Summary of A Deep Reinforcement Learning-based Charging Scheduling Approach with Augmented Lagrangian For Electric Vehicle, by Guibin. Chen and Xiaoying. Shi
A Deep Reinforcement Learning-Based Charging Scheduling Approach with Augmented Lagrangian for Electric Vehicle
by Guibin. Chen, Xiaoying. Shi
First submitted to arxiv on: 20 Sep 2022
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper tackles the challenge of optimizing electric vehicle charging schedules when participating in demand response. The uncertainty surrounding remaining energy, arrival/departure times, and future electricity prices makes it difficult to make cost-effective charging decisions while maintaining a specific battery state-of-charge. To address this issue, the authors formulate the problem as a constrained Markov decision process (CMDP) and propose a novel safe off-policy reinforcement learning approach that combines the augmented Lagrangian method and soft actor critic algorithm. The proposed algorithm uses an actor network updated through policy gradients with a Lagrangian value function and a double-critics network to estimate action-value functions, allowing it to avoid overestimation bias and achieve high solution optimality while complying with constraints. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper solves the problem of optimizing electric vehicle charging schedules by combining the augmented Lagrangian method and soft actor critic algorithm. This approach handles uncertainty in remaining energy, arrival/departure times, and electricity prices. The result is a novel safe off-policy reinforcement learning algorithm that can achieve high solution optimality while complying with constraints. |
Keywords
» Artificial intelligence » Reinforcement learning
