Distributed, self-adjusting and optimizing core network with machine learning

A computing system for dynamically creating distributed, self-adjusting and optimizing core network with machine learning, the computing system comprising:

• one or more hardware processors;
• and
• a memory coupled to the one or more hardware processors, wherein the memory comprises a plurality of modules in a form of programmable instructions executable by the one or more hardware processors, wherein the plurality of modules comprises:
• a data receiver module configured to receive a request from one or more client devices to access one or more services hosted on one or more external devices, wherein the request comprises:
• type of the one or more client devices, type of network associated with the one or more client devices, subscriber data passing through one of:
• the one or more client devices and one or more service layers, traffic load on each of the one or more client devices, location of the one or more client devices, underlying cloud infrastructure running the one or more client devices, a set of resources and processor types associated with the underlying cloud infrastructure;
• a session establishing module configured to establish a secure real time communication session with the one or more client devices and a set of service layers based on the received request, wherein the set of service layers comprise:
• one or more discovery layers, one or more control layers and one or more data layers, wherein the set of service layers is associated with at least one or combination of:
• inter-network and one or more intra-networks;
• a service parameter determination module configured to determine one or more service parameters associated with the one or more services based on the received request by using a trained service based Machine Learning (ML) model, wherein the one or more service parameters comprise:
• type of the one or more services, demand of each of the one or more services and location of the one or more external devices hosting the one or more services;
• a broadcasting module configured to broadcast one or more handshake messages to each of the set of service layers within at least one of:
• the inter-network and the one or more intra-networks;
• an environmental parameter determination module configured to determine one or more environmental parameters associated with each of the set of service layers within the established secure real time communication session based on one or more responses of the broadcasted one or more handshake messages, the received request and the one or more service parameters by using the trained service based ML model, wherein the one or more environmental parameters comprise:
• cost, distance to reach each of the set of service layers, latency, green energy, resiliency, a set of external devices peered to each of the set of service layers and a set of compute hosting the set of service layers;
• a layer determination module configured to determine best possible service layer among at least one of:
• the inter-network and the one or more intra-networks capable of processing the received request within the established secure real time communication session based on the determined one or more environmental parameters, the received request, the one or more service parameters and predefined priority of each of the one or more client devices by using the trained service based ML model;
• a request processing module configured to process the received request at the determined best possible service layer;
• and
• a session management module configured to perform one of:
• terminate and transfer the established secure real time communication session after the received request is processed.