Voltage Grid State Prediction Using AI Time-Series Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing volatility of voltage grids due to fluctuating energy demand and irregular renewable energy feed-in leads to decreased grid quality, resulting in potential disruptions and outages.
Innovation Solution
A method involving the acquisition of at least one characteristic parameter of the voltage grid at multiple points in time, processed by a processor unit, including artificial intelligence, to predict future grid states, allowing for early identification and mitigation of potential disruptions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If only instantaneous grid quality analysis is performed, then the monitoring system remains simple and cost-effective, but it cannot predict future disruptions in volatile voltage grids
Solution Approach 1:
The system performs preliminary actions by acquiring and storing characteristic parameters at multiple past points in time before disruptions occur. This historical data collection enables future state prediction through AI processing, allowing the system to anticipate disruptions before they happen rather than merely reacting to current conditions.
Solution Approach 2:
An artificial intelligence processor unit is introduced as an intermediary between the acquired voltage grid parameters and the prediction output. This AI intermediary processes the temporal patterns in the characteristic parameters to generate future state predictions, bridging the gap between simple data collection and complex prediction capabilities.
2Loss of time
If characteristic parameters are acquired at multiple points in time for prediction, then future disruptions can be anticipated, but data processing requirements and system complexity increase
Solution Approach 1:
The system applies partial action by selectively processing only the necessary characteristic parameters that are most indicative of future grid state. Rather than analyzing all possible voltage grid parameters, the system focuses on acquiring and processing key parameters at multiple time points, reducing unnecessary computational energy consumption while maintaining prediction effectiveness.
3Measurement precision
If AI processing is used to predict future grid states, then disruption prediction accuracy improves, but computational resources and processing time increase
Solution Approach 1:
The characteristic parameters are acquired and stored at multiple predetermined points in time before prediction is needed. This preliminary data collection allows the AI processor to work with pre-organized historical data, improving prediction accuracy while reducing the computational burden during actual prediction operations.
Data Source
AI summary
A method of monitoring a voltage grid (12) is described, in which at least a first characteristic parameter is acquired at a first point in time and the first characteristic parameter u of the voltage grid (12) is acquired at a second point in time. The first characteristic parameter acquired at the first point in time and the first characteristic parameter acquired at the second point in time are fed into a processor unit (16) which processes the first characteristic parameter acquired at the two points in time together such that a future state of the voltage grid (12) is predicted on the basis of the first characteristic parameter acquired at the at least two different points in time. The predicted future state of the voltage grid (12) is output. In addition, there are described a method of training an artificial intelligence (24), a system (10), a computer program (18), and a computer-readable data carrier (20).