Fault scheduling method and device for power distribution network, medium and equipment

By combining deep reinforcement learning models and pre-set fault location models, the problem of difficult fault location in 10kV distribution network lines was solved, achieving fast and accurate fault location and reducing the time and resource waste of manual line inspection.

CN117422218BActive Publication Date: 2026-07-21STATE GRID HEBEI ELECTRIC POWER CO LTD BAODING POWER SUPPLY BRANCH CO +3
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
STATE GRID HEBEI ELECTRIC POWER CO LTD BAODING POWER SUPPLY BRANCH CO
Filing Date
2023-09-11
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

In existing technologies, fault location in 10kV distribution network lines is difficult, especially the identification and selection of low-current grounding faults. This leads to prolonged fault repair time due to manual line inspection and circuit pulling methods, increased power outage losses on normal lines, and wasted manpower and resources.

Method used

By combining a deep reinforcement learning model with a pre-set fault location model, the fault location results are constructed by preprocessing the fault data to be detected in the distribution network, calculating the time difference using a two-end traveling wave ranging algorithm, and optimizing the fault location strategy through a deep reinforcement learning model to achieve accurate location.

Benefits of technology

It improves the accuracy and efficiency of fault location, reduces the time spent on manual line inspection, reduces losses from power outages on normal lines, and saves manpower and resources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117422218B_ABST
    Figure CN117422218B_ABST
Patent Text Reader

Abstract

The application provides a power distribution network fault scheduling method and device, medium and equipment. The method comprises the following steps: obtaining to-be-detected fault data of a power distribution network, preprocessing the to-be-detected fault data to obtain preprocessed to-be-detected fault data, obtaining a fault positioning result corresponding to the to-be-detected fault data according to the preprocessed to-be-detected fault data and a preset fault positioning model, obtaining a target fault positioning strategy according to the fault positioning result and a deep reinforcement learning model, and scheduling the power distribution network according to the target fault positioning strategy. The preprocessed to-be-detected fault data is input into the preset fault positioning model to determine the fault positioning result, and then the fault positioning result is input into the deep reinforcement learning model to obtain the target fault positioning strategy, so that the power distribution network can be scheduled in a timely manner.
Need to check novelty before this filing date? Find Prior Art