基于ISOA的LS-SVM地铁站空调系统能耗预测模型

doi:10.3969/j.issn.1006-2475.2018.10.008

计算机与现代化

基于ISOA的LS-SVM地铁站空调系统能耗预测模型

(1.北京工业大学信息学部,北京100124；2.数字社区教育部工程研究中心,北京100124；
3.城市轨道交通北京实验室,北京100124；4.计算智能与智能系统北京市重点实验室,北京100124)

收稿日期:2018-03-05 出版日期:2018-10-26 发布日期:2018-10-26
作者简介:高学金（1973-），男，河北唐山人，北京工业大学信息学部副教授，研究方向：复杂生产过程建模、优化与故障诊断，生物传感器；付龙晓（1991-），女，硕士研究生，研究方向：复杂生产过程建模，地铁站空调系统的节能；武翠霞（1992-），女，硕士研究生，研究方向：复杂生产过程建模，地铁站空调系统的节能；王普(1962-），男，研究员，博士，研究方向：复杂过程建模、优化与控制。
基金资助:
国家自然科学基金资助项目(61640312，61364009，61174109)；北京市自然科学基金资助项目（4172007）

Energy Consumption Prediction Model of Air-conditioning System #br# in Subway Station Based on ISOA-LS-SVM

（1. Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China；

2. Engineering Research Center of Digital Community, Ministry of Education, Beijing 100124, China；
3. Beijing Laboratory for Urban Mass Transit, Beijing 100124, China;
4. Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing 100124, China）

Received:2018-03-05 Online:2018-10-26 Published:2018-10-26

摘要/Abstract

摘要： 为提高地铁站空调系统能耗的预测精度，利用最小二乘支持向量机（Least Squares Support Vector Machines, LS-SVM）建立能耗预测模型是一种有效的方法。但是LS-SVM在处理大规模数据集的回归问题时难以确定最佳模型参数值，较大程度地影响了模型的拟合精度和泛化能力。为此，提出一种从算法搜索步长和搜索方向这2个方面进行改进的人群搜索算法（Improved Seeker Optimization Algorithm, ISOA）对LS-SVM建模过程中的模型参数进行优化选择。将所提出的基于ISOA-LS-SVM建立的能耗预测模型应用于北京某高校地铁实训平台。研究结果表明：该模型能够准确预测出系统能耗，相比于网格搜索法、粒子群算法以及传统的人群搜索算法，优化的LS-SVM在速度和精度上都有所提升。

关键词: 通风空调系统, 能耗预测模型, 最小二乘支持向量机, 人群搜索算法

Abstract: To improve the prediction accuracy of energy consumption of air conditioning system in subway station, it is an effective method to establish energy consumption forecasting model by Least Squares Support Vector Machines (LS-SVM). However, LS-SVM is difficult to determine the optimal model parameter value in dealing with regression problem for large datasets, which affects the fitting precision and generalization ability of the model to a large extent. An Improved Seeker Optimization Algorithm (ISOA) is proposed to optimize the model parameters in the LS-SVM modeling process by introducing an improved algorithm from search step and search direction. The energy consumption forecasting model based on ISOA-LS-SVM is applied to the training platform of subway in a school of Beijing. The results show that the model can accurately predict the energy consumption of the system. Compared with the grid search method, the particle swarm algorithm and the traditional population search algorithm, the LS-SVM is improved in speed and precision.

Key words: air conditioning system, energy consumption prediction model, least squares support vector machines, seeker optimization algorithm

中图分类号:

TP27

高学金1,2,3,4,付龙晓1,2,3,4,武翠霞1,2,3,4,王普1,2,3,4. 基于ISOA的LS-SVM地铁站空调系统能耗预测模型[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2018.10.008.

GAO Xue-jin1,2,3,4, FU Long-xiao1,2,3,4, WU Cui-xia1,2,3,4, WANG Pu1,2,3,4. Energy Consumption Prediction Model of Air-conditioning System #br# in Subway Station Based on ISOA-LS-SVM[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2018.10.008.

