Building Energy Load Partitioning for Actionable Use Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing energy load measurement systems, such as smart meters, primarily provide gross energy consumption data, making it difficult for energy systems engineers to identify causal factors of energy use in large non-residential buildings, which are complex and have varying occupancy and equipment usage patterns, limiting their effectiveness in reducing energy consumption.
Innovation Solution
The system processes energy load data using unsupervised machine learning methods to identify partitions or clusters and perform temporal processing, allowing for the visualization of accurate energy consumption patterns, which can be used to reduce energy consumption and waste in buildings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If smart meters are deployed to measure energy load data in large non-residential buildings, then energy consumption data becomes available, but the data remains at a gross level and causal factors of energy use cannot be identified
Solution Approach 1:
The patent applies segmentation by dividing the gross energy consumption data into distinct partitions representing different operational states (occupied, closed, open, unoccupied). This segmentation transforms the aggregated energy data into state-specific partitions, enabling identification of energy consumption patterns associated with different building states and causal factors.
Solution Approach 2:
The patent introduces an intermediary processing system that acts as a mediator between the raw smart meter data and the energy analysis. This system applies unsupervised machine learning to transform the gross energy consumption data into meaningful partitions and patterns, bridging the gap between available data and actionable insights.
2Quantity of substance
If energy load data is collected from large non-residential buildings with multiple units and varying occupancy, then comprehensive energy consumption data is obtained, but the complexity of analyzing varying patterns increases
Solution Approach 1:
The patent implements self-service through unsupervised machine learning that automatically identifies partitions and patterns in the energy data without requiring manual intervention or expert analysis. The system serves itself by autonomously processing the complex multi-unit building data, grouping similar patterns together, and generating actionable insights without human supervision.
Solution Approach 2:
The patent applies parameter changes by transforming the raw energy consumption data through unsupervised learning algorithms that change the organizational parameters of the data. The system reorganizes the data based on inherent patterns and similarities, converting complex varying patterns into structured partitions that are easier to analyze and interpret.
3Productivity
If traditional energy measurement systems are used in buildings, then gross energy consumption figures are provided for billing, but the data cannot be used to identify opportunities for reducing energy consumption
Solution Approach 1:
The patent applies universality by creating a multi-functional energy data processing system that serves both billing purposes and energy reduction identification. The same processed partitions and patterns can be used for accurate billing while simultaneously providing actionable insights for energy conservation, making the system versatile for multiple objectives.
Solution Approach 2:
The patent implements feedback by using the identified energy consumption patterns and partitions to provide actionable recommendations that can reduce future energy consumption. The system creates a feedback loop where analyzed patterns inform energy reduction actions, which in turn affect future energy consumption and can be monitored through continued data collection and analysis.
Data Source
AI summary
Certain examples described herein provide a system and a method for the determination of energy consumption patterns for a building. The system (410) may have an energy load data interface (414) to receive energy load data (412) originating from energy use sensors for the building; a data partition engine (416) to apply a clustering model to the energy load data to determine one or more partitions (418) within the energy load data; a temporal processing engine (420) to segment and aggregate the energy load data over a set of predefined time periods, wherein the temporal processing engine is independently applied to the partitions determined by the data partition engine; a visualisation engine (424) to generate visualisation data from the output of the temporal processing engine, the visualisation data comprising respective sets of data for the partitions determined by the data partition engine; and an output interface (426) to output the visualisation data (428) for display.