Built Environment Energy Prediction for Occupancy-Aware Load Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing energy consumption prediction systems for large facilities are inefficient, lacking real-time reporting and user-specific energy consumption analysis, and fail to accurately account for changing occupancy and operational factors, leading to increased costs and manual maintenance.
Innovation Solution
A method and system for predicting future energy consumption by collecting and analyzing real-time data from energy-consuming devices and users, using statistical models to aggregate and impute data, and applying multiplication factors to estimate residual standard deviations for pre-defined time bins, incorporating factors like temperature, occupancy, and energy behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing energy consumption prediction systems are used, then energy consumption trends can be analyzed, but real-time reporting and user-specific energy consumption analysis are not provided
Solution Approach 1:
The system segments energy consumption data by user, device, and time period, enabling both comprehensive trend analysis and specific real-time user reporting. Each user's energy consumption is tracked separately through portable communication devices, allowing precise measurement while providing individualized real-time feedback.
Solution Approach 2:
The system implements real-time feedback by notifying users immediately when their energy consumption exceeds predetermined thresholds. This feedback mechanism provides both real-time reporting and actionable insights, resolving the contradiction between comprehensive analysis and immediate information delivery.
2Quantity of substance
If traditional data collection methods are used, then data can be gathered, but the scope is limited and cannot cover each device present in electrical and mechanical systems
Solution Approach 1:
The system uses universal portable communication devices that users already possess to collect energy consumption data across multiple devices and systems. This multi-functional approach enables comprehensive data collection without requiring separate specialized equipment for each device, thus expanding coverage while managing complexity.
Solution Approach 2:
The portable communication device acts as an intermediary between users and the energy management system. It collects data from various energy-consuming devices and transmits it to the server, enabling comprehensive data collection without direct complex connections between the management system and each individual device.
3Reliability
If manual maintenance and monitoring are performed, then systems can be maintained, but cost escalation and frequent manual intervention are required
Solution Approach 1:
The system enables self-service by automatically monitoring energy consumption, detecting anomalies, and notifying users of threshold exceedances. This automated self-monitoring reduces the need for manual maintenance while improving reliability, as the system continuously tracks its own performance and alerts operators only when intervention is needed.
Solution Approach 2:
Real-time feedback on energy consumption patterns enables proactive maintenance by alerting users to abnormal usage before equipment failure occurs. This feedback loop improves system reliability while reducing the frequency of manual inspections, thereby increasing operational efficiency.
4Adaptability or versatility
If existing prediction systems are used, then general energy trends can be measured, but user-specific energy consumption patterns and behavioral changes are not considered
Solution Approach 1:
The system segments energy consumption data by individual user, device, and time period, enabling precise measurement of user-specific patterns. Each user's consumption is tracked separately through their portable communication device, allowing both high precision measurement and adaptability to individual behaviors.
Solution Approach 2:
The system dynamically adapts to changing user behaviors and occupancy patterns by continuously collecting real-time data and updating consumption profiles. This dynamic approach maintains measurement precision while becoming increasingly adaptable to individual user patterns over time.
Data Source
AI summary
The present disclosure provides a method and system for predicting a potential future energy consumption of a plurality of energy loads in a built environment. The method includes a step of collecting a first set of statistical data associated with a plurality of energy consuming devices. The method includes another step of accumulating a second set of statistical data associated with each of a plurality of users present inside the built environment. The method includes yet another step of analyzing the first set of statistical data and the second set of statistical data. In addition, the method includes yet another step of predicting a set of predictions associated with the potential future energy consumption of each of the plurality of energy consuming devices.