Distribution Transformer Load Prediction via Data Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current load forecasting methods for distribution transformers are inadequate for handling large volumes of data and varied loading patterns, particularly in providing pre-warnings for heavy loads and overloads, which can lead to equipment damage and power outages in areas with rapid economic growth.
Innovation Solution
A method, device, and system that select and convert data from multiple sources into a unified format, filter and transform it into predictor variables, and use a model trained on a subset of these variables to forecast heavy loads or overloads, providing pre-warnings for distribution transformers through a user interface or system alerts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional load forecasting methods are used, then the system is simple to implement, but it cannot handle large volumes of data and varied loading patterns effectively
Solution Approach 1:
The patent segments the forecasting system into multiple components: data collection module, data preprocessing module, model training module, and prediction module. Each component handles specific tasks independently, enabling the system to process large volumes of diverse data effectively while maintaining manageable complexity through modular architecture.
Solution Approach 2:
The system dynamically adapts to different loading patterns by using historical data from multiple sources and adjusting prediction models based on varying conditions. The forecasting approach changes dynamically according to the specific characteristics of each distribution transformer and time period, enhancing versatility without requiring a completely different system for each scenario.
2Measurement precision
If comprehensive data from multiple sources is collected, then prediction accuracy improves, but data processing time and computational resources increase
Solution Approach 1:
The system performs preliminary data preprocessing and cleaning before actual forecasting, organizing data from multiple sources into standardized formats in advance. Historical data is pre-processed and stored in optimized structures, reducing the computational burden during real-time prediction and minimizing processing time while maintaining comprehensive data utilization.
Solution Approach 2:
The patent applies different processing strategies to different data types and time periods based on their specific characteristics. Not all data undergoes the same level of processing - critical data receives more intensive preprocessing while less critical data uses streamlined processing, optimizing the balance between accuracy and processing time through localized quality adjustments.
Data Source
AI summary
A system can generate a heavy load pre-warning or an overload pre-warning for distribution transformers. Operation of the system can include selecting data records received from a plurality of data sources; converting the data records in the plurality of different data formats; filtering the data records in the database by using a predetermined threshold and matching each of the filtered data records with one of a plurality of distribution transformers; transforming the matched data records to a plurality of predefined predictor variables; selecting a subset of the plurality of predefined predictor variables; training, testing and tuning a model and forecasting at least one of heavy load or overload for each of the plurality of distribution transformers in a predetermined region.