Iterative Energy Load Forecasting via Dynamic Factor Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current energy load forecasting methods for utility industries face challenges in accurately prioritizing and weighting contextual influencing factors across different grid hierarchy elements and time scale periods, leading to inconsistencies in energy grid infrastructure management.
Innovation Solution
A method and system that utilize a processor to identify and prioritize contextual influencing factors for energy load forecasting, assigning relative priority values based on relevance to specific grid hierarchy elements and time scale periods, and iteratively weight these factors to generate revised forecasts that align with historic data within a threshold value.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional energy load forecasting methods are used, then the forecasting process is simple, but the accuracy of load forecasts deteriorates due to inability to properly prioritize and weight contextual influencing factors across different grid hierarchy elements and time scale periods
Solution Approach 1:
The forecasting system segments contextual influencing factors into different sets based on grid hierarchy elements (zonal substation, sub-transmission feeder, distribution substation, etc.) and forecast time scale periods. Each segment receives customized weighting, allowing accurate forecasting without overwhelming complexity by treating different factors differently according to their specific context.
Solution Approach 2:
The system dynamically changes the weighting parameters of contextual influencing factors based on the specific grid hierarchy element and forecast time scale period being analyzed. This parameter adaptation enables the system to achieve high accuracy by adjusting the importance of different factors (e.g., weather factors may be more important for short-term forecasts than long-term forecasts) without requiring a completely complex restructuring of the forecasting approach.
2Reliability
If uniform weighting is applied to all contextual influencing factors, then the forecasting system is easy to operate, but the reliability of energy grid infrastructure management deteriorates due to inconsistencies across different grid hierarchy elements and time periods
Solution Approach 1:
The system implements dynamic weighting where the importance of different contextual influencing factors automatically adjusts based on the specific grid hierarchy element and forecast time scale period. This dynamic adaptation ensures reliable and consistent forecasting across diverse scenarios without requiring manual intervention to set appropriate weights for each case, thereby maintaining ease of operation while achieving high reliability.
Solution Approach 2:
The forecasting system performs self-weighting by automatically determining the appropriate priority values for different contextual influencing factors based on the input parameters (grid hierarchy element and time scale period). This self-service capability eliminates the need for manual weighting adjustments while ensuring consistent and reliable results across different operating conditions.
3Measurement precision
If iterative weighting of contextual factors is performed, then the accuracy of forecasts is improved by aligning with historic data, but the processing time increases
Solution Approach 1:
The system performs preliminary segmentation and initial weighting of contextual influencing factors based on the grid hierarchy element and forecast time scale period before the iterative process begins. This preliminary preparation reduces the scope and complexity of subsequent iterative weighting operations, allowing the system to achieve high accuracy by aligning with historic data while minimizing the time required for iterative processing.
Data Source
AI summary
Energy load forecasts are generated via model(s) for the grid hierarchy elements for different forecast time scale periods as a function of different sets of prioritized contextual influencing factors for respective associated combinations of grid hierarchy elements and forecast time scale periods. Relative priority values of the sets of the contextual influencing factors are iteratively weighted until a revised energy load forecast generated as a function of the weighted values via the model(s) is within a threshold value of a historic energy load data value for the associated combination of the grid hierarchy element and forecast time scale period.