Building Energy Analytics for Granular Overconsumption Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current energy consumption analysis in buildings focuses on aggregate values like minimum, maximum, mean, and median, failing to capture detailed intervals of energy consumption throughout a day, leading to inefficiencies and high costs.
Innovation Solution
Implementing an energy management system with real-time monitoring and metering that disaggregates energy consumption data into granular classifications, identifies baseload candidates, and generates models to detect inefficiencies and overconsumption, enabling actionable recommendations for energy savings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If aggregate energy consumption values (minimum, maximum, mean, median) are used for analysis, then the analysis is simple and computationally efficient, but detailed intervals of energy consumption throughout the day are not captured
Solution Approach 1:
The patent segments energy consumption data into multiple granular time intervals (e.g., 15-minute intervals) throughout the day, allowing detailed analysis of energy consumption patterns at different times. This segmentation enables the system to capture detailed intervals while maintaining manageable data structures through systematic organization of time-based segments.
2Loss of information
If real-time monitoring and granular classification of energy consumption data is implemented, then detailed energy consumption intervals are captured, but the system complexity and computational requirements increase
Solution Approach 1:
The patent extracts key features and patterns from granular energy consumption data by identifying baseload candidates and generating predictive models. This extraction process distills detailed information into essential characteristics that can be analyzed without requiring the full complexity of raw granular data, reducing system complexity while preserving important detailed intervals.
Solution Approach 2:
The patent performs preliminary processing of energy consumption data by disaggregating aggregate values into granular time intervals and identifying baseload patterns before detailed analysis. This preliminary action organizes and pre-processes data structures, making subsequent detailed analysis more efficient and reducing the computational burden on the overall system.
3Device complexity
If minimum value is used to represent baseload, then the representation is simple, but the variance of the baseload period is not captured
Solution Approach 1:
The patent applies local quality by treating different time intervals within the baseload period differently, analyzing the variance and characteristics of each interval rather than applying a single minimum value representation. This allows the system to capture local variations in baseload consumption patterns while maintaining an organized structure for analysis.
Data Source
Figure 1
Figure 2A~2F
Figure 3
AI summary
Energy analytics and management includes collecting energy consumption data for a site by energy consumption meters. The energy consumption data is disaggregated into a plurality of granular classifications as a function of data point values and data point timestamps and analyzed in view of the classifications and in view of additional site information and historical energy consumption data to identify periods of over consumption and associated over consumption patterns for the site. A visualization provides information about the periods of over consumption and associated over consumption patterns, including a recommendation for improving energy consumption efficiency for the site.