Review on Artificial Intelligence Based Load Forecasting Research for the New-type Power System

Driven by the goal of ‘double carbon’, constructing the new-type power system with new energy as the main part is the important premise and inevitable trend to promote the low carbon transformation and development of the modern power system. As the complex and variable multi-load is an important part of the new-type power system, load forecasting is of great significance for the planning, operation, control, and dispatching of the new-type power system. In this context, this paper firstly gives a brief overview of power system load forecasting. Secondly, in view of the new characteristics and challenges of load forecasting for the new-type power system, the status quo of applications of data driven artificial intelligence technologies in various load forecasting scenarios is described in detail. Then, from the perspectives of data and models, the problems and shortcomings of current artificial intelligence based load forecasting methods are deeply analyzed. Finally, in view of the challenges of artificial intelligence based load forecasting technologies for the new-type power system, the key technology research directions in the future are prospected, and the relevant key research scenarios are summarized, in order to provide the constructive reference for the development of the new-type power system under the goal of ‘double carbon’. ©2023 Chin.Soc.for Elec.Eng.