Power transaction data prediction and verification method and system based on DFT-KNNI-KMEANS algorithm

• Main Authors: LIU XUWEN, FAN JIE, GAO BO, WANG LINJIE, FENG YINGCHUN, CHEN CHENG
• Format: Patent
• Language: Chinese; English
• Published: 21.03.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a power transaction data prediction and verification method and system based on a DFT-KNNI-KMEANS algorithm, and the method comprises the steps: extracting the historical transaction data of a power market, and constructing a power transaction data set; performing power transaction data fitting prediction by adopting a linear fitting method and a KNNI nearest neighbor method to obtain a linear verification value and a KNNI verification value; according to the linear fitting method, a least square method is combined with Fourier transform to obtain a linear check value; performing linear weighting on the linear check value and the KNNI check value according to the size of the check range to obtain a check data feature set; and the obtained verification data feature set is verified based on an improved K-MEANS clustering algorithm. Accurate prediction and verification of power transaction data can be realized. 基于DFT-KNNI-KMEANS算法的电力交易数据预测与校验方法和系统，所述方法包括：抽取电力市场历史交易数据，构建电力交易数据集；分别采用线性拟合方法和