Section: New Results

Wireless network deployment

Participants : Walid Bechkit, Amjed Belkhiri, Jad Oueis, Hervé Rivano, Razvan Stanica, Fabrice Valois

UAVs positionning

Mobile base stations mounted on unmanned aerial vehicles (UAVs) provide viable wireless coverage solutions in challenging landscapes and conditions, where cellular/WiFi infrastructure is unavailable. Operating multiple such airborne base stations, to ensure reliable user connectivity, demands intelligent control of UAV movements, as poor signal strength and user outage can be catastrophic to mission critical scenarios. In [17], we propose a deep reinforcement learning based solution to tackle the challenges of base stations mobility control. We design an Asynchronous Advantage Actor-Critic (A3C) algorithm that employs a custom reward function, which incorporates SINR and outage events information, and seeks to provide mobile user coverage with the highest possible signal quality. Preliminary results reveal that our solution converges after 4 × 10 5 steps of training, after which it outperforms a benchmark gradient-based alternative, as we attain 5dB higher median SINR during an entire test mission of 10,000 steps.

Network functions placement

Emerging mobile network architectures (e.g., aerial networks, disaster relief networks) are disrupting the classical careful planning and deployment of mobile networks by requiring specic self-deployment strategies. Such networks, referred to as self-deployable, are formed by interconnected rapidly deployable base stations that have no dedicated backhaul connection towards a traditional core network. Instead, an entity providing essential core network functionalities is co-located with one of the base stations. In [5], we tackle the problem of placing this core network entity within a self-deployable mobile network, i.e., we determine with which of the base stations it must be co-located. We propose a novel centrality metric, the ow centrality, which measures a node capacity of receiving the total amount of ows in the network. We show that in order to maximize the amount of exchanged trac between the base stations and the core network entity, under certain capacity and load distribution constraints, the latter should be co-located with the base station having the maximum ow centrality. We rst compare our proposed metric to other state of the art centralities. Then, we highlight the signicant trac loss occurring when the core network entity is not placed on the node with the maximum ow centrality, which could reach 55

Mobile edge computing orchestration

Orchestrating network and computing resources in Mobile Edge Computing (MEC) is an important item in the networking research agenda. In [12], we propose a novel algorithmic approach to solve the problem of dynamically assigning base stations to MEC facilities, while taking into consideration multiple time-periods, and computing load switching and access latency costs. In particular, leveraging on an existing state of the art on mobile data analytics, we propose a methodology to integrate arbitrary time-period aggregation methods into a network optimization framework. We notably apply simple consecutive time period aggregation and agglomerative hierarchical clustering. Even if the aggregation and optimization methods represent techniques which are different in nature, and whose aim is partially overlapping, we show that they can be integrated in an efficient way. By simulation on real mobile cellular datasets, we show that, thanks to the clustering, we can scale with the number of time-periods considered, that our approach largely outperforms the case without time-period aggregations in terms of MEC access latency, and at which extent the use of clustering and time aggregation affects computing time and solution quality.

On User Mobility in Dynamic Cloud Radio Access Networks

The development of virtualization techniques enables an architectural shift in mobile networks, where resource allocation, or even signal processing, become software functions hosted in a data center. The centralization of computing resources and the dynamic mapping between baseband processing units (BBUs) and remote antennas (RRHs) provide an increased flexibility to mobile operators, with important reductions of operational costs. Most research efforts on Cloud Radio Access Networks (CRAN) consider indeed an operator perspective and network-side performance indicators. The impact of such new paradigms on user experience has been instead overlooked. In [20], we shift the viewpoint, and show that the dynamic assignment of computing resources enabled by CRAN generates a new class of mobile terminal handover that can impair user quality of service. We then propose an algorithm that mitigates the problem, by optimizing the mapping between BBUs and RRHs on a time-varying graph representation of the system. Furthermore, we show that a practical online BBU-RRH mapping algorithm achieves results similar to an oracle-based scheme with perfect knowledge of future traffic demand. We test our algorithms with two large-scale real-world datasets, where the total number of handovers, compared with the current architectures, is reduced by more than 20%. Moreover, if a small tolerance to dropped calls is allowed, 30% less handovers can be obtained.

Wireless sensor network deployment for environmental monitoring

Air pollution has major negative effects on both human health and environment. Thus, air quality monitoring is a main issue in our days. In [9], we focus on the use of mobile WSN to generate high spatio-temporal resolution air quality maps. We address the sensors' online redeployment problem and we propose three redeployment models allowing to assess, with high precision, the air pollution concentrations. Unlike most of existing movement assisted deployment strategies based on network generic characteristics such as coverage and connectivity, our approaches take into account air pollution properties and dispersion models to offer an efficient air quality estimation. First, we introduce our proposition of an optimal integer linear program based on air pollution dispersion characteristics to minimize estimation errors. Then, we propose a local iterative integer linear programming model and a heuristic technique that offer a lower execution time with acceptable estimation quality. We evaluate our models in terms of execution time and estimation quality using a real data set of Lyon City in France. Finally, we compare our models' performances to existing generic redeployment strategies. Results show that our algorithms outperform the existing generic solutions while reducing the maximum estimation error up to 3 times.