A novel approach for radio resource management in multi-dimensional heterogeneous 5G networks

Abstract

Abstract:A GRA-BKP (Grey Relational Analysis-Bounded Knapsack Problem) scheme was proposed for the radio resource management of the 5G networks. It consists of two steps, access selection and admission control. The former step was executed via GRA, whereas the latter problem was formulated as a bounded knapsack problem. Accordingly, an optimal solution of the BKP was given for access selection a greedy algorithm, GRA-Greedy, was proposed for admission control. The simulation UHVXOWV VKRZ WKDW WKH *5$%.3 VFKHPH FDQ HIIHFWLYHO\ LQFUHDVH V\VWHP SUR¿W DQG GHFUHDVH WKH GURSSLQJ SUREDELOLW\ FRPSDUHG with the existing scheme. In addition, GRA-Greedy achieves comparable perform-ance with the optimal solution GRA-DP, but its computational complexity is much lower than that of the latter.

User-aware centralized resource allocation in heterogeneous networks

“…The problem consists in the selection of the most appropriate access network, with characteristics able to satisfy the 5G requirements, over which sending the traffic (traffic steering problem). Several approaches have been proposed to solve the problems of traffic steering and network selection, ranging from Multiple Attribute Decision Making (MADM) [15], [16] and fuzzy logic [17] to game theory, Markov Decision Processes (MDPs) [18] and Reinforcement Learning [19] applied also to other network resource allocation problems in the context of SDN and VNF [20], [21], [22].…”

Network Selection in 5G Networks Based on Markov Games and Friend-or-Foe Reinforcement Learning

“…A fundamental concept in RL is the trade-off between knowledge exploitation and environment exploration. The update of the tables (2) and the solution of the maximin problem (3) represent, respectively, the process of learning from experience, or knowledge acquiring, and its exploitation to derive a proper strategy for the player. To provide the players with an adequate degree of exploration, the action selection is subject to the following rule, known as -gready selection:…”

“…From a methodological point of view, several approaches were investigated in the literature for the network selection problem, spacing from solutions based on Multiple Attribute Decision Making (MADM) [2], [3], to Fuzzy Logic control systems [4], and Game Theory-based approaches [5], [6]. Additionally, Markov Decision Processes (MDPs) and Reinforcement Learning (RL) were tested, among the others, in [7] and [8].…”

Iterative MPC for Energy Management and Load Balancing in 5G Heterogeneous Networks

“…Several methodologies were studied in the field of multiconnectivity for resource management and traffic steering, such as Multiple Attribute Decision Making (MADM) [8], [9], Game Theory [10]- [12] and Reinforcement Learning [13]- [15]. Multi-Access Networks allow the "Always Best Connected" concept presented in [16], defined as the capability to provide to users with the best connection experience, exploiting several radio accesses characterized by heterogenous technologies.…”

“…( ) = 0, ∀ > 0 ( ) = 0 (8) ( 9) where ( 7) allows to take in consideration the measured values of the disturbances (8) specifies that the optimization is performed without taking in consideration future unknown values of the disturbances ( 9) specifies that at the end of the time horizon users' queues should be empty…”