A Recurrent Neural Network Based Approach for Coordinating Radio and Computing Resources Allocation in Cloud-RAN

Abstract

Cloud Radio Access Network (Cloud-RAN) is a novel architecture that aims at centralizing the baseband processing of base stations. This architecture opens paths for joint, flexible, and optimal management of radio and computing resources. To increase the benefit from this architecture, efficient resource management algorithms need to be devised. In this paper, we consider a coordinated allocation of radio and computing resources to mobile users. Optimal resource allocation that respects the Hybrid-Automatic-Repeat-Request deadline may require formulating high-complexity and resourceheavy algorithms. We consider two Integer Linear Programming problems (ILP) that implement a coordinated allocation of radio and computing resources with the objectives of maximizing throughput and maximizing users' satisfaction, respectively. Since solving these highly-complex problems requires a high execution time, we investigate low-complexity alternatives based on machine learning models; more precisely on Recurrent Neural Networks (RNN). These RNN models aim to depict the performance of the ILP problems with a much lower execution time. Our simulation results demonstrate the great ability of RNN models to perform very closely to the ILP problems while being able to reduce the execution time by up to 99.65%.

Minimizing Energy Consumption by Joint Radio and Computing Resource Allocation in Cloud-Ran

“…Authors demonstrate a significant ability to decrease the amount of wasted transmission power. In the same context, and to reduce the complexity of the Integer Linear Programming (ILP)-based coordination algorithms, lower complexity Recurrent Neural Network (RNN)-based algorithms are developed in [15]. They are trained to perform close to the ILP solver.…”

Minimizing Power Consumption by Joint Radio and Computing Resource Allocation in Cloud-Ran

“…The considered schemes demonstrated a significant ability to decrease the amount of wasted transmission power. To reduce the complexity of the Integer Linear Programming (ILP)-based coordination algorithms, lower complexity Recurrent Neural Network (RNN)-based algorithms were developed in [10]. They were trained to perform close to the ILP solver and were shown to significantly reduce the execution time with respect to the ILP problems.…”

“…Equation (8) ensures users belonging to one base station cannot use the same RB and ensures that no more than one MCS can be used on this RB. The minimum throughput requirement of a user is ensured by (9), while the limit on the total transmission power of a user is imposed by (10). Equation (11) ensures that the signal power of a user on a RB is zero if this RB is not used.…”

Policy-Gradient-Based Reinforcement Learning for Computing Resources Allocation in O-RAN

“…For a given frame, the MCS index could be decreased and would lead to reduced throughput, but the computing scheduler would be able to allocate the required computing resources to process this frame. Knowing that solving an ILP problem is NP-Hard, [14] presents a Recurrent Neural Network Model that aims at performing as close as possible to the ILP model presented in [13] but with lower complexity.…”