基于自适应谐振网络的电力需求侧设备辨识方法和系统

• Format: Patent
• Language: Chinese
• Published: 03.11.2020
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

本发明公开了基于自适应谐振网络的电力需求侧设备辨识方法和系统，通过采集电力需求侧未知设备多维特征数据，并根据事件检测算法提取未知设备负荷事件，利用未知设备负荷事件得到未知设备启停时间、各特征暂态变化量和稳态运行特征数据；将所述特征数据进行分类得到输入数据和测试数据，将输入数据和测试数据进行归一化和编码处理；通过自适应谐振网络对输入数据进行训练学习，得到自适应谐振网络训练模型；根据自适应谐振网络训练模型对测试数据进行辨识，得到辨识结果；根据预存数据库对所述辨识结果进行匹配，得到未知设备匹配结果。本发明的自适应谐振网络既能使用标准数据训练，进行监督学习，又能对无标记数据进行分类，识别未知设备。 The invention discloses a power demand side device identification method and system based on an adaptive resonance network. The method comprises the following steps of acquiring the multi-dimensionalfeature data of a power demand side unknown device, extracting the load events of the unknown device according to an event detection algorithm, and obtaining the start-stop time, the feature transientvariations and the steady-state operation feature data of the unknown device by utilizing the load events of the unknown device; classifying the feature data to obtain the input data and the test data, and normalizing and encoding the input data and the test data; training and learning the input data through the adaptive res