Network Power Prediction Using Virtual Device Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing artificial intelligence applications face challenges in environments with limited or no available data, particularly in complex network arrangements with non-homogeneous or unknown device specifications, making it difficult to predict power consumption and recommend optimal network arrangements.
Innovation Solution
The system generates and trains a model using a device profile repository that includes both known and virtual device specifications, creating a 'digital twin' of devices with unknown specifications to complete incomplete data sets and properly train the AI model, enabling power consumption predictions and recommendations for network arrangements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If artificial intelligence models are used to predict power consumption in network arrangements, then prediction capability is improved, but the requirement for large amounts of high-quality training data increases
Solution Approach 1:
The patent creates virtual device profiles that are copies or representations of physical devices with unknown specifications. These virtual profiles replicate the essential characteristics and power consumption patterns of physical devices, allowing the AI model to train on synthesized data without requiring extensive measurements from every possible device configuration.
Solution Approach 2:
The system performs preliminary actions by pre-generating virtual device profiles and populating the device profile repository before the AI model needs training data. This advance preparation ensures that when power consumption predictions are needed, the model already has access to a comprehensive set of training data covering diverse device specifications.
2Adaptability or versatility
If the system supports non-homogeneous devices with unknown specifications, then adaptability is improved, but data completeness deteriorates
Solution Approach 1:
The virtual device profile acts as an intermediary between physical devices with unknown specifications and the AI model requiring training data. By creating virtual representations that bridge this gap, the system enables the model to learn power consumption patterns for diverse device types without direct access to every physical device's actual performance data.
Solution Approach 2:
The system changes parameters by synthesizing virtual device specifications based on available information and power consumption patterns from similar devices. This parameter transformation allows the system to work with incomplete data by inferring and generating plausible device characteristics that maintain data completeness for training purposes.
3Reliability
If the device profile repository includes virtual specifications, then model training capability is improved, but system complexity increases
Solution Approach 1:
The patent segments the device profile repository into distinct virtual profiles, each representing specific device types or configurations. This segmentation organizes the complex data into manageable units, making it easier to generate, store, and retrieve appropriate training data for the AI model without being overwhelmed by the overall system complexity.
Data Source
AI summary
Systems and methods are described herein for novel uses and/or improvements to artificial intelligence applications in an environment with limited or no available data. In particular, systems and methods are described herein for providing network arrangement recommendations based on power consumption predictions for selected applications within network arrangements featuring devices with non-homogeneous or unknown specifications.