BP人工神经网络评价在建筑能源需求侧管理综合评价中的应用研究(上):综述及算法  

Research on the Application of BP Artificial Neural Network in DSM Comprehensive Evaluation

作　　者：吴俊伟 梁星宇[1,2] 于兵 金俭 王东伟 

机构地区：[1]上海东方延华节能技术服务股份有限公司 [2]同济大学机械与能源工程学院 [3]上海延华智能科技(集团)股份有限公司

出　　处：《智能建筑》2016年第10期51-55,共5页Intelligent Building

摘　　要：建筑能源需求侧管理(DSM)是应对能源危机的重要手段之一.DSM综合评价系统对于发展、改进和推广能源需求侧管理意义重大。然而DSM综合评价是一个复杂的多指标综合评价问题,传统的综合评价方法应用在DSM综合评价中往往存在效率低、成本高、主观随意性大等问题。因此.本文探究了BP人工神经网络评价法在DSM综合评价中的应用,结合DSM综合评价的特点,分析其应用的可行性、优越性及现有缺陷,并辅以实例加以论证,为DSM综合评价系统中评价方法的选择提供一种解决方案。Demand Side Management （DSM） is one of the most important measures to deal with the energy crisis. For the improvement and promotion of DSM, it is particularly significant to evaluate DSM with DSM comprehensive evaluation system. But to evaluate it synthetically is a colnplex evaluation work with multiple indexes while the traditional comprehensive evaluation methods usually tend to be low-efficient, high-cost and subjective in application. Therefore, according to the feature of DSM comprehensive evaluation, this paper researches the application of the comprehensive evaluation methods based on back propagation （BP） artificial neural network in DSM comprehensive evaluation. The author also analyzes the feasibility, advantages and disadvantages of BP artificial neural network in application, and proves it with a practical example. This paper provides a solution about the selection of comprehensive evaluation methods m DSM comprehensive evaluation system.

关 键 词：BP人工神经网络 需求侧管理 综合评价 

分 类 号：TU111.195[建筑科学—建筑理论] TP183[自动化与计算机技术—控制理论与控制工程]