Comprehensive energy system load prediction method considering multivariate load coupling characteristics

Abstract

The invention discloses a comprehensive energy system load prediction method considering multivariate load coupling characteristics. The method specifically comprises the following steps: 1) preprocessing historical data of a comprehensive energy system; 2) carrying out multivariate load modal decomposition; 3) establishing a multivariate load multi-task learning prediction model; 4) performing multivariate load prediction error compensation; The historical cold, heat and electric load time sequences are decomposed by adopting a self-adaptive local iterative filtering decomposition method, andthe periodic sequence, fluctuation sequence and trend sequence of each load are obtained through reconstruction on the basis, so that the complexity and non-stationarity of the multivariate load timesequence can be reduced, and the model prediction precision is improved on the data level.

Description

technical field [0001] The invention relates to the field of multiple load forecasting of integrated energy systems, in particular to a load forecasting method of an integrated energy system considering the coupling characteristics of multiple loads, and provides a method for multiple load forecasting of an integrated energy system. Background technique [0002] With the increasingly serious global environmental pollution and the rapid maturity of renewable energy power generation technology, the integrated energy system has attracted more and more attention because of its advantages such as energy cascade utilization and efficient consumption of renewable energy. [0003] The integrated energy system refers to the use of advanced physical information technology and innovative management models in a certain area to integrate various energy sources such as coal, oil, natural gas, electric energy, and thermal energy in a certain area to achieve coordinated planning among variou...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the shortcomings of the existing multi-element load forecasting method for integrated energy systems that do not consider the coupling characteristics between different types of loads, and do not perform corresponding error compensation for load forecasting errors. An integrated energy system load forecasting method that considers multiple load coupling characteristics and forecast error compensation based on multiple load coupling characteristics and corresponding forecast error compensation

Images