Power Restoration System Forecasting Loads

Solution Overview

Problem

Existing power distribution networks face challenges in efficiently restoring power due to changing loads, which often require frequent network reconfigurations and can lead to cascading power failures, as current systems rely on real-time load information for restoration plans rather than forecasted loads.

Innovation Solution

A system and method that identify zones within a power distribution network, predict energy demand, identify alternative power sources, and generate restoration plans by selecting appropriate switches to reroute power, thereby minimizing the need for reconfigurations and reducing the risk of cascading failures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If restoration plans are generated based on current load information, then the restoration can be implemented quickly, but frequent network reconfigurations are required as loads change

Engineering Contradiction:

Improverestoration speedVSAvoidnetwork reconfiguration frequency

Core Design Contradiction:

SpeedVSDevice complexity

Solution Approach 1:

The system performs preliminary action by forecasting future load conditions before generating restoration plans. Load forecasters predict future loads based on historical data and patterns, allowing the restoration plan generator to create plans that accommodate anticipated load changes, thereby reducing the need for frequent reconfigurations while maintaining quick restoration implementation

Inventive Principle:

Principle #10Preliminary action

2Device complexity

If restoration plans are generated based on current load information, then the planning process is simple, but the plans become invalid as loads change within short periods

Engineering Contradiction:

Improveplanning process complexityVSAvoidrestoration plan validity

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The system performs preliminary action by forecasting future load conditions before generating restoration plans. Load forecasters predict future loads based on historical data and patterns, allowing the restoration plan generator to create plans that accommodate anticipated load changes, thereby reducing the need for frequent reconfigurations while maintaining quick restoration implementation

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by continuously monitoring actual load conditions and comparing them with forecasted loads. This feedback loop allows the system to validate restoration plans against real-time conditions and adjust plans as needed, ensuring plan validity despite load variations while maintaining manageable planning complexity

Inventive Principle:

Principle #23Feedback

3Speed

If power is restored without considering forecasted loads, then restoration can be performed quickly, but cascading power failures may occur

Engineering Contradiction:

Improverestoration speedVSAvoidrisk of cascading failures

Core Design Contradiction:

SpeedVSReliability

Solution Approach 1:

The system performs preliminary action by forecasting future load conditions before generating restoration plans. Load forecasters predict future loads based on historical data and patterns, allowing the restoration plan generator to create plans that accommodate anticipated load changes, thereby reducing the need for frequent reconfigurations while maintaining quick restoration implementation

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies preliminary anti-action by proactively identifying and preventing potential cascading failures before they occur. The capacity checker uses forecasted loads to assess whether the network can handle restoration without causing overloads or cascading failures, and the restoration plan generator avoids configurations that could lead to such failures, thus preventing harmful effects before they manifest

Inventive Principle:

Principle #9Preliminary anti-action

Data Source

PatentEP2757648B1Methods and systems for restoring power based on forecasted loads

Publication Date: 2019.10.02 GENERAL ELECTRIC CO

Figure 1
Figure 2
Figure 3

AI summary

A system (400) for use in restoring power to a power distribution network (100) is provided. The system includes a forecast system (415) configured to generate forecast information about the power distribution network, and a fault detection, isolation, and recovery (FDIR) system (405) coupled to the power distribution network is configured to generate fault information about at least one zone (211,212,213,221,222,230) in the power distribution network, receive forecast information from the forecast system, identify at least one alternate source of power (455) for the at least one zone, and generate a restoration plan based on the fault information and the forecast information.