Aerial-Aided Multi-Access Edge Computing: Dynamic and Joint Optimization of Task and Service Placement and Routing in Multi-Layer Networks

Ubiquity in network coverage is one of the main features of 5G and is expected to be extended to the computing domain in 6G. In order to provide ubiquity in communication and computation, the integration of satellite, aerial and terrestrial networks is foreseen. In particular, the rising amount of applications such as In-Flight Entertainment and Connectivity Services (IFECS) and Software Defined Networking-enabled satellites renders network management more challenging. Moreover, due to the stringent Quality of Service (QoS) requirements, edge computing is vital for these applications. Network performance can be boosted by considering components of the aerial network, like aircrafts, as potential Multi-Access Edge Computing (MEC) nodes. Thus, to cater to the QoS-critical applications, we propose an Aerial-Aided Multi-Access Edge Computing (AA-MEC) architecture that provides a framework for optimal management of computing resources and internet-based services in the sky. Furthermore, we formulate optimization problems to minimize the network latency for the two use cases of providing IFECS to other aircrafts in the sky and providing services for offloading AI/ML-tasks from satellites. Due to the dynamic nature of the satellite and aerial networks, we propose a re-configurable optimization. For the transforming network we continuously identify the optimal MEC node for each application and the optimal path to the destination MEC node. In summary, our results demonstrate, that using AA-MEC improves network latency performance by 10.43% compared to the traditional approach of using only terrestrial MEC nodes, for latency-critical applications such as online gaming. Furthermore, while comparing our proposed dynamic approach with a static one, we record a minimum of 6.7% decrease in flow latency for IFECS and 56.03% decrease for computation offloading.