Power Model Training Using Network Data Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing power monitoring systems are inefficient in providing accurate, aggregate electricity usage data for multiple devices in a building, as they require multiple expensive devices and significant manual effort, and struggle with disaggregating power usage from collective electrical signals.
Innovation Solution
A system that combines electrical line data with network data to identify and track individual devices and their state changes using power monitoring signals and network transmissions, allowing for more accurate and efficient monitoring of electricity usage across multiple devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple power monitors are used to monitor individual devices, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent segments the power monitoring task by separating signal acquisition (single aggregate monitor at electrical panel) from signal processing (disaggregation algorithms that divide collective signal into individual device components). This allows one monitor to perform the function of multiple monitors through computational segmentation of the electrical signal.
Solution Approach 2:
The patent introduces network data as an intermediary that bridges the gap between aggregate power measurements and individual device states. Network data provides device-level information that complements power signal data, enabling the system to attribute power consumption to specific devices without physically monitoring each device.
2Measurement precision
If multiple power monitors are installed for each device, then measurement precision is improved, but ease of operation deteriorates due to significant manual effort required for installation
Solution Approach 1:
The patent merges power monitoring functionality with existing network infrastructure. Instead of installing separate monitoring devices for each appliance, the system combines aggregate power monitoring with network data collection to achieve device-level monitoring through a unified approach that leverages already-present components.
Solution Approach 2:
The system enables devices to self-identify through network broadcasts, eliminating the need for manual device registration or configuration. Devices automatically provide their identity and status information through network protocols, and the system autonomously correlates this with power consumption data.
3Ease of operation
If a single power monitor is installed at the electrical panel, then ease of operation is improved, but measurement precision deteriorates due to difficulty in extracting specific device information from collective signals
Solution Approach 1:
The patent replaces the mechanical approach of physically connecting monitors to individual devices with an information-based approach. Instead of mechanical/electrical connections to each appliance, the system uses signal processing and data correlation through the electrical and network infrastructure already present in the building.
Solution Approach 2:
The patent adds a temporal dimension to the monitoring approach by continuously collecting and analyzing power signals over time, enabling the system to distinguish individual device patterns within the aggregate signal. The system also incorporates a second dimension of network data to provide additional discrimination capabilities for identifying device-level consumption.
Data Source
AI summary
Power models may be used to identify devices in a building or state changes of devices in a building by processing a power monitoring signal with the power models. A power model for a device may be trained using examples of power monitoring signals corresponding to that device, and network monitoring may be used to identify training data for training power models for that device. Network monitoring may include receiving information about network packets transmitted by devices in the building and processing the information about the network packets to determine information about a state change of a first device in the building at a first time. A portion of the power monitoring signal that includes the first time may then be used to train a power model for the first device. The trained power model for the first device may then be deployed to a building where it used to perform power monitoring of the first device.