Distributed Routing for Edge Computing Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless networks are not well-suited for low-latency, high-bandwidth edge-based computing due to slow and overhead-heavy connection handoffs, particularly in real-time data processing scenarios like self-driving cars and autonomous drones, where centralized authorities introduce significant latency and congestion.
Innovation Solution
Implementing a distributed routing environment using blockchain for contract-based handoffs between wireless base stations, allowing for decentralized coordination of handoffs and data processing at edge-based data centers, reducing reliance on central authorities and minimizing latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If centralized authorities (base station controllers, mobile switching centers) are used to coordinate handoffs between cellular towers, then connection handoff coordination is achieved, but significant latency and network overhead are introduced
Solution Approach 1:
The patent segments the centralized handoff coordination function into distributed autonomous agents deployed at edge data centers. Each agent independently makes handoff decisions for its associated cellular towers without requiring centralized coordination, thereby eliminating the latency introduced by centralized authorities while maintaining reliable handoff coordination through local intelligence.
Solution Approach 2:
The patent introduces a new dimensional approach by deploying autonomous handoff coordination agents at the edge of the network (at data centers) rather than maintaining a traditional centralized hierarchy. This spatial redistribution of coordination functions to the network edge enables parallel decision-making across multiple locations, reducing the time dimension of handoff latency while preserving coordination reliability.
2Power
If data is uploaded to traditional public cloud data centers for processing, then high-powered computing is achieved, but transmission time and latency increase due to large geographic distances
Solution Approach 1:
The patent applies local quality by distributing high-powered computing resources into multiple edge data centers located geographically close to end users. Each edge data center provides localized processing capability, ensuring that data processing power is available locally rather than requiring long-distance transmission to centralized cloud data centers, thereby reducing transmission time while maintaining computing power.
Solution Approach 2:
The patent transforms the traditional single-dimension centralized cloud model into a multi-dimensional distributed edge computing architecture. By adding the spatial dimension of distribution across multiple geographically dispersed edge locations, the system maintains high computing power locally at each edge data center while eliminating the time penalty of long-distance data transmission to centralized clouds.
3Device complexity
If geographically concentrated data centers are used, then infrastructure simplicity is maintained, but real-time processing latency increases for distant users
Solution Approach 1:
The patent segments the geographically concentrated data center infrastructure into multiple distributed edge data centers located throughout the service area. This segmentation reduces the average distance between users and processing resources, thereby reducing processing latency for distant users while maintaining infrastructure simplicity through modular replication of standardized edge data center units.
Solution Approach 2:
The patent addresses the latency problem by adding a spatial distribution dimension to the data center infrastructure. Instead of a single centralized location, multiple edge data centers are distributed across the geographic service area, creating a multi-location infrastructure that reduces transmission and processing latency for users regardless of their location, while maintaining operational simplicity through standardized deployment models.
Data Source
AI summary
Provided is a process including: advertising a plurality of values corresponding to computing components to peer nodes of a peer-to-peer network; storing the plurality of values in a tamper-evident, distributed ledger; determining a target data center in the distributed computing environment, wherein the target data center performs computations based on data sent from a mobile computing device, and wherein the target data center executes a peer node of the peer-to-peer network; determining a network path that is linked to the target data center based on a distance to the target data center; and transferring a packet from the target data center, wherein the packet traverses the network path and comprises one or more computation results from the target data center.