Edge Computing Peer-to-Peer Transfer via Availability Scores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing edge computing solutions are inefficient in handling frequent entry and exit of mobile computing devices, as they rely on central orchestrators for computation transfer, leading to inefficiencies in processing and data management within edge computing ecosystems.
Innovation Solution
Implement a peer-to-peer computation transfer method where mobile computing devices proactively assess and transfer compute functions to peers with higher availability scores, matching security and compute capabilities, without relying on central coordination, by periodically calculating availability scores and predicting device departures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If centralized orchestrators are used for computation transfer, then coordination and control are improved, but system complexity and processing overhead increase
Solution Approach 1:
The patent extracts the centralized orchestrator from the system architecture and replaces it with distributed peer-to-peer mechanisms. Mobile computing devices independently perform availability scoring, departure prediction, and peer selection without central coordination, eliminating the single point of control and reducing system complexity while maintaining reliability through distributed consensus
Solution Approach 2:
Mobile computing devices autonomously manage their own computation transfer by self-assessing availability scores, predicting their own departure times, identifying suitable peers, and executing state transfers independently. This self-service approach eliminates dependency on centralized orchestrators, reducing coordination overhead and system complexity
2Reliability
If computation transfer relies on central orchestrators, then control is improved, but processing efficiency and response time deteriorate
Solution Approach 1:
The patent segments the centralized control function into distributed autonomous operations at each mobile computing device. By dividing the monolithic orchestrator into individual device-level decision-making units, the system achieves parallel processing of availability assessment, peer selection, and state transfer initiation, dramatically improving processing efficiency and response time
Solution Approach 2:
Mobile computing devices continuously perform preliminary actions by periodically calculating availability scores and predicting future departure times before actual departure occurs. This proactive approach enables computation transfer to be initiated earlier and executed more efficiently without waiting for central orchestrator commands, improving overall processing speed
3Adaptability or versatility
If mobile devices frequently enter and exit edge computing ecosystems, then adaptability is improved, but computation handover efficiency deteriorates
Solution Approach 1:
The patent implements preliminary action by having mobile computing devices continuously predict their future departure times and proactively initiate computation transfers before actually leaving the edge computing ecosystem. This advance preparation ensures seamless handover to peer devices, maintaining high computation handover efficiency despite frequent device mobility and ecosystem entry/exit events
Solution Approach 2:
The system dynamically adapts to frequent device mobility by continuously updating availability scores and re-evaluating peer selections based on current system state. Mobile devices can dynamically enter and exit the ecosystem while the peer-to-peer mechanism automatically adjusts computation assignments, maintaining handover efficiency through real-time adaptability
Data Source
AI summary
Peer-to-peer transfer of compute function state in an edge computing ecosystem is provided. An availability score corresponding to a mobile computing device is received. It is determined whether the availability score is less than an availability score threshold. In response to determining that the availability score is less than the availability score threshold, departure coordinates of the mobile computing device from the edge computing ecosystem and departure time are determined. At least one peer mobile computing device is identified having a corresponding availability score greater than the availability score threshold, a corresponding security profile that at least matches a security profile of the mobile computing device, and a corresponding compute power capability that at least matches a compute power capability of the mobile computing device. A compute function state of the mobile computing device is transferred to the at least one peer mobile computing device.