基于改进PSO-BP算法的冷负荷预测模型

doi:10.16182/j.issn1004731x.joss.19-0223

系统仿真学报 ›› 2021, Vol. 33 ›› Issue (1): 54-61.doi: 10.16182/j.issn1004731x.joss.19-0223

基于改进PSO-BP算法的冷负荷预测模型

于军琪¹, 井文强¹, 赵安军^1,2, 任延欢¹, 周梦², 黄馨乐¹, 杨雪³

1.西安建筑科技大学建筑设备与工程学院,陕西西安 710055;
2.西安建筑科大工程技术有限公司,陕西西安 710055;
3.大唐移动通信设备有限公司,陕西西安 710055

收稿日期:2019-05-23 修回日期:2019-11-15 发布日期:2021-01-18
作者简介:于军琪(1969-),男,博士,教授,研究方向为建筑智能与节能技术。E-mail：junqiyu@126.com
基金资助:
陕西省重点研发计划(2017zdcxl-sf-03-02),陕西省教育厅产业化培育项目(17JF016),陕西省科技厅专项科研项目(2017JM6106),校基础研究基金(JC1706)

Cold Load Prediction Model Based on Improved PSO-BP Algorithm

Yu Junqi¹, Jing Wenqiang¹, Zhao Anjun^1,2, Ren Yanhuan¹, Zhou Meng², Huang Xinle¹, Yang Xue³

1. School of Construction Equipment and Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China;
2. Xi'an University of Architecture and Technology Engineering Co., Ltd., Xi'an 710055, China;
3. Datang Mobile Communications Equipment Co., Ltd., Xi'an 710055, China

Received:2019-05-23 Revised:2019-11-15 Published:2021-01-18

摘要/Abstract

摘要： 针对PSO-BP(Particle Swarm Optimization-Back Propagation)神经网络预测模型在冰蓄冷空调冷负荷预测中存在输入输出数据关联度低和预测模型存在误差的情况,提出了一种基于JMP数据处理软件、PSO-BP神经网络和马尔可夫链的组合预测方法。利用JMP处理输入数据,剔除耦合度低的样本,进行PSO-BP神经网络训练,得到冷负荷预测结果,利用马尔可夫链消除系统产生的随机误差得到最终预测结果。结果表明：该组合预测方法对比传统PSO-BP算法其预测精度更高,预测结果符合商场冷负荷的变化规律,满足实际的应用需求。

关键词: 空调冷负荷, PSO-BP神经网络, 预测算法, 马尔可夫链

Abstract: Aiming at the low correlation between input and output data and the error of prediction model in PSO-BP neural network prediction model, a combined prediction method based on JMP, PSO-BP neural network and Markov chain is proposed. The method first uses JMP data processing software to process the input data and eliminating the low coupling degree samples, then conducts PSO-BP neural network training to obtain the cold load prediction results, and finally uses markov chain to eliminate the random errors generated by the system to obtain the final prediction results. The results show that the combined prediction method has higher prediction accuracy, and the prediction result conforms to the change rule of the shopping mall load, and meets the actual application requirements.

Key words: air conditioning cooling load, PSO-BP neural, prediction algorithms, markov chain

中图分类号:

TU831
TP391

于军琪, 井文强, 赵安军, 任延欢, 周梦, 黄馨乐, 杨雪. 基于改进PSO-BP算法的冷负荷预测模型[J]. 系统仿真学报, 2021, 33(1): 54-61.

Yu Junqi, Jing Wenqiang, Zhao Anjun, Ren Yanhuan, Zhou Meng, Huang Xinle, Yang Xue. Cold Load Prediction Model Based on Improved PSO-BP Algorithm[J]. Journal of System Simulation, 2021, 33(1): 54-61.

