|dc.description.abstract||Ever increasing user base of social media platforms such as Facebook, Youtube and the Over-the-Top platforms such as Netflix, Prime Video etc., has increased the demand for High Definition Videos/Contents over the Mobile Networks. This has triggered a new area of research named the Content Centric Networks (CCNs), where the designs of network are based on Contents and their features such as popularity, frequency of request, size of the content etc. Since, the social media and the OTT platforms are here to stay, the Next Generation wireless networks such as 5G, 6G etc. are inherently designed to be content centric.
We study the effect of different components of CCNs, such as Queueing, Caching, Scheduling, Power Control and Beamforming, on the content delivery performance. We propose several cross-layer designs that improve the Quality of Service (QoS) to the users. We present the study systematically in three parts.
In the first part of the thesis, we study the interplay between Queueing and Caching and the effect of fading in wireless CCNs. We consider a CCN with a server connected to several users over a shared finite capacity link. Each user is equipped with a cache. File requests at the users are generated as independent Poisson processes according to a popularity profile from a fixed finite library of files. The server has access to all the files in the library. Users can store parts of the files or full files from the library in their local caches. The server should send missing parts of the files requested by the users. The server attempts to fulfill the pending requests with minimal transmissions exploiting multicasting and coding opportunities among the pending requests. We consider a queue in which requests for the same file from different users are merged and transmitted simultaneously to all the requested users. We study and compare the performance of this novel queueing system in terms of queuing delays when Least Recently Used (LRU) caches are used and when coded caching schemes proposed in the literature are used. We provide approximate expressions for the mean queuing delay for these models and establish their accuracies via simulations. We extend the analysis to the case when transmission errors are also taken into account.
In the second part, we improve over the systems proposed in the first part and show that power control and adaptive scheduling can significantly improve the wireless CCNs performance under fading. We use deep reinforcement learning where we use function approximation of the Q-function via a deep neural network to obtain a power control policy that matches the optimal policy for a small network. We show that power control policy can be learnt for reasonably large systems via this approach. Further we use multi-timescale stochastic optimization to maintain the average power constraint. We demonstrate that a slight modification of the learning algorithm allows tracking of time varying system statistics. Finally, we extend the multi-time scale approach to simultaneously learn the optimal queueing strategy along with power control. We demonstrate scalability, tracking and cross-layer optimization capabilities of our algorithms via simulations. The proposed multi-time scale approach can be used in general large state-space dynamical systems with multiple objectives and constraints, and may be of independent interest.
In the third part, we study cross-layer designs for Multiuser, Multiple Input, Single Output (MU-MISO) CCNs which are proving to be indispensable in the next generation wireless networks such as 5G and 6G. Several recent studies have utilised redundancies in the content request along with the spatial diversity of a MISO system to improve the capacity of wireless networks. It is shown that Max-Min Fair (MMF) Beamforming schemes for MISO based on SDMA, NOMA, OMA and Rate-Splitting could be used to improve the content delivery rates. However, in most of these studies the key aspects such as the queueing delays in the downlink and the user dynamics have generally been ignored. In this work, we study how the interplay between queueing, beamforming and the user dynamics affects the Quality-of-Service (user experienced delay) of downlink in MU-MISO content centric networks (CCNs). We propose queueing theoretic models that are simple in nature and can be directly adapted to MU-MISO CCNs to perform optimal multi-group multicast downlink transmissions. We show that the Simple Multicast Queue (SMQ) developed in the first part for SISO systems can be directly used for MU-MISO systems and that it provides superior performance due to its always-stable nature. Further, we observe that MMF Beamforming schemes coupled with SMQ can be quite unfair to users with good channels. Thus, we propose an improvement to SMQ called Dual SMQ which addresses this issue. We also provide theoretical analysis of the mean delay experienced by the users in such MU-MISO CCNs.||en_US