Multi-Connectivity in 5G Terrestrial-Satellite Networks: the 5G-ALLSTAR solution

The 5G-ALLSTAR project is aimed at integrating Terrestrial and Satellite Networks for satisfying the highly challenging and demanding requirements of the 5G use cases. The integration of the two networks is a key feature to assure the service continuity in challenging communication situations (e.g., emergency cases, marine, railway, etc..) by avoiding service interruptions. The 5G NTN (Non-Terrestrial Network e.g., Satellite Network) would have a fundamental role in 5G [1], thanks to its characteristics exploited typically for live events broadcasting in large areas and for ultra-reliable and secure communications; The networks integration will have a great impact to the network performances. The 5G-ALLSTAR project proposes to develop Multi-Connectivity (MC) solutions in order to guarantee network reliability and improve the throughput and latency for each connection between User Equipment (UE) and network. In the 5GALLSTAR vision to easily integrate the terrestrial and satellite networks, allowing Fast Switching and User Plane Aggregation, we divide the gNB in two entities [3]: 1) gNB-CU (Centralized Unit) and 2) gNB-DU (Distributed Unit). Each gNB-CU controls a set of different gNB-DUs (see Figure 1-a). The gNB-CU integrates an innovative Traffic Flow Control algorithm able to optimize the network resources by coordinating the controlled gNB-DUs resources, while implementing MC solutions. The MC [2] permits to connect each UE (whether possible) with simultaneous multiple access points which can belong to both the same and different radio access technologies. The 5G-ALLSTAR solution for the MC deals with the possibility to have a common RRC and partial User Plane functionalities in the gNB-CU, i.e., SDAP and PDCP layers. This solution leads to have independent gNB-DU/s that contain the RLC, MAC and PHY layers. The communication between gNB-CU and the controlled gNB-DUs takes place by using the wellknown F1 interface [3]. As an example of integration between NTN and Terrestrial Networks we can consider the MC solution shown in Figure 1-b where the same packet (duplicated by the PDCP layer) are delivered independently to the two access points (gNB-DU-SAT and gNB-DU-5G) [4],[5],[6]. The 5G-ALLSTAR MC algorithms offer advanced functionalities to RRC layer [7] (in the gNB-CU) that is, in turn, able to set up the SDAP [8], the PDCP [9] and the lower layers in gNB-DU. In this regard, the AI-based MC algorithms, implemented in gNB-CU (also known as Cloud RAN), by considering the network performances in the UE surrounding environment as well as the UE QoS requirements, will dynamically select the most promising access points able to guarantee the fulfillment of the requirements (guarantying the required degree of throughput and latency) also enabling the optimal traffic splitting to cope with the connection reliability. In this paper, we present also an innovative AI-based framework, included within the Traffic Flow Control, able to address the MC objectives (as presented above), by implementing a Reinforcement Learning algorithm in charge of solving the network control problem.