AI Pod Resource Manager for Edge Computing Latency

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current cloud and edge computing systems face challenges in efficiently scheduling and allocating resources to meet the low latency requirements of time-sensitive applications, such as autonomous driving and video surveillance, due to high data transfer latency and inefficient resource utilization.

Innovation Solution

A pod resource manager that leverages AI and machine learning, specifically reinforcement learning, to dynamically allocate computing resources based on telemetry data and performance metrics, continuously learning and adapting to optimize resource configurations and meet service level agreements (SLAs).

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If data is transferred from client to remote computer for processing, then computing resources are available, but latency increases making it unacceptable for time-sensitive applications

Engineering Contradiction:

Improvelatency requirementVSAvoiddata transfer speed

Core Design Contradiction:

ReliabilityVSSpeed

Solution Approach 1:

The system segments computing resources into edge computing nodes distributed geographically closer to client devices, separating the remote cloud computing function into local edge processing units that can serve time-sensitive applications without requiring long-distance data transfer

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Edge computing nodes serve as intermediary processing points between client devices and remote cloud data centers, enabling local processing of time-sensitive data while maintaining connection to remote computing resources for non-time-critical tasks

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If more computing resources are allocated to meet application demands, then service quality improves, but resource utilization efficiency decreases

Engineering Contradiction:

Improveservice level agreementVSAvoidresource utilization

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system implements dynamic resource allocation where computing resources are automatically adjusted based on real-time workload demands, application priorities, and current system state, allowing resources to be allocated precisely when and where needed rather than statically provisioned

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms that monitor application performance, resource utilization, and workload characteristics to continuously optimize resource allocation decisions, using learned patterns to predict future demands and pre-position resources accordingly

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11507430B2Accelerated resource allocation techniques

Publication Date: 2022.11.22 INTEL CORP

AI summary

Examples described herein can be used to determine and suggest a computing resource allocation for a workload request made from an edge gateway. The computing resource allocation can be suggested using computing resources provided by an edge server cluster. Telemetry data and performance indicators of the workload request can be tracked and used to determine the computing resource allocation. Artificial intelligence (AI) and machine learning (ML) techniques can be used in connection with a neural network to accelerate determinations of suggested computing resource allocations based on hundreds to thousands (or more) of telemetry data in order to suggest a computing resource allocation. Suggestions made can be accepted or rejected by a resource allocation manager for the edge gateway and the edge server cluster.