Electric power spot market equal quotation collusion unit identification method

• Main Authors: LIU SIJIE, ZHAO YUE, GAO HAIXIANG, BAI YANG, LIN SHAOHUA, CAI QIUNA, GONG CHAO
• Format: Patent
• Language: Chinese; English
• Published: 18.05.2021
• 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; 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

The invention relates to an electric power spot market equal quotation collusion unit identification method, which is based on an Adaboost-BP algorithm and specifically comprises a data acquisition step, a data preprocessing step, an equal-quoted-price collusion unit feature extraction step and a model establishment step, and is characterized in that equal-quoted-price collusion units are analyzed, the equal-quoted-price collusion unit features are extracted, quantitative processing by using spot market data is carried out; an overall framework of the model is constructed through the Adaboost algorithm, so that the recognition accuracy of the recognition model is improved; a basic classification model is constructed through a BP neural network algorithm, and units with medium quotation collusion in the spot market are identified. Compared with the prior art, the method has the advantages of high accuracy, high reliability and the like of identifying the equal quotation collusion unit. 本发明涉及一种电力现货市场等报价串谋机组识别方法