Risk-Aware Energy Scheduling for Edge Computing with Microgrid: A Multi-Agent Deep Reinforcement Learning Approach.
Md. Shirajum MunirSarder Fakhrul AbedinNguyen H. TranZhu HanEui-Nam HuhChoong Seon HongPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- multi agent
- cooperative
- function approximation
- scheduling problem
- risk management
- resource allocation
- multi agent environments
- single agent
- optimal policy
- force field
- resource constraints
- model free
- risk assessment
- machine learning
- learning agents
- energy consumption
- dynamic programming
- multi agent systems
- edge information
- multi agent reinforcement learning
- traffic signal control
- risk factors
- multiagent systems
- decision making
- learning algorithm
- parallel machines
- multiple agents
- undirected graph
- reinforcement learning algorithms
- coalition formation
- energy minimization
- flexible manufacturing systems
- multiscale
- multiagent reinforcement learning