Charging station operation and maintenance path planning method combining heuristic algorithm based on divide-and-conquer thought with reinforcement learning
The invention provides a charging station operation and maintenance path planning method based on the combination of a heuristic algorithm of a divide-and-conquer idea and reinforcement learning, and the method mainly comprises the following steps: collecting the longitudes and latitudes of all oper...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention provides a charging station operation and maintenance path planning method based on the combination of a heuristic algorithm of a divide-and-conquer idea and reinforcement learning, and the method mainly comprises the following steps: collecting the longitudes and latitudes of all operation and maintenance target charging stations, and initializing a grid map; the operation and maintenance sites are divided according to the administrative regions to which the operation and maintenance sites belong by adopting the idea of division and treatment; a heuristic path optimization algorithm is selected to plan paths between the regions; a reinforcement learning Q-learning algorithm is adopted to carry out path planning on the maintenance stations in all the areas; the path plans of the maintenance stations in all the areas are combined according to the shortest path traversal sequence among the areas, and then a heuristic path optimization algorithm is adopted for local adjustment and optimization; and |
---|