An air conditioner cold storage power intelligent scheduling method for virtual power grid transaction
CN120931018BActive Publication Date: 2026-05-29GUANGZHOU HAOMING DIGITAL TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGZHOU HAOMING DIGITAL TECH CO LTD
- Filing Date
- 2025-08-07
- Publication Date
- 2026-05-29
AI Technical Summary
Technical Problem
Existing technologies cannot efficiently allocate electricity for cold storage and trading, resulting in low power dispatch efficiency.
Method used
By periodically acquiring and preprocessing data, an environmental model is constructed, and a deep reinforcement learning agent is used to output the scheduling ratio. The scheduling state is adjusted in combination with the cold storage characterization value and the power curve, thereby optimizing the cold release rate and cooling power of the cold storage equipment to achieve rational power scheduling.
Benefits of technology
It has improved the efficiency and accuracy of power dispatch, reduced energy consumption, optimized the utilization of power resources, and enhanced the flexibility and stability of the power system.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN120931018B_ABST
Abstract
The present application relates to the technical field of power dispatch, and particularly relates to an air conditioner cold storage power intelligent dispatching method for virtual power grid transaction. The present application can make the data information realize time synchronization by preprocessing the periodically obtained data information, so that the obtained data is more effective; and completes environment modeling based on the preprocessed data information, so that the state change is more accurately represented based on the periodically updated data information using the environment modeling, so that the dispatching proportion output after the environment modeling is input into the deep reinforcement learning intelligent agent is more accurate; determines the power dispatching state based on the cold storage representation value, and adjusts the related parameters based on the dispatching state, so that the dispatching of the power for cold storage and transaction is more effective. The present application solves the problem that the power for cold storage and transaction cannot be reasonably dispatched in the prior art, so that the power dispatching efficiency is low.
Need to check novelty before this filing date? Find Prior Art