Data-Aware Network Slice Reallocation for Edge-Cloud Workloads
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 5G systems lack data-centric services for application optimization and load balancing, leading to inefficiencies in processing and resource management, particularly in high computational applications requiring real-time processing and ultra-low latency.
Innovation Solution
Implementing a data-aware computing and storage management function (DCSMF) that dynamically reallocates network and computing resources based on application requirements, resource availability, and network conditions, using machine learning and AI to optimize traffic and storage policies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If heavy or material-rich devices with high processing capacity are used, then processing capability is improved, but manufacturing cost and device weight increase
Solution Approach 1:
The patent segments processing tasks between edge devices and cloud data centers. Edge devices handle local real-time processing while cloud data centers handle heavy computational loads, allowing lighter edge device hardware while maintaining overall system processing capability.
Solution Approach 2:
The patent introduces edge computing nodes as intermediaries between end devices and cloud data centers. These edge nodes provide local processing capacity, reducing the need for extremely powerful (and expensive) local hardware while maintaining low latency through proximity-based processing.
2Loss of time
If more processing tasks are handled locally, then latency is reduced, but device resource consumption increases
Solution Approach 1:
The patent divides processing tasks into local and remote components. Time-sensitive tasks are processed locally at the edge to minimize latency, while non-time-critical tasks are offloaded to cloud data centers, optimizing the balance between latency and energy consumption.
Solution Approach 2:
The patent implements dynamic task allocation that adjusts processing location based on real-time conditions. When edge resources are available, tasks are processed locally; when edge resources are constrained, tasks are offloaded to cloud, creating a flexible system that adapts to changing energy and computational requirements.
3Productivity
If distributed computing is implemented, then resource utilization is improved, but system complexity increases
Solution Approach 1:
The patent creates a universal distributed computing architecture where edge devices and cloud data centers both implement standardized computing functions. This multi-functionality allows the same system components to serve multiple purposes (local processing, relay computing, cloud connectivity), improving resource utilization while managing complexity through standardization.
Data Source
AI summary
Aspects of the subject disclosure may include, for example, obtaining data, the data including first data indicative of a first amount of resources available as part of a first network slice of a plurality of network slices of a communication network, analyzing the data to determine that at least a first portion of a service provisioned via the first network slice is to be reallocated to at least a second network slice of the plurality of slices, and reallocating, based on the analyzing, the at least a first portion of the service to the at least a second network slice. Other embodiments are disclosed.