Battery Energy Forecasting in Electric Vehicle Using Deep Residual Neural Network

Abstract

In the recent decade, it is possible to use electric vehicles in a safe, cost-effective, and environmentally friendly manner, but only if accurate and trustworthy state parameter predictions are produced prior to their disposal. The state of health (SOH) of the lithium-ion batteries (LIBs) must be precisely forecasted in order to ensure that the LIB can operate safely. The inability of physical SOH estimators to cope with the dynamic character of SOH when operating in a highly nonlinear environment is a common limitation when operating in nonlinear environments. Traditional SOH estimation techniques have demonstrated that they have limits that can be overcome by data-driven methods. TCN, a new machine learning technique, combines the advantages of residual neural networks (ResNet) with the computing efficiency of neural networks to produce a technique that is both efficient and effective. The results of rgw simulation show that the proposed method has reduced placement cost, and also a TCN can accurately estimate the SOH of a LIB with an MSE error of less than 1% over the LIB lifetime. The performance of an electric car battery, which are numerous and diverse, can be anticipated more precisely using this approach.

Analysis on flexibility resources of Western Inner Mongolia power grid

“…; 2) interruptible/adjustable loads on the load side, such as air conditioning, electric vehicle [2], etc. ; 3) energy storage equipment such as battery management systems [3]; 4) ramping equipment on the grid side such as interconnection lines, distribution transformer [4], etc. The above research mostly starts from ideal conditions, and rarely involves the actual situation of flexibility in Inner Mongolia region.…”