Machine Learning Power Attribution System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional electricity usage monitors are costly, clutter-inducing, and unable to detect changes in power consumption over time, making it difficult to identify malfunctioning devices without separate installation and aggregation of data.
Innovation Solution
A computing system uses time series data and machine learning to attribute power consumption to individual devices without the need for conventional monitors, detecting changes in usage patterns to identify devices that require repair or maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional electricity usage monitors are installed at each outlet to track device power consumption, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent merges multiple outlet monitors into a single system that monitors the entire premises. Instead of deploying individual monitors at each outlet, the system consolidates monitoring functions into one centralized device that tracks total power consumption and uses machine learning to attribute usage to individual devices.
Solution Approach 2:
The system creates a virtual model of device power consumption patterns through machine learning. Rather than physically monitoring each device, the system copies the behavioral characteristics of devices by analyzing temporal patterns in aggregated power data and reconstructing individual device usage profiles.
2Measurement precision
If conventional electricity usage monitors are installed at each outlet to track device power consumption, then measurement precision is improved, but the quantity of devices and clutter increase
Solution Approach 1:
The patent merges multiple outlet monitors into a single system that monitors the entire premises. Instead of deploying individual monitors at each outlet, the system consolidates monitoring functions into one centralized device that tracks total power consumption and uses machine learning to attribute usage to individual devices.
Solution Approach 2:
The single monitoring system performs multiple functions that would otherwise require separate devices: it monitors total premises consumption, identifies individual device usage, detects anomalies, and provides actionable insights. This multi-functional approach eliminates the need for multiple specialized monitors.
3Loss of information
If conventional electricity usage monitors are used to track power consumption, then power usage data is collected, but the ability to detect changes in usage patterns and identify malfunctioning devices is insufficient
Solution Approach 1:
The system implements feedback by continuously comparing actual power consumption patterns against learned normal patterns for each device. When deviations are detected, the system generates alerts and provides diagnostic information, creating a closed-loop system that not only collects data but actively monitors for anomalies and responds to potential issues.
Solution Approach 2:
The system transitions from static threshold-based monitoring to dynamic pattern recognition. Instead of using fixed thresholds to detect anomalies, the machine learning model continuously adapts to changing device behaviors and seasonal variations, enabling reliable detection of malfunctions even when usage patterns evolve over time.
Data Source
AI summary
A computing system may use time series data and machine learning to attribute power consumption to various devices in a location. The computing system may obtain time series data indicating a total amount of electricity being used at a location over time. The computing system may use a machine learning model, which has been trained to recognize devices based on an amount of electricity being used, to identify the devices at the location and determine how much electricity each device is using. Further, the computing system may use the machine learning model to detect changes in electricity consumption that may enable determination of devices that need to be repaired, turned on, or reconnected to the power source.