Deep data plane programming and AI for zero-trust self-driven networking in beyond 5G

Othmane Hireche,Chafika Benzaïd,Tarik Taleb

doi:10.1016/j.comnet.2021.108668

Abstract

Along with the high demand for network connectivity from both end-users and service providers, networks have become highly complex; and so has become their lifecycle management. Recent advances in automation, data analysis, artificial intelligence, distributed ledger technologies (e.g., Blockchain), and data plane programming techniques have sparked the hope of the researchers’ community in exploring and leveraging these techniques towards realizing the much-needed vision of trustworthy self-driving networks (SelfDNs). In this vein, this article proposes a novel framework to empower fully distributed trustworthy SelfDNs across multiple domains. The framework vision is achieved by exploiting (i) the capabilities of programmable data planes to enable real-time in-network telemetry collection; (ii) the potential of P4 – as an important example of data plane programming languages – and AI to (re)write the source code of network components in a fashion that the network becomes capable of automatically translating a policy intent into executable actions that can be enforced on the network components; and (iii) the potential of blockchain and federated learning to enable decentralized, secure and trustable knowledge sharing between domains. A relevant use case is introduced and discussed to demonstrate the feasibility of the intended vision. Encouraging results are obtained and discussed.

Highlights

Along with the ongoing advances in the communications and networking technologies, highly-innovative mobile services have emerged, involving a potential number of users and a much further higher number of devices (e.g., Internet of Things — IoT devices)
The framework vision is achieved by exploiting (i) the capabilities of programmable data planes to enable real-time in-network telemetry collection; (ii) the potential of P4 – as an important example of data plane programming languages – and Artificial Intelligence (AI) towrite the source code of network components in a fashion that the network becomes capable of automatically translating a policy intent into executable actions that can be enforced on the network components; and (iii) the potential of blockchain and federated learning to enable decentralized, secure and trustable knowledge sharing between domains
While in the previous section we provided an overview of the main stages composing the operation and management closed loop of a self-driving networks (SelfDNs) in general, here we motivate the need of empowering SelfDN in 5G and beyond networks and discuss the key requirements and challenges that should be taken into account to enable self-driving mobile networks

Summary

Introduction

Along with the ongoing advances in the communications and networking technologies, highly-innovative mobile services have emerged, involving a potential number of users and a much further higher number of devices (e.g., Internet of Things — IoT devices). Configuring these extremely-large, extremely dynamic, and extremely-complex networks and constantly managing their lifecycle have become much more challenging. In this regard, human interventions have lead to eventual errors: 80% of businesses claim to have experienced network errors caused by human mistakes on a regular basis [1]. The road towards realizing this vision is still quite long, but the community of researchers firmly believes that this defines a new horizon for the future of smart network management

Objectives

Results

Conclusion