Water supply pump station scheduling method based on deep neural network

• Main Authors: YAN HEXIANG, CHEN LEI, XIN KUNLUN, WANG JIAYING, TAO TAO, PU ZHENGHENG, LI SHUPING
• Format: Patent
• Language: Chinese; English
• Published: 23.11.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention provides a water supply pump station scheduling method based on a deep neural network, and the method is characterized in that the method comprises the following steps: determining the input characteristics of the deep neural network, determining a pump station scheduling instruction sending time interval, and building a deep neural network PumpNet; obtaining historical monitoring data and historical pump station dispatching instructions of the water supply system corresponding to deep neural network input features, and training a deep neural network PumpNet; collecting real-time monitoring data of a water supply system corresponding to input characteristics of the deep neural network PumpNet, and inputting the real-time monitoring data into the trained deep neural network for prediction; and outputting a pump station real-time scheduling instruction. According to the method provided by the invention, the time and space characteristics of the monitoring data of the water supply system can be aut