Distributed Trusted Sensing for Integrated Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional centralized processing schemes in integrated communication, sensing, and computation networks consume significant communication and computation resources, leading to privacy leakage and data security risks.
Innovation Solution
A distributed trusted sensing method and system that utilizes edge nodes to perform local training on a global model using local data, with miners facilitating weighted aggregation and digital signature verification to maintain data security and resource efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If centralized processing scheme is used, then data security and privacy protection are improved, but communication and computation resource consumption increase significantly
Solution Approach 1:
The patent segments the centralized processing function into distributed edge nodes, each performing local training independently. This segmentation eliminates the need to transmit all raw data to a central server, reducing communication resource consumption while maintaining security through localized processing
Solution Approach 2:
The patent introduces a miner as an intermediary component that collects local model parameters from edge nodes, performs weighted aggregation, and generates global model parameters. This intermediary mechanism enables secure distributed processing without requiring direct data sharing between nodes, thus reducing communication overhead while maintaining data security
2Reliability
If centralized processing scheme is used, then data security is improved, but computation resource consumption increases significantly
Solution Approach 1:
The computation task is segmented into local training operations at edge nodes and global aggregation operations at miners. Each edge node performs computation only on its local data, avoiding the need to transmit and process all data centrally, thereby significantly reducing overall computation resource consumption while maintaining security
Solution Approach 2:
The miner acts as an intermediary that performs computation aggregation rather than centralized processing. It collects model parameters from multiple edge nodes and computes weighted averages to generate global parameters, reducing computation resource consumption compared to centralized processing while maintaining data security
3Use of energy by moving object
If distributed processing is implemented, then communication and computation resource consumption are reduced, but data security and privacy protection may be compromised
Solution Approach 1:
The miner serves as a trusted intermediary that aggregates model parameters without accessing raw data from edge nodes. It performs weighted aggregation on model parameters and generates global model parameters, ensuring data security while enabling distributed processing. The intermediary mechanism prevents data exposure between nodes while maintaining security through centralized coordination
Solution Approach 2:
The patent uses model parameter copies instead of raw data copies. Each edge node trains a local model and shares only the parameter copies with the miner, not the actual data. This copying approach enables distributed processing with reduced communication overhead while maintaining data security, as only parameter information is transmitted rather than complete datasets
4Productivity
If original datasets are shared for processing, then computation efficiency is improved, but privacy leakage risks increase
Solution Approach 1:
The patent replaces data sharing with parameter copying. Instead of sharing original datasets for processing, each edge node trains locally and shares only the model parameter copies with the miner. This approach maintains computation efficiency through distributed training while eliminating privacy leakage risks, as only parameter information is exchanged rather than raw data
Solution Approach 2:
The miner acts as an intermediary that processes parameter copies rather than raw data. It performs weighted aggregation on model parameters to generate global parameters, enabling efficient computation without exposing original datasets. This intermediary mechanism maintains productivity while preventing privacy leakage by processing only aggregated parameter information
Data Source
AI summary
The present disclosure relates to a distributed trusted sensing method and system for an integrated communication, sensing, and computation network, and relates to the field of wireless sensing technologies. First, a global model and an initial global parameter are transmitted to each edge node. Each edge node performs local training by using local data, to obtain a local model parameter, broadcasts the local model parameter through a corresponding miner, then assigns a weight to each local model parameter, to calculate a global parameter, and updates the global parameter through aggregation iteration. In the present disclosure, calculation is performed by using computation resources and data resources of each distributed edge node, thus saving the overall communication and computation resources.