PMU-Based Voltage Violation Prediction in Active Distribution Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional voltage control schemes in power grids are ineffective in managing voltage imbalances caused by distributed energy sources like solar power generators, particularly due to fluctuations in solar output and bidirectional power flow, which can lead to voltage limit violations.
Innovation Solution
A neural network is trained using the Levenberg-Marquardt backpropagation algorithm to predict voltage fluctuations and adjust transformer tap positions or inject reactive power to maintain voltage levels, leveraging phasor measurement units (PMUs) for real-time data and controlling distributed energy sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional voltage control schemes are used, then system simplicity is maintained, but voltage limit violations occur due to distributed energy source fluctuations
Solution Approach 1:
The neural network predicts voltage fluctuations before they occur by analyzing historical and real-time data from PMUs. This preliminary prediction enables proactive adjustment of transformer tap positions and reactive power injection, preventing voltage limit violations before they happen rather than reacting after violations occur.
Solution Approach 2:
The system continuously monitors voltage levels, power production, and demand through PMUs, feeding this real-time data back to the neural network. The network uses this feedback to update predictions and adjust control actions dynamically, creating a closed-loop control system that adapts to changing grid conditions.
2Reliability
If real-time voltage monitoring and prediction is implemented, then voltage constraint violations are prevented, but system complexity and computational requirements increase
Solution Approach 1:
The neural network serves multiple functions simultaneously: it predicts voltage fluctuations, identifies potential constraint violations, determines optimal control actions, and coordinates multiple distributed energy sources. This multi-functionality consolidates what would otherwise require separate systems into a single integrated solution.
Solution Approach 2:
The system uses readily available data from existing PMUs and grid infrastructure to train and operate the neural network. It leverages historical data already present in the system and automatically adjusts control parameters without requiring external intervention or additional complex monitoring equipment.
3Productivity
If distributed energy sources are integrated into the power grid, then renewable energy utilization increases, but voltage imbalances and limit violations occur
Solution Approach 1:
The system dynamically adjusts the operational parameters of distributed energy sources based on real-time grid conditions. The neural network continuously optimizes power injection levels and reactive power output of PV systems, allowing maximum renewable utilization while adapting to changing load demands and preventing voltage instability.
Solution Approach 2:
The neural network modifies operational parameters of distributed energy sources, including active power injection, reactive power output, and transformer tap positions. By dynamically changing these parameters based on predicted voltage fluctuations, the system maintains voltage stability while maximizing renewable energy integration.
Data Source
AI summary
Intelligent voltage limit violation prediction and mitigation for active distribution networks may be provided by: measuring, at one or more of a plurality of phasor measurement units (PMUs) connected between a power grid and associated loads, a present power produced by photovoltaic systems deployed downstream from the one or more of the plurality of PMUs; measuring, at the one or more of the plurality of PMUs, a present demand for power from the associated loads; generating a power production prediction by the photovoltaic systems for an upcoming time period; generating a demand prediction for power from the loads for the upcoming time period; and taking a mitigation action based on the power production prediction and the demand prediction indicating a predicted voltage constraint violation in the upcoming time period.