参考文献

［1］ RAHNAMA S, AFSHARI A, BERGSEE N C, et al. Experimental study of the pressure reset control strategy for energy-efficient fan operation : Part 1: Variable air volume ventilation system with dampers［J］. Energy and Buildings, 2017,139:72-77.
［2］ HUANG J, XU D, YUAN X, et al. Nonlinear control of back-to-back VSC-HVDC system via command-filter back stepping［J］. Journal of Control Science and Engineering, 2017,7(5):1-10.
［3］ FENG Z, REN Q, LI J, et al. An air-conditioning load forecasting based on dynamical combined residual error correction［J］. Open Automation and Control Systems Journal, 2015,7(1):1441-1449.
［4］邓劲梅. 模糊神经网络控制在中央空调中的研究［J］. 计算机与现代化, 2011(4):131-134..
［5］ TRATAR L F, MOJKERC B, TOMAN A, et al. Demand forecasting with four-parameter exponential smoothing［J］. International Journal of Production Economics, 2016,181:162-173.
［6］杨昭,余龙清,马锋,等. 地铁通风空调系统的逐时优化节能控制策略［J］. 天津大学学报, 2012,45(7):599-603.
［7］裴杰才,李志华,丁伟聪. 基于混合核函数PSO-SVM的模拟电路故障诊断［J］. 计算机与现代化, 2017(1):41-45.
［8］ WANG Z, YAN M. Online adaptive least squares support vector machine and its application in utility boiler combustion optimization systems［J］. Journal of Process Control, 2011,21(7):1040-1048.
［9］戬钢，王景成，葛阳，等. 城市小时级需水量的改进型引力搜索算法——最小二乘支持向量机模型［J］. 控制理论与应用, 2014，31（10）:1377-1382.
［10］晏密英,桂卫华,阳春华. 基于灰色关联和改进SVM的钴离子浓度预测研究［J］. 仪器仪表学报, 2011,32(5):961-967.
［11］叶永伟,陆俊杰,钱志勤,等. 基于LS-SVM的机械式温度仪表误差预测研究［J］. 仪器仪表学报, 2016,37(1):57-66.
［12］吕游,刘吉臻,杨婷婷,等. 基于PLS特征提取和LS-SVM结合的NOx排放特性建模［J］. 仪器仪表学报, 2013,34(11):2418-2424.
［13］张广明,袁宇浩,龚松建. 基于改进最小二乘支持向量机方法的短期风速预测［J］. 上海交通大学学报,2011,45(8):1125-1129.
［14］KRISHNANAND K R, ROUT P K, PANIGRAHI B K, et al. Solution to non-convex electric power dispatch problem using seeker optimization algorithm［C］// First International Conference on Swarm, Evolutionary, and Memetic Computing. 2010:537-544.
［15］魏立兵,赵峰,王思华. 基于人群搜索算法优化参数的支持向量机短期电力负荷预测［J］. 电测与仪表, 2016,53(8):45-49.
［16］DAI C, CHEN W, LI L, et al. Seeker optimization algorithm for parameter estimation of time-delay chaotic systems［J］. Physical Review E Statistical Nonlinear and Soft Matter Physics, 2011,83(2):036203.
［17］戴朝华. IIR数字滤波器设计的搜寻者优化算法［J］. 西南交通大学学报， 2009,44(6):871-876.
［18］SHAW B, MUKHERJEE V, GHOSHAL S P, et al. Solution of Economic Dispatch Problems by Seeker Optimization Algorithm［M］. Pergamon Press Inc., 2012:508-519.
［19］DAI C, CHEN W, ZHU Y, et al. Seeker optimization algorithm［C］// IEEE International Conference on Computational Intelligence and Security. 2007:225-229.
［20］YAN X, YANG W, SHI H, et al. A Group Search Optimization Based on Improved Small World and its Application on Neural Network Training in Ammonia Synthesis［M］. Elsevier Science, 2012:94-107.
［21］尹嘉鹏. 支持向量机核函数及关键参数选择研究［D］. 哈尔滨：哈尔滨工业大学, 2016.

[1]	苏立. 基于HHT变换和FOA_LSSVM的电缆故障诊断[J]. 计算机与现代化, 2017, 0(9): 96-101,105.
[2]	王磊1，殷姣姣1，余心杰2. 基于近红外光谱技术的三文鱼肉质分类研究[J]. 计算机与现代化, 2015, 0(9): 109-112.
[3]	赵伟. 基于SOA-LSSVM的短时交通流量预测[J]. 计算机与现代化, 2015, 0(6): 27-31.
[4]	乔国娟，陈光. 一种基于预测模型的负载均衡算法[J]. 计算机与现代化, 2014, 0(8): 91-95.
[5]	夏卿;李先锋. 基于改进PSO算法和LS-SVM的苹果分级检测[J]. 计算机与现代化, 2012, 1(201): 161-168,.

基于ISOA的LS-SVM地铁站空调系统能耗预测模型

Energy Consumption Prediction Model of Air-conditioning System #br# in Subway Station Based on ISOA-LS-SVM

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价