ML based framework for optimal distributed generation management including EV loading

Abstract

The load profile of radial distribution networks (RDN) gets significantly impacted when plug- in electric vehicles (PEVs) are connected to it in large numbers. The disturbances in the load profile may lead to increased power losses in distribution lines, and deterioration of network voltage profile. Provision of distributed generation (DG) at strategic locations in the distribution network can help to compensate the impact on the electrical network due to PEVs loads. This paper proposes the use of Machine Learning (ML) based models for determining the optimal location of distributed generators (DGs) in RDN. The proposed method considered time-varying load in addition to PEVs load. The suggested method determines optimal DGs placement based on Power loss reduction index (PLRI), and Voltage deviation index reduction index (VDIRI). Four distinct types of ML models were used in the proposed approach using synthesized data on IEEE 33-bus RDN. The performance of the ML models were evaluated with respect to mean squared error (MSE) and mean absolute percentage error (MAPE) and, for the ML models considered, Random Forest ML model gave the best performance.