專利授權區國立清華大學國際產學營運總中心 Operations Center for Industry Collaboration

搜尋專利授權區

關鍵字

» 新增關鍵字

選單

專利授權區

專利授權區
專利名稱(中)	基於強化學習的充電站能源使用規劃方法及裝置
專利名稱(英)	METHOD AND APPARATUS FOR PLANNING ENERGY USAGE OF CHARGING STATION BASED ON REINFORCEMENT LEARNING
專利家族	中華民國：I767868
專利權人	國立清華大學 100.00%
發明人	江坤諺,邱偉育
技術領域	能源科技,資訊工程,電子電機

專利摘要(中)
一種基於強化學習的充電站能源使用規劃方法。此方法使用充電站自身的電力需求、電池剩餘電量及能源共享區域的全局電力需求與內部電價定義多個系統狀態，並預估在各系統狀態下安排能源使用動作的期望報酬以建構強化學習表；依據強化學習表選擇適於在當前系統狀態下安排的能源使用動作並上傳合作者裝置，根據合作者裝置所安排的交易電量及所計算的採用此能源使用動作的獎勵，以更新強化學習表；以及記錄當前系統狀態、能源使用動作、獎勵及系統狀態的歷經次數以產生模擬環境，計算在各系統狀態下安排電源使用動作的獎勵，據以更新強化學習表。

專利摘要(中)

一種基於強化學習的充電站能源使用規劃方法。此方法使用充電站自身的電力需求、電池剩餘電量及能源共享區域的全局電力需求與內部電價定義多個系統狀態，並預估在各系統狀態下安排能源使用動作的期望報酬以建構強化學習表；依據強化學習表選擇適於在當前系統狀態下安排的能源使用動作並上傳合作者裝置，根據合作者裝置所安排的交易電量及所計算的採用此能源使用動作的獎勵，以更新強化學習表；以及記錄當前系統狀態、能源使用動作、獎勵及系統狀態的歷經次數以產生模擬環境，計算在各系統狀態下安排電源使用動作的獎勵，據以更新強化學習表。

專利摘要(英)
A method and an apparatus for planning energy usage of charging station based on reinforcement learning are provided. In the method, multiple system states are defined by using a power demand and a remaining battery energy of a charging station itself, and a global power demand and an internal power price of an energy sharing area, and expected returns for arranging energy use actions under each system state are estimated to construct a reinforcement learning table. According to the reinforcement learning table, an energy use action adapted for a current system state is selected and uploaded to a coordinator device, and a trading electricity arranged by the coordinator device and a reward of adopting the power use action calculated by the coordinator device are used to update the reinforcement learning table. The current system state, the power use action, the reward and a number of times the system state being selected are recorded and used to generate a simulation environment, so as to calculate an overall benefit of arranging the power use action under each system state and accordingly update the reinforcement learning table.

專利摘要(英)

A method and an apparatus for planning energy usage of charging station based on reinforcement learning are provided. In the method, multiple system states are defined by using a power demand and a remaining battery energy of a charging station itself, and a global power demand and an internal power price of an energy sharing area, and expected returns for arranging energy use actions under each system state are estimated to construct a reinforcement learning table. According to the reinforcement learning table, an energy use action adapted for a current system state is selected and uploaded to a coordinator device, and a trading electricity arranged by the coordinator device and a reward of adopting the power use action calculated by the coordinator device are used to update the reinforcement learning table. The current system state, the power use action, the reward and a number of times the system state being selected are recorded and used to generate a simulation environment, so as to calculate an overall benefit of arranging the power use action under each system state and accordingly update the reinforcement learning table.

聯絡資訊
承辦人姓名	李曉琪
承辦人電話	03-5715131 #31061
承辦人Email	hsiaochi@mx.nthu.edu.tw