Abstract | ||
---|---|---|
Abstract One of the goals of Smart Grids is to encourage distributed generation of energy in houses, hence allowing the user to profit by injecting energy into the power grid. The implementation of a differentiated tariff of energy per time of use, coupled with energy storage in batteries, enables profit maximization by the user, who can choose to sell or store the energy generated whenever it is convenient. This paper proposes a solution to the sequential decision-making problem of energy sale by applying reinforcement learning. Results show a significant increase in the total long-term profit by using the policy obtained with the proposed approach, when compared with a price-unaware selling policy. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/s10846-014-0169-8 | Journal of Intelligent and Robotic Systems |
Keywords | Field | DocType |
SmartHome,SmartGrid,Energy management system,Reinforcement learning | Energy storage,Energy management,Smart grid,Simulation,Operations research,Home automation,Control engineering,Energy management system,Distributed generation,Engineering,Profit maximization,Reinforcement learning | Journal |
Volume | Issue | ISSN |
80 | Supplement 1 | 1573-0409 |
Citations | PageRank | References |
1 | 0.37 | 8 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Heider Berlink | 1 | 1 | 0.37 |
Nelson Kagan | 2 | 15 | 3.47 |
Anna Helena Reali Costa | 3 | 192 | 31.97 |