Global IP traffic reached 38 exabytes per month at the end of 2019, with a projected fourfold increase by 2025. By that time, 5G networks are expected to carry 45% of the total mobile traffic and serve up to 65% of the world’s population, supporting different vertical sectors. To efficiently serve the respective application scenarios, advanced networking, computing, and software technologies are being developed. Also, the respective infrastructures are undergoing a major transformation towards a disaggregated model, with the adoption of Software Defined Networking (SDN), Network Function Virtualization (NFV), and cloud-native principles that enable the virtualization and easy deployment of various services over rapidly allocated network slices.
It is clear, however, that the plethora of current and future verticals and uses cases requires an abstraction layer to be in place that will automate the use and fully exploit the available technologies. In this way, the overall infrastructure configuration will be performed in a simple, holistic and integrated manner, overcoming the barriers set by the increased complexity of the heterogeneous set of wireless and optical networking and computing resources, deployed in the fronthaul, midhaul and backhaul network segments.
Inline with the above, MAESTRO steps in to propose a novel intent-based networking (IBN) architecture for the orchestration of converged fiber-wireless-computing-storage infrastructures, adopting a closed-loop structure for life-cycle management. Optimization mechanisms will be proposed, based on Machine Learning (ML), Artificial Intelligence (AI), Deep-Reinforcement Learning (DRL) and multi-objective optimization to continuously improve application service delivery over the available resources. MAESTRO will enable the automation of an infrastructure’s configuration, translating intents to resource constraints (Objective – 1), deciding resource allocation and function/service workload placement (Objective – 2), and monitoring in real-time through telemetry the infrastructure (Objective – 3) and applying configuration changes programmable (Objective – 4).
MAESTRO’s intent-based converged fiber-wireless-computation-storage architecture
