Electricity Sensor Pairing Profiles for Fair Shared Property Billing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing insurance and utility cost allocation systems are inadequate for shared properties, as they do not account for individual usage or risk factors among multiple users, leading to inequitable cost distribution.
Innovation Solution
A control system that collects electricity and device pairing data using sensors and machine learning to determine individual usage patterns, enabling fair cost allocation based on actual usage and risk levels, with a PCA computing device managing payments and insurance adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If existing insurance and utility cost allocation systems are used, then cost distribution is simplified, but individual usage and risk factors are not accounted for, leading to inequitable cost distribution
Solution Approach 1:
The system segments the property into multiple controllable zones with separate electricity sensors, allowing individual usage tracking for each zone. This enables precise measurement of energy consumption by specific devices or locations while maintaining the ability to allocate costs equitably among multiple users based on actual usage data.
2Measurement precision
If sensor data collection and machine learning analysis are implemented, then usage tracking accuracy is improved, but system complexity increases
Solution Approach 1:
The system employs machine learning models that automatically analyze sensor data, detect usage patterns, and allocate costs without requiring manual intervention or complex user configuration. The system self-adjusts to changing usage behaviors and automatically updates allocations, reducing the operational burden on users while maintaining high measurement precision.
3Measurement precision
If real-time sensor monitoring and machine learning analysis are implemented, then cost allocation fairness is improved, but processing time and computational resources increase
Solution Approach 1:
The system continuously collects and stores sensor data in advance, building historical usage profiles through machine learning. When cost allocation is needed, the pre-trained models can quickly analyze stored data and generate allocations without requiring real-time processing of all historical data, thus reducing processing time while maintaining fairness.
Solution Approach 2:
The system performs cost allocation calculations periodically rather than continuously, using pre-computed usage patterns and profiles. This periodic processing approach reduces computational resource consumption and processing time while still providing accurate and fair cost allocations based on the most recent usage data available.
Data Source
AI summary
A control system includes at least one electricity sensor and a control hub, both physically located at a property. Each electricity sensor is continuously measuring electricity passing therethrough. The control hub is configured to wirelessly pair with/detect proximity of registered mobile devices within/at the property and to generate a pairing record each instance any registered mobile device wirelessly pairs with/is detected within proximity of the control hub. The control system records electricity measurements and pairing records, executes a trained machine learning model using the electricity measurements and pairing records—wherein output from the model includes a pairing profile for each registered mobile device, each pairing profile representing a standard/typical schedule of the registered mobile device in relation to electricity consumption with a same/similar standard or typical schedule—and pre-emptively associates further electricity measurements with a respective registered mobile device according to the pairing profiles without requiring corresponding pairing records.