A cooperative online learning scheme for resource allocation in 5G systems

Abstract

CitationAlQerm I, Shihada B (2016) A cooperative online learning scheme for resource allocation in 5G systems.Abstract-The demand on mobile Internet related services has increased the need for higher bandwidth in cellular networks. The 5G technology is envisioned as a solution to satisfy this demand as it provides high data rates and scalable bandwidth. The multi-tier heterogeneous structure of 5G with dense base station deployment, relays, and device-to-device (D2D) communications intends to serve users with different QoS requirements. However, the multi-tier structure causes severe interference among the multi-tier users which further complicates the resource allocation problem. In this paper, we propose a cooperative scheme to tackle the interference problem, including both cross-tier interference that affects macro users from other tiers and co-tier interference, which is among users belong to the same tier. The scheme employs an online learning algorithm for efficient spectrum allocation with power and modulation adaptation capability. Our evaluation results show that our online scheme outperforms others and achieves significant improvements in throughput, spectral efficiency, fairness, and outage ratio.

Sophisticated Online Learning Scheme for Green Resource Allocation in 5G Heterogeneous Cloud Radio Access Networks

“…Result: RB and P k s,n allocation for RUE initialization of Learning for each(x, y ∈ Y ) do initialize resource allocation strategy π t (x, y); initialize approximated Q-value ξ t ψ T (x, y); end while (true) do evaluate the state x = x t Select action y according to π t (x, y) in (20); if (C1 to C7 are satisfied ) then R(x, y) is achieved else R(x, y) = 0 end Update ξ t+1 i ψ T (x, y) according to (19) Update π t+1 i (x, y) according to (20) x = x t+1 t = t + 1 end requirements for RUEs and MUEs as input to check the quality of the strategies selected and they are compared to the capacity achieved by different BSs. The algorithm selects action strategies according to (20). If the conditions C1 to C7 are satisfied, then, the reward is achieved.…”

“…If the conditions C1 to C7 are satisfied, then, the reward is achieved. Finally, the Q-value and resource allocation strategy are updated according to (19) and (20) respectively, and the new state is observed.…”

“…Data: π t (x, y), t = 1, δ, θ * , θ, γ k s,n , γ k u,m and 1 ≤ µ ≤ F ≤ ν Result: RB, P k s,n allocation for RUEs initialization of Learning for each(x, y ∈ Y ) do initialize resource allocation strategy π t (x, y); initialize approximated Q-value ξ t ψ T (x, y); end while (true) do evaluate the state x = x t if (t < ν + 1) then Select action y according to π t (x, y) in (20); if (C1 to C7 are satisfied ) then R(x, y) is achieved else R(x, y) = 0 end else Update Yu(x t ) = {y|Rc(x, y) = 1} for x t Randomly select YF (XF (x t , F (t))) out of F joint actions associated with XF (x t , F (t))…”

“…Calculate R c (x, yj) according to (33) and populate Y u (x t ) if (C8 and C9 hold) then select the action from YF (XF (x t , F (t))) Yu(x t ) else select an action from Y u (x t ) end end Update ξ t+1 i ψ T (x, y) according to (19) Update π t+1 i (x, y) according to (20) x = x t+1 t = t + 1 end Note that µ and ν are two integers that satisfy 1 ≤ µ ≤ F ≤ ν. The algorithm states that when t < ν + 1, the resource allocation process according to the probability in (20) is engaged to determine the resource allocation strategy.…”

“…The authors in [19] explore a system framework of cooperative green heterogeneous networks for 5G wireless communication systems. A joint efficient resource allocation was proposed in [20]. To realize the 5G vision, Heterogeneous networks with massive densification of small cells and CRANs are combined in one network structure called heterogeneous cloud radio access networks (H-CRANs) to improve spectral efficiency, resource management, and energy efficiency [21] [22].…”