参考文献

[1] 刘静纨, 魏东, 朱为明. 神经网络模糊预测优化控制在VAV系统中的应用[J]. 系统仿真学报, 2010, 22(12): 2909-2914.
Liu Jingwan, Wei Dong, Zhu Weiming.Application of Neural Network Fuzzy Predictive Optimal Control in VAV System[J]. Journal of System Simulation, 2010, 22(12): 2909-2914.
[2] 于军琪, 王胤钧, 陈旭, 等. 基于粒子群算法的冰蓄冷空调系统运行优化研究[J]. 西安建筑科技大学学报(自然科学版), 2018, 50(1): 148-154.
Yu Junqi, Wang Yinjun, Chen Xu, et al.Study on Operation Optimization of Ice Storage Air Conditioning System Based on Particle Swarm Optimization[J]. Journal of Xi'an University of Architecture and Technology (Natural Science Edition), 2018, 50(1): 148-154.
[3] Wei Y X, Zhang X X.A Review of Data-Driven Approaches for Prediction and Classification of Building Energy Consumption[J]. Renewable and Sustainable Energy Reviews (S1364-0321), 2018, 82: 1027-1047.
[4] Li Q, Meng Q L, Cai J J, et al.Applying Support Vector Machine to Predict Hourly Cooling Load in the Building[J]. Appl Energy (S0306-2619), 2009, 86(10): 2249-2256.
[5] Zhao H X, Magoulès F.Parallel Support Vector Machines Applied to the Prediction of Multiple Buildings Energy Consumption[J]. J Algorithms Comput Technol (S0196-6774), 2010, 4(2): 231-250.
[6] Li Q, Meng Q, Cai J, et al.Predicting Hourly Cooling Load in the Building: A Comparison of Support Vector Machine and Different Artificial Neural Networks[J]. Energy Convers Manag (S0196-8904), 2009, 50(1): 90-96.
[7] Swan L G, Ugursal V I.Modeling of End-use Energy Consumption in the Residential Sector: a Review of Modeling Techniques[J]. Renew Sustain Energy Rev (S1364-0321), 2009, 13(8): 1819-1835.
[8] Yu Z, Haghighat F, Fung B C M, et al. A Decision Tree Method for Building Energy Demand Modeling[J]. Energy Build (S0378-7788), 2010, 42(10): 1637-1646.
[9] Tso G K F, Yau K K W. Predicting Electricity Energy Consumption: A Comparison of Regression Analysis, Decision Tree and Neural Networks[J]. Energy (S0360-5442), 2007, 32(9): 1761-1768.
[10] Beyer H G.Evolutionary Algorithms in Noisy Environments: Theoretical Issues and Guidelines for Practice[J]. Comput Methods Appl Mech Eng (S0045-7825), 2000, 186(2/3/4): 239-267.
[11] Azadeh A, Ghaderi S F, Tarverdian S, et al.Integration of Artificial Neural Networks and Genetic Algorithm to Predict Electrical Energy Consumption[J]. Appl Math Comput (S0096-3003), 2007, 186(2): 1731-1741.
[12] Li K, Su H.Forecasting Building Energy Consumption with Hybrid Genetic Algorithm-Hierarchical Adaptive Network-Based Fuzzy Inference System[J]. Energy Build (S0378-7788), 2010, 42(11): 2070-2076.
[13] Li K J, Su H Y, Chu J.Forecasting Building Energy Consumption Using Neural Networks and Hybrid Neuro-Fuzzy System: A Comparative Study[J]. Energy Build (S0378-7788), 2011, 43(10): 2893-2899.
[14] Huang J F, He L L.Application of Improved PSO-BP Neural Network in Customer Churn Warning[J]. Procedia Computer Science (S1877-0599), 2018, 131: 1238-1246.
[15] 郭晨露. 西安某商城冰蓄冷空调负荷预测与多目标优化运行研究[D]. 西安: 西安建筑科技大学,2018.
Guo Chenlu.Research on load Prediction and Multi-objective Optimization Operation of Ice Storage Air conditioning in a shopping mall in Xi'an [D]. Xi'an: Xi'an University of Architecture and Technology, 2018.
[16] 赵新玥, 赵文, 陈华. pH测定检验能力验证及评价新方法的应用[J]. 药物分析杂志, 2018, 38(3): 545-550.
Zhao Xinyue, Zhao Wen, Chen Hua.Application of a New Method to Test the Ability of pH Determination and Evaluation[J]. Journal of Pharmaceutical Analysis, 2018, 38(3): 545-550.
[17] 刘义才, 刘斌, 石安伟. 区间化随机时延的网络控制系统建模与控制[J]. 系统仿真学报, 2018, 30(2): 654-663.
Liu Yicai, Liu Bin, Shi Anwei.Modeling and Control of Network Control System with Interval Random Delay[J]. Journal of System Simulation, 2013, 30(2): 654-663.
[18] 陆欣, 沈艳霞, 陈杰, 等. 考虑风力发电随机性的超短期风电功率区间预测研究[J]. 太阳能学报, 2017, 38(5): 1307-1315.
Lu Xin, Shen Yanxia, Chen Jie, et al.Study on Ultra-Short Term Wind Power Interval Prediction Considering Wind Power Generation Randomness[J]. Acta Solar Energy Sinica, 2017, 38(5): 1307-1315.
[19] 黄银华, 彭建春, 李常春, 等. 马尔科夫理论在中长期负荷预测中的应用[J]. 电力系统及其自动化学报, 2011, 23(5): 131-136.
Huang Yinhua, Peng Jianchun, Li Changchun, et al.Application of Markov Theory in Medium and Long-term Load Forecasting[J]. Journal of Power System Automation, 2011, 23(5): 131-136.
[20] 景亚平, 张鑫, 罗艳. 基于修正组合模型的青海省城市需水量预测[J]. 自然资源学报, 2012, 27(6): 1013-1021.
Jing Yaping, Zhang Xin, Luo Yan.Prediction of Urban Water Demand in Qinghai Province Based on Modified Combined Model[J]. Journal of Natural Resources, 2012, 27(6): 1013-1021.

基于改进PSO-BP算法的冷负荷预测模型

Cold Load Prediction Model Based on Improved PSO-BP Algorithm

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	刘灏哲, 李伟, 马萍, 杨明. 基于多源先验数据的系统性能评估方法[J]. 系统仿真学报, 2021, 33(11): 2673-2680.
[2]	王闯, 张勇, 李学贵, 董宏丽. 改进粒子群优化算法及其在聚类分析中应用[J]. 系统仿真学报, 2020, 32(8): 1577-1587.
[3]	潘文雯, 安冰玉, 池臧博, 张明敏, 胡铸鑫. 基于休假排队模型的小区开放效果仿真[J]. 系统仿真学报, 2018, 30(7): 2533-2539.