Design of peer-to-peer energy trading in transactive energy management for charge estimation of lithium-ion battery on hybrid electric vehicles.

• The OML-SOCE is aimed for estimating an accurate capacity of SOC of Li-ion batteries on HEVs. • To develop optimal machine learning based SOC estimation (OML-SOCE) model for HEVs in TEM. • SSAE are optimally adjusted by the use of SSA in such a way that the prediction performance can be considerably improved. Transactive energy is a next big thing in the energy sector which considerably transform the association between utility, consumer, and the environment. Transactive energy management (TEM) system comprises a collection of economical and controlling strategies which helps to dynamically balance the power infrastructure. Peer-to-Peer (P2P) trading becomes familiar, which mainly based on the process of power generation and consumption is completely decentralized. At the same time, Hybrid electric vehicles (HEV) have become an important technology to accomplish energy efficiency and environmental sustainability. Battery Management System (BMS) evaluates the power and State of Charge (SOC), confirms the well-being depending upon the measurement. Accurate SOC estimation is crucial to ensure the unfailing functioning of Li-ion battery that is mainly employed in HEVs. A reliable SOC prediction model is needed to assure the precise measurement of the residual driving range of the vehicle and appropriate battery balancing. In this view, this paper presents an optimal machine learning based SOC estimation (OML-SOCE) model for HEVs in TEM. The OML-SOCE is aimed for estimating an accurate capacity of SOC of Li-ion batteries on HEVs. The OML-SOCE technique involves a two stage process namely stacked sparse autoencoder (SSAE) based prediction and salp swarm algorithm (SSA). At the first stage, SSAE is used for the prediction of SOC. Sparse auto-encoder (AE) is an enhanced AE technique that improves any some sparsity restrictions in the hidden layer of standard AE. A stack of multiple sparse AE forms a deep network framework that is named as SSAE. Next, in the second stage, the parameters involved in the SSAE are optimally adjusted by the use of SSA in such a way that the prediction performance can be considerably improved. A wide range of experiments take place and the results are investigated under varying temperature levels. The experimental outcomes showcased the supremacy of the presented technique the recent techniques with respect to different measures. [ABSTRACT FROM AUTHOR]