Energy Load Disaggregation for Building Peak Demand Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current energy management systems lack the ability to effectively identify and manage energy load peaks across multiple assets in a building, leading to inefficiencies and increased energy costs due to the inability to accurately determine individual contributions to these peaks.
Innovation Solution
A computer-implemented method that receives total energy load data, determines energy load peaks using pattern recognition or machine learning algorithms, and disaggregates this data into individual asset contributions, allowing for control strategies to mitigate peaks and provide insights for energy managers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If total energy load data is monitored without disaggregation, then energy consumption overview is maintained, but individual asset contributions to energy load peaks cannot be identified
Solution Approach 1:
The patent applies segmentation by disaggregating total energy load data into individual asset energy load data. The system segments the aggregated energy consumption information into contributions from specific assets, enabling identification of individual asset contributions to energy load peaks while maintaining system-level monitoring capabilities.
2Productivity
If energy load peaks are not detected and managed, then system operates continuously, but energy costs increase and efficiency decreases
Solution Approach 1:
The patent applies preliminary action by detecting energy load peaks in advance and providing early warning signals. The system identifies upcoming energy load peaks through pattern recognition and machine learning algorithms, enabling proactive management actions to be taken before peaks occur, thereby preventing increased energy costs and improving overall energy management efficiency.
3Measurement precision
If pattern recognition and machine learning algorithms are used to detect energy load peaks, then detection accuracy improves, but processing time and computational resources increase
Solution Approach 1:
The patent applies partial action by using pattern recognition and machine learning algorithms selectively for detecting significant energy load peaks rather than continuously processing all data. The system focuses computational resources on identifying and analyzing peak events specifically, achieving high detection accuracy for critical moments while reducing overall processing time and computational burden compared to continuous full-data analysis.
Data Source
Figure 1~3
Figure 4~5
Figure 6
AI summary
Computer-implemented method for determining an energy load distribution in a system, comprising: receiving total energy load data of the system, wherein the total energy load data comprises individual energy load data of a plurality of assets; determining at least one energy load peak in the total energy load data; disaggregating the total energy load data into the individual energy load data of the plurality of assets; providing the disaggrateted individual energy load data of the plurality of assets for further processing.