Medium-Term Load Forecasting Using Support Vector Regression, Feature Selection, and Symbiotic Organism Search Optimization

TL;DR

This paper presents a hybrid approach combining Support Vector Regression, feature selection, and Symbiotic Organism Search Optimization to improve medium-term load forecasting accuracy in power systems, tested on the EUNITE dataset.

Contribution

It introduces a novel hybrid model integrating SVR, SOSO, and feature selection for enhanced medium-term load forecasting accuracy.

Findings

The proposed method outperforms several previous models on the EUNITE dataset.

Feature selection improves model efficiency and accuracy.

SOSO effectively optimizes SVR parameters for better forecasting.

Abstract

An accurate load forecasting has always been one of the main indispensable parts in the operation and planning of power systems. Among different time horizons of forecasting, while short-term load forecasting (STLF) and long-term load forecasting (LTLF) have respectively got benefits of accurate predictors and probabilistic forecasting, medium-term load forecasting (MTLF) demands more attention due to its vital role in power system operation and planning such as optimal scheduling of generation units, robust planning program for customer service, and economic supply. In this study, a hybrid method, composed of Support Vector Regression (SVR) and Symbiotic Organism Search Optimization (SOSO) method, is proposed for MTLF. In the proposed forecasting model, SVR is the main part of the forecasting algorithm while SOSO is embedded into it to optimize the parameters of SVR. In addition, a minimum redundancy-maximum relevance feature selection algorithm is used to in the preprocessing of input data. The proposed method is tested on EUNITE competition dataset to demonstrate its proper performance. Furthermore, it is compared with some previous works to show eligibility of our method.