modified particle swarm optimizer［C］∥Proc of IEEE International Conference on Evolutionary Computation,1998:4-9.
［21］	Friedman J H.Greedy function approximation:A gradient boosting machine ［J］.Annals of Statistics,2001,29(5):1189-1232.
	附中文参考文献:
［5］	马煜,黄哲洙,钟丽波,等.基于CNN和SVR相结合的电力负荷预测分析［J］.东北电力技术,2020,41(2):37-41.
［7］	张亚丽,胡伯轩,李莎莎,等.基于相似日搜索的改进LMD与ESN相结合的短期电力负荷预测模型［J］.郑州大学学报(理学版),2017,49(2):121-127.
［12］	朱小明,张慧斌.PSO算法的稳定性分析及算法改进［J］.计算机科学,2013,40(3):275-278.
［16］	琚垚,祁林,刘帅.基于改进乌鸦算法和ESN神经网络的短期风电功率预测［J］.电力系统保护与控制,2019,47(4):58-64.