Distributed Core Network with ML Service Layer Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional computer networking systems face issues such as latency, scalability, cost, and unscalability due to their monolithic and centralized nature, failing to dynamically optimize service layer access and consider local and cloud resources, leading to inefficient cloud-native network deployments.
Innovation Solution
A computing system utilizing machine learning to dynamically create a distributed, self-adjusting, and optimizing core network by determining the best service layer based on environmental and service parameters, leveraging both local and cloud resources for secure real-time communication sessions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If conventional centralized systems are used to access services, then system stability is maintained, but latency and access speed increase
Solution Approach 1:
The patent segments the monolithic core network into multiple service layers (control plane, user plane, management plane) that can be independently deployed and executed across distributed edge devices and cloud platforms. This segmentation enables parallel processing and reduces access latency while maintaining system stability through modular architecture.
Solution Approach 2:
The patent transitions from a single centralized dimension to a multi-dimensional distributed architecture where service layers can be deployed across edge devices, local servers, and cloud platforms simultaneously. This dimensional expansion allows services to be accessed from multiple locations, reducing latency while distributing system complexity across different nodes.
2Adaptability or versatility
If monolithic centralized systems are used, then ease of operation is maintained, but scalability deteriorates
Solution Approach 1:
The patent creates universal service layers that can function across multiple environments (edge devices, local servers, cloud platforms) with consistent interfaces and protocols. This multi-functionality enables scalable deployment while maintaining ease of operation through standardized service access methods that work uniformly across distributed infrastructure.
Solution Approach 2:
The patent implements dynamic service layer deployment where individual service layers can be independently scaled, updated, and relocated based on demand. This dynamic architecture enables scalability while maintaining operational simplicity through automated service discovery and load balancing that abstracts the complexity from users.
3Productivity
If conventional systems host services locally or on single cloud providers, then control is maintained, but cost and resource efficiency worsen
Solution Approach 1:
The patent introduces service layers as intermediaries between client devices and underlying infrastructure (local servers, multiple cloud providers). These service layers abstract infrastructure complexity while enabling efficient resource utilization by intelligently routing requests to appropriate execution environments based on cost, performance, and availability criteria.
Solution Approach 2:
The patent dynamically changes execution parameters (location, resource allocation, pricing models) for service layers based on real-time conditions. This enables optimization of resource utilization and cost efficiency by migrating services between edge, local, and cloud environments while maintaining operational control through parameter-based decision making.
4Reliability
If conventional systems are used, then existing infrastructure compatibility is maintained, but resilience and throughput deteriorate
Solution Approach 1:
The patent segments network functions into independent service layers that can be distributed across multiple execution environments. This segmentation improves resilience by isolating failures to specific layers or nodes while maintaining overall system functionality, and increases throughput through parallel processing across distributed edge and cloud infrastructure.
Data Source
AI summary
A system and method for dynamically creating distributed, self-adjusting and optimizing core network with machine learning is disclosed. The method includes receiving a request to access one or more services and establishing a secure real time communication session with one or more client devices and a set of service layers based on the received request. The method further includes determining one or more service parameters based on the received request and sending one or more handshake messages to each of the set of service layers. Further, the method includes determining one or more environmental parameters and determining best possible service layer capable of processing the received request by using a trained service based ML model. The method includes processing the request at the determined best possible service layer and terminating or transferring the secure real time communication session after the request is processed.