Name
Title | ||
|---|---|---|
Boosting Grid Efficiency And Resiliency By Releasing V2g Potentiality Through A Novel Rolling Prediction-Decision Framework And Deep-Lstm Algorithm |
Abstract | ||
|---|---|---|
The bidirectional link between the power grid and electric vehicles enables the flexible, cheap, and fast-responding application of vehicle batteries to provide services to the grid. However, in order to realize this, a critical issue that should be addressed first is how to predict and utilize vehicle-to-grid (V2G) schedulable capacity accurately and reasonably. This article proposes a novel V2G scheduling approach that considers predicted V2G capacity. First of all, with the concept of dynamic rolling prediction and deep long short term memory (LSTM) algorithm, a novel V2G capacity modeling and prediction method is developed. Then, this article designs a brand-new rolling prediction-decision framework for V2G scheduling to bridge the gap between optimization and forecasting phases, where the predicted information can be more reasonably and adequately utilized. The proposed methodologies are verified by numerical analysis, which illustrates that the efficiency and resiliency of the grid can be significantly enhanced with V2G services managed by the proposed methods. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/JSYST.2020.3001630 | IEEE SYSTEMS JOURNAL |
Keywords | DocType | Volume |
Vehicle-to-grid, Prediction algorithms, Predictive models, Heuristic algorithms, Resilience, Scheduling, Deep learning and vehicle to grid (V2G) schedulable capacity, electric vehicle (EV), long-short-term memory, rolling prediction and decision, V2G | Journal | 15 |
Issue | ISSN | Citations |
2 | 1932-8184 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shuangqi Li | 1 | 0 | 2.03 |
| Chenghong Gu | 2 | 4 | 7.82 |
| Jianwei Li | 3 | 2 | 4.11 |
| Hanxiao Wang | 4 | 0 | 0.34 |
| Qingqing Yang | 5 | 0 | 0.68 |