Deep Deterministic Policy Gradient-DRL Enabled Multiphysics-Constrained Fast Charging of Lithium-Ion Battery

Abstract

Fast charging is an enabling technique for the large-scale penetration of electric vehicles. This paper proposes a knowledge-based, multi-physics-constrained fast charging strategy for lithium-ion battery (LIB), with a consciousness of the thermal safety and degradation. A universal algorithmic framework combining model-based state observer and a deep reinforcement learning (DRL)based optimizer is proposed, for the first time, to provide a LIB fast charging solution. Within the DRL framework, a multi-objective optimization problem is formulated by penalizing the over-temperature and degradation. An improved environmental perceptive deep deterministic policy gradient (DDPG) algorithm with priority experience replay is exploited to trade-off smartly the charging rapidity and the compliance of physical constraints. The proposed DDPG-DRL strategy is compared experimentally with the rule-based strategies and the state-of-the-art model predictive controller to validate its superiority in terms of charging rapidity, enforcement of LIB thermal safety and life extension, as well as the computational tractability.

A Novel Energy-Safe Algorithm for Enhancing the Battery Life for IoT Sensors’ Applications

“…As for PAN 2, it represents the node's main parent (4, 5, 6, and 7) and makes up subgroup 2. Subgroup 3 is composed of PAN 3 and four relevant children (8,9,10,11). Regarding subgroup 4, it includes PAN 4 combined with the nodes 12, 13, 14, and 15.…”

“…It seems that an electric vehicle field, the battery state of charge, state of life, and protection are the most important factors that must be supervised and controlled. Different recharging techniques appear in the literature, such as in [8], which uses the deep learning technology for improving the recharge method of the main energy source. In addition, managing the energy coming from the battery for feeding the other equipment seems to help with increasing the battery performance.…”

Wireless Power Transfer Using Double DD Coils

“…Maximum wireless charger power is limited by physical constraints of the lithium battery, such as the battery over-voltage and over-temperature. Battery modeling, observation, and the use of models in fast-charging algorithms are presented in [10,11]. The coupling coefficient is dependent on the distance and horizontal misalignment between the transmitter and receiver coils.…”

Co-Optimizing Battery Storage for Energy Arbitrage and Frequency Regulation in Real-Time Markets Using Deep Reinforcement Learning

“…An expert-assistance deep deterministic policy gradient (DDPG) strategy was introduced to minimize the energy consumption and optimize the power allocation of the hybrid electric buses [31]. A multiphysics-constrained fast-charging strategy was proposed for lithium-ion batteries in [32] based on an environmental perceptive DDPG. However, DDPG is not effective in avoiding overestimation in the actor-critic setting [33,34].…”