Naive Bayes Grid State Estimation for Power Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting the state of power distribution grids, especially at the low-voltage level, face challenges due to the increasing complexity and variability from distributed renewable energy sources, leading to inaccuracies and the need for extensive measurement infrastructure, which is costly and time-consuming.
Innovation Solution
The implementation of a naive Bayes method for state estimation in power distribution grids, utilizing historical and real-time data from various sources, including weather and market data, to accurately predict voltage and phase angles across network sections, with error correction mechanisms to improve prediction accuracy and reduce the need for extensive measurement points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional SCADA systems with extensive measurement infrastructure are used, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent introduces a state estimation device as an intermediary computational layer that processes data from existing measurements and predictions to infer grid state. This mediator enables accurate grid state estimation without requiring direct measurements at every location, thus reducing measurement infrastructure complexity while maintaining prediction accuracy
Solution Approach 2:
The patent replaces physical measurement infrastructure (sensors, meters) with a computational system using naive Bayes algorithms. Instead of installing extensive physical measurement devices across the grid, the system uses data processing and probabilistic modeling to estimate grid state, substituting mechanical/physical systems with information-processing systems
2Measurement precision
If more measurement points are installed to improve prediction accuracy, then measurement precision is improved, but loss of time and cost increase
Solution Approach 1:
The state estimation device acts as a computational intermediary that synthesizes information from limited measurements and predictions to infer complete grid state. This approach achieves accurate predictions without the time-consuming deployment of extensive measurement infrastructure across all grid locations
3Adaptability or versatility
If distributed renewable energy sources are integrated, then adaptability is improved, but measurement precision deteriorates due to increased variability
Solution Approach 1:
The system performs preliminary actions by collecting predictions from multiple sources (weather forecasts, market data, historical patterns) before the actual grid state occurs. This advance data gathering and probabilistic modeling prepares the state estimation device to handle the variability introduced by distributed renewable energy sources, maintaining prediction accuracy despite increased system adaptability
Solution Approach 2:
The naive Bayes state estimation system incorporates feedback loops that continuously update probability distributions based on new measurements and predictions. This feedback mechanism allows the system to adapt to the variability introduced by distributed renewable energy sources while maintaining measurement precision through continuous refinement of grid state estimates
Data Source
AI summary
A method estimates a grid state of an electrical power distribution grid having a multiplicity of network sections, in which a central computer arrangement is used to receive measured values from measuring devices. A state estimation device is used to make a prediction of a future grid state, wherein a voltage and a phase angle are respectively ascertained for each network section, and in that a naive Bayes method is used for the prediction.