In this paper, we propose a joint radio and core resource allocation framework for NFV-enabled networks. In the proposed system model, the goal is to maximize energy efficiency (EE), by guaranteeing end-to-end (E2E) quality of service (QoS) for different service types. To this end, we formulate an optimization problem in which power and spectrum resources are allocated in the radio part. In the core part, the chaining, placement, and scheduling of functions are performed to ensure the QoS of all users. This joint optimization problem is modeled as a Markov decision process (MDP), considering time-varying characteristics of the available resources and wireless channels. A soft actor-critic deep reinforcement learning (SAC-DRL) algorithm based on the maximum entropy framework is subsequently utilized to solve the above MDP. Numerical results reveal that the proposed joint approach based on SAC-DRL algorithm could significantly reduce energy consumption compared to the case in which R-RA and NFV-RA problems are optimized separately.

In this paper, we propose a new resource allocation framework for unmanned aerial vehicle (UAV) assisted multicast wireless networks in which the network users according to their request are divided into several multicast groups. We adopt power domain non-orthogonal multiple access (PD-NOMA) as the transmission technology using which the dedicated signals of multicast groups are superimposed and transmitted simultaneously as the UAV passes over the communication area for fixed and mobile users.We discuss the proposed scenarios from two perspectives, offline and online mode. In offline mode, we implement the problem for fixed and mobile users whose locations are predictable (the location of users, over the communication time, is known at the beginning of the communication time) and in online mode for mobile users whose locations are unpredictable (the location of users, over the communication time, is unknown at the beginning of the communication time). Also, we proposed a scenario in which the online model the number of mobile users can grow in each time slot. We formulate the problem of joint power allocation and UAV trajectory design as an optimization problem that is non-linear and nonconvex for two proposed scenarios. To solve the problem, we adopt an alternate search method (ASM), successive convex approximation (SCA), and geometric programming (GP). Using simulation results, the performance of the proposed scheme is evaluated for different values of the network parameters.