充电桩群动态功率分配方法及系统

By constructing a unified data benchmark and capability mask fusion mechanism, combined with multi-level cyclic balance control and a hybrid gradient enhancement proxy model, the problem of insufficient information fusion in the power allocation of charging pile groups is solved, achieving efficient and safe power quality assurance and equipment longevity.

CN122402297APending Publication Date: 2026-07-17STATE GRID ZHEJIANG ELECTRIC POWER CO LTD NINGBO ZHENHAI DISTRICT POWER SUPPLY CO

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
STATE GRID ZHEJIANG ELECTRIC POWER CO LTD NINGBO ZHENHAI DISTRICT POWER SUPPLY CO
Filing Date
2026-06-18
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

The existing power allocation methods for charging pile clusters fail to effectively integrate multi-dimensional operational information, ignore vehicle-to-grid interaction capabilities, and lack closed-loop safety verification, resulting in power quality risks and insufficient equipment lifespan.

Method used

By constructing a unified data benchmark and capability mask fusion mechanism, utilizing critical operating condition index mapping and group dynamic adjustment, and combining multi-level cyclic balance control and hybrid gradient enhancement proxy model, refined dynamic power allocation of charging pile groups can be achieved.

Benefits of technology

It improves transformer capacity utilization, eliminates V2G reverse feedback, reduces three-phase imbalance, lowers temperature rise and protection coordination mismatch risk, and ensures charging safety and equipment longevity.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122402297A_ABST
    Figure CN122402297A_ABST
Patent Text Reader

Abstract

本发明属于电动汽车充电管理与功率调度技术领域,具体涉及一种充电桩群动态功率分配方法及系统。方法包括:通过采集各充电桩多源传感器数据生成标准化输入特征张量和能力掩码张量,并离线建立从总功率限额到变动充电桩集合的索引映射表,在线运行时利用该映射表锁定变动充电桩并划分为正向调节组、负向调节组和可逆调节组完成粗分配,通过多层级循环平衡控制修正各桩功率指令以消除变压器过载和三相不平衡,进而采用混合梯度增强代理模型和多目标进化算法搜索帕累托最优功率配置,并由充电站机理仿真模型进行暂态验证与闭环优化,实现了安全、高效、延长设备寿命且充分利用双向充放电能力的充电桩群精细化动态功率分配。
Need to check novelty before this filing date? Find Prior Art