计算机科学
能源管理
初始化
动态规划
强化学习
插件
电源管理
最优控制
荷电状态
人工神经网络
软件部署
控制器(灌溉)
控制工程
数学优化
电池(电)
人工智能
功率(物理)
能量(信号处理)
工程类
算法
程序设计语言
操作系统
物理
统计
生物
量子力学
数学
农学
作者
Chang Liu,Yi Lu Murphey
出处
期刊:IEEE transactions on neural networks and learning systems
[Institute of Electrical and Electronics Engineers]
日期:2020-06-01
卷期号:31 (6): 1942-1954
被引量:57
标识
DOI:10.1109/tnnls.2019.2927531
摘要
Energy optimization for plug-in hybrid electric vehicles (PHEVs) is a challenging problem due to the system complexity and many physical and operational constraints in PHEVs. In this paper, we present a Q-learning-based in-vehicle learning system that is free of physical models and can robustly converge to an optimal energy control solution. The proposed machine learning algorithms combine neuro-dynamic programming (NDP) with future trip information to effectively estimate the expected future energy cost (expected cost-to-go) for a given vehicle state and control actions. The convergences of these learning algorithms were demonstrated on both fixed and randomly selected drive cycles. Based on the characteristics of these learning algorithms, we propose a two-stage deployment solution for PHEV power management applications. Furthermore, we introduce a new initialization strategy, which combines the optimal learning with a properly selected penalty function. This initialization scheme can reduce the learning convergence time by 70%, which is a significant improvement for in-vehicle implementation efficiency. Finally, we develop a neural network (NN) for predicting battery state-of-charge (SoC), rendering the proposed power management controller completely free of physical models.
科研通智能强力驱动
Strongly Powered by AbleSci AI