Conditional generative adversarial network-based short-term wind power prediction method

• Main Authors: WANG WENNA, CAI DEFU, LIU HAIGUANG, YANG XUAN, ZHOU YUE, ZHANG LIANGYI, SUN GUANQUN, LEE DAE-HO, CHEN RUSI, ZHOU KUNPENG, WANG ERXI
• Format: Patent
• Language: Chinese; English
• Published: 25.07.2023
• Subjects: CALCULATING; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTINGELECTRIC POWER; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRICITY; GENERATION; PHYSICS; SYSTEMS FOR STORING ELECTRIC ENERGY; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention relates to a short-term wind power prediction method based on a generative adversarial network, and the method comprises the steps: extracting a meteorological variable fluctuation time sequence and a historical wind power time sequence from a short-term meteorological scale, generating a feature matrix as condition data, and building a short-term wind power prediction model based on a CNN-LSTM-CGAN improved condition generative adversarial network; inputting the condition data and the random noise data into a generator together to obtain generated prediction data; inputting the generated prediction data and condition data into a discriminator together, and discriminating with real power data; introducing a feature loss function, measuring the feature value deviation between the generated prediction data and the real data, and updating and optimizing the network parameter weight; if the maximum number of iterations is reached, iteration is terminated, and network parameters are output; and perfo