Periodic Reporting for period 1 - MAPNET (Mathematical Modelling and Optimization of Programmable 5G Networks) Reporting period: 2019-01-01 to 2020-12-31 Summary of the context and overall objectives of the project The exponential increase in mobile data traffic warrants disruptive changes in the design and management of cellular networks. The next generation (5G) networks target to support a variety of applications having diverse requirements in data rates, latency, energy, etc. To address this surge in traffic demand and the associated heterogeneity in service requirements, several candidate technologies are being investigated under the 5G vision, naming a few: 1) Ultra-dense network deployment for high spatial capacity; 2) Network slicing to support heterogeneous service requirements; and 3) Cloud radio access networks (CRAN), etc. An important element of the 5G vision is to achieve a 50% reduction in the total network energy consumption. To ensure that the future networks meet both the service and the sustainability requirements, energy-efficient designs and integration of renewable-energy sources into the network infrastructure are needed. To address the sudden capacity demands, on-demand network deployment is desired, instead of maintaining a permanently over-engineered infrastructure. Inclusion of these approaches result in highly complex and stochastic network topologies. Modeling and optimizing such networks is a challenging problem. The primary goal of MAPNET is to propose new modelling techniques for 5G-and-beyond networks mainly characterized by a very dense deployment and heterogeneous radio access technologies coupled with the requirements of energy- efficiency and the applications’ quality of service in terms of latency and data rates. The specific objectives are listed as follows:(i) Mathematical modelling of ultra-dense networks(ii )Energy-efficiency maximization of ultra-dense networks(iii) Network slicing reformulations to satisfy user demands Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far During MAPNET, research has been conducted along four main research axes:1. Deep reinforcement learning based optimization of ultra-dense Millimeter wave networksWe developed a DRL based framework for power and beamwidth allocation in ultra-dense mmWave deployment.2. Energy efficiency maximization of ultra-dense Millimeter wave networksEnergy efficiency is a very important metric for ultra-dense mmWave deployments catering for the high data-rate applications. To address this challenge, we defined a novel energy consumption analysis model of mmWave UDNs.3. Latency and energy Optimization of mobile edge/fog computing systems We considered a fog/edge computing aided drone communication system where latency and energy consumption optimizations are highly important. We formulated the joint minimization of both service latency and energy consumption as a bi-objective minimization problem. 4. Admission control in radio access network slicing systemsWe proposed strategies to avoid frequent switching behavior using the tool of game theory resulting in a more stable tenant behavior and increased profit for the MNOs. Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far) In MAPNET, the ER got opportunity to work on cutting edge topics in the area of wireless networks and attended many courses on hot-topic related to stochastic geometry, machine learning and artificial intelligence. During the overall stay at the host institute, ER acquired new scientific and transferable skills. The knowledge generated and contribution made towards energy-efficient wireless network will definitely have indirect impact economically and environmentally. Host CNRS Laboratory Logo
