AI Power Consumption Prediction from Mixed Home Device Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing energy storage systems struggle to accurately predict power consumption in homes due to the lack of data on electronic devices with unknown usage patterns, necessitating a solution that can estimate and provide reliable energy consumption information.
Innovation Solution
An artificial intelligence apparatus using a neural network model to process power consumption data, classify mixed data into individual device data, and estimate consumption patterns for unknown devices, incorporating energy and usage information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If power consumption data is collected only for pre-registered electronic devices, then data accuracy for known devices is improved, but completeness of power consumption prediction deteriorates due to missing data on unknown devices
Solution Approach 1:
The patent introduces a neural network model as an intermediary component that processes mixed power consumption data and extracts individual device characteristics. This mediator enables the system to infer power consumption patterns of unknown devices by learning from aggregated data, thereby compensating for the lack of direct measurement data while maintaining prediction accuracy.
Solution Approach 2:
The patent creates virtual copies of power consumption data by synthesizing individual device power consumption patterns from mixed aggregate data using the neural network. This copying approach allows the system to generate realistic power consumption profiles for unknown devices without requiring actual measurement data from each specific device.
2Loss of information
If a neural network model is introduced to estimate power consumption of unknown devices, then power consumption prediction completeness is improved, but system complexity increases
Solution Approach 1:
The patent segments the power consumption prediction system into distinct functional modules: data collection module, neural network processing module, and prediction output module. The neural network itself is segmented into input layer, hidden layers, and output layer, each handling specific aspects of the data processing task. This segmentation makes the complex system more manageable and easier to implement.
Solution Approach 2:
The neural network model performs self-learning and self-adjustment by automatically optimizing its internal parameters through training on available power consumption data. This self-service capability reduces the need for manual configuration and complex external control mechanisms, thereby managing system complexity while maintaining high prediction accuracy.
3Measurement precision
If mixed power data is classified into individual device data, then specificity of power consumption information is improved, but processing complexity increases
Solution Approach 1:
The patent transforms the classification problem by changing the parameters used for differentiation. Instead of using complex multi-dimensional classification rules, the neural network learns to differentiate devices based on characteristic patterns in the power consumption data such as temporal patterns, magnitude variations, and spectral characteristics. This parameter transformation simplifies the processing while maintaining high specificity.
Data Source
AI summary
The present disclosure relates to an artificial intelligence device and method capable of predicting an amount of power consumption occurring in a home, can obtain power consumption data for pre-registered electronic devices, check whether there is a specific electronic device for which the power consumption data has not been obtained, and if there is a specific electronic device for which the power consumption data has not been obtained, obtain mixed power data consumed in a current home, classify the obtained mixed power data into a plurality of individual power data, extracts individual power data matching the specific electronic device, estimate power consumption data for the specific electronic device based on the extracted individual power data, and predict an amount of power consumption in a home based on power consumption data for all pre-registered electronic devices.