Ultra-short-term multi-node load forecasting – a composite approach

Abstract

In the electric power system, grasping active and reactive load variation regularity of each node is a key problem for optimal dispatch, preventive control, security assessment and transmission capacity evaluation. This study presents a novel composite approach of ultra-short-term forecasting for multi-node active and reactive load. It proposes a hierarchy and sub-area idea to construct a framework of self-adapting dynamic load models. With load forecasting at the top layer implemented by the recursive least square support vector machines (RLS-SVM) algorithm, discrete state-space equations are established to describe the dynamic characteristics of the multi-node active load distribution factors and power factors, and then the Takagi–Sugeno (TS) fuzzy control technique is introduced to realise feedback compensation. The application of the proposed technique in the actual power system control centre of Shandong Province is verified and satisfactory results are found.