某大型城市智能供水调度优化算法研究与模拟实践  

Optimized Algorithm of Intelligent Water Supply Scheduling and Its Simulation Practice in a Large City

作　　者：林峰 李旭 曾翰 赵治成 童麒源 高健 LIN Feng;LI Xu;ZENG Han;ZHAO Zhi-cheng;TONG Qi-yuan;GAO Jian(Shenzhen Water and Environment Group Co.Ltd.,Shenzhen 518031,China;Zhejiang Heda Technology Co.Ltd.,Jiaxing 314000,China)

机构地区：[1]深圳市环境水务集团有限公司,广东深圳518031 [2]浙江和达科技股份有限公司,浙江嘉兴314000

出　　处：《中国给水排水》2023年第9期109-115,共7页China Water & Wastewater

摘　　要：随着大数据和人工智能的发展,城市供水调度开始由人工调度向智能调度方向演变。为此,以出厂压力优化控制和绿色节能为目标,设计了智能供水调度优化算法。该算法综合运用朴素贝叶斯等机器学习模型,构建包含总需水量预测模型、宏观水力模型、调度行为预测模型、综合评估算法的调度优化算法组合,实现“控压好、次数少、能耗低、空间大”的供水调度目标,并在深圳市5座自来水厂供水辖区对供水调度优化算法进行验证与应用。结果表明,该算法具有较高的准确性、可靠性和适用性。同时,智能调度控压效果显著优于人工调度,对于大中城市智能供水调度研究与实践具有借鉴意义。With the development of big data and artificial intelligence,urban water supply scheduling has evolved from manual scheduling to intelligent scheduling.This paper designed an optimized water supply scheduling algorithm to achieve the goal of optimal control of water supply pressure and green energy saving.The algorithm comprehensively utilized naive Bayes and other machine learning models to establish an optimized scheduling algorithm combination including the total water demand prediction model,macroscopic hydraulic model,scheduling behavior prediction model and comprehensive evaluation algorithm,so as to achieve the water supply scheduling target of“better control pressure,less scheduling times,low energy consumption and large space”.The optimized water supply scheduling algorithm was verified and applied in service districts of 5 water plants in Shenzhen.The algorithm has high accuracy,reliability and applicability.In addition,the performance of intelligent scheduling is significantly better than that of manual scheduling,which has reference significance for the research and practice of intelligent water supply scheduling in large and medium sized cities.

关 键 词：供水调度优化 朴素贝叶斯 机器学习 水量预测 宏观水力模型 

分 类 号：TU991[建筑科学—市政工程]