Abstract
This paper studies energy management in a smart grid-powered cellular network consisting of an independent system operator (ISO) and multiple geographically distributed aggregators. The aggregators have energy storage devices and can purchase energy from the electric grid via the ISO to serve their users. To account for the uncertainty of the renewable energy supply as well as the impacts of multiple aggregators on the electric grid and energy prices, a foresighted strategy combined with the adaptive \epsilon-greedy method is developed for the aggregators to distributively and adaptively minimize the long-term overall cost of the system, based on the ahead-of-time decision making of the storage pre-charging amount. Simulation results validate that the proposed strategy surpasses a recent learning-based storage management design and a myopic design.
Original language | English |
---|---|
Article number | 8643542 |
Pages (from-to) | 4064-4068 |
Number of pages | 5 |
Journal | IEEE Transactions on Vehicular Technology |
Volume | 68 |
Issue number | 4 |
Early online date | 18 Feb 2019 |
DOIs | |
Publication status | Published - 1 Apr 2019 |
Keywords
- Distributed management
- energy management
- online learning