非正交多址接入系統(tǒng)中基于受限馬爾科夫決策過程的網(wǎng)絡切片虛擬資源分配算法
doi: 10.11999/JEIT180131
-
重慶郵電大學移動通信技術重點實驗室 ??重慶 ??400065
基金項目: 國家自然科學基金(61571073)
Network Slice Virtual Resource Allocation Algorithm Based on Constrained Markov Decision Process in Non-orthogonal Multiple Access
-
Key Laboratory of Mobile Communication Technology, Chongqing University of Post and Telecommunications, Chongqing 400065, China
Funds: The National Natural Science Foundation of China (61571073)
-
摘要: 針對無線接入網(wǎng)絡切片虛擬資源分配優(yōu)化問題，該文提出基于受限馬爾可夫決策過程(CMDP)的網(wǎng)絡切片自適應虛擬資源分配算法。首先，該算法在非正交多址接入(NOMA)系統(tǒng)中以用戶中斷概率和切片隊列積壓為約束，切片的總速率作為回報，運用受限馬爾可夫決策過程理論構建資源自適應問題的動態(tài)優(yōu)化模型；其次定義后決策狀態(tài)，規(guī)避最優(yōu)值函數(shù)中的期望運算；進一步地，針對馬爾科夫決策過程(MDP)的“維度災難”問題，基于近似動態(tài)規(guī)劃理論，定義關于分配行為的基函數(shù)，替代決策后狀態(tài)空間，減少計算維度；最后設計了一種自適應虛擬資源分配算法，通過與外部環(huán)境的不斷交互學習，動態(tài)調整資源分配策略，優(yōu)化切片性能。仿真結果表明，該算法可以較好地提高系統(tǒng)的性能，滿足切片的服務需求。
-
關鍵詞:
- 5G網(wǎng)絡切片 /
- 資源分配 /
- 受限馬爾可夫決策過程 /
- 非正交多址接入
Abstract: An adaptive virtual resource allocation algorithm is proposed based on Constrained Markov Decision Process (CMDP) for wireless access network slice virtual resource allocation. First of all, this algorithm in the Non-Orthogonal Multiple Access (NOMA) system, uses the user outage probability and the slice queues as constraints, uses the total rate of slices as a reward to build a resource adaptive problem using the CMDP theory. Secondly, the post-decision state is defined to avoid the expectation operation in the optimal value function. Furthermore, aiming at the problem of " dimensionality disaster” of MDP, based on the approximate dynamic programming theory, a basis function for the assignment behavior is designed to replace the post-decision state space and to reduce the computational dimension. Finally, an adaptive virtual resource allocation algorithm is designed to optimize the slicing performance. The simulation results show that the algorithm can improve the performance of the system and meet the service requirements of slicing. -
表 1 基函數(shù)定義
基函數(shù) 描述 $P_{ln }^m(t) + {\alpha _{ln}}(t)$ 切片l 功率分配粒度 ${N_{ln }}(t) + {\beta _{ln }}(t)$ 切片l 的子載波數(shù) ${(P_{ln }^m(t) + {\alpha _{ln }}(t))^2}$ 切片l 功率分配粒度平方 ${({N_{ln }}(t) + {\beta _{ln }}(t))^2}$ 切片l 的子載波數(shù)平方 $({N_{ln }}(t) + {\beta _{ln }}(t))(P_{ln }^m(t) + {\alpha _{ln }}(t))$ 切片l 中功率分配粒度與子載波數(shù)的乘積 
下載: 導出CSV
表 2 基于近似動態(tài)規(guī)劃的資源自適應算法
輸入： ${\chi _h}\left( {{S^a}\left( t \right)} \right)$：基函數(shù)； $\gamma $：折扣因子； 輸出： ${{η}}$：參數(shù)向量； ${\lambda _1}$, ${\lambda _2}$：拉格朗日因子； (1) while a new time period starts do (2) t← 0; ${{η}}$← 0; ${\lambda _1}$, ${\lambda _2}$← 0; //初始化 (3) for (t = 1; t <= T; t++) (4) while (5) while (6) 根據(jù)式(40)更新樣本函數(shù)值 (7) if t>0 then (8) 根據(jù)式(39)更新參數(shù)向量 ${{η}}$ (9) End if (10) 采樣外部隨機變量w(t+1)的樣本值 (11) 代入更新參數(shù)向量 ${{η}}$，根據(jù)式(35)更新決策后 狀態(tài)的近似函數(shù)值 (12) end while (13) 根據(jù)式(34)代入最優(yōu)策略行為計算目標函數(shù) (14) 根據(jù)式(32)和式(33)更新 ${\lambda _1}$, ${\lambda _2}$ (15) end while (16) end for (17) end while
下載: 導出CSV
表 3 系統(tǒng)仿真參數(shù)
仿真參數(shù) 仿真值 子載波數(shù) 64 基站發(fā)射功率 33 dBm 路徑損耗 133.6+35lg(d) 傳輸天線數(shù) 1 接收天線數(shù) 1 基站服務范圍 500 m 單個子載波疊加用戶數(shù) 1～4 (個) 分配行為：調整功率粒度 $\alpha = \{ {\rm{0}}{\rm{.25}},{\rm{0}}{\rm{.50}},{\rm{1.00}}\} $ 分配行為：調整子載波數(shù) $\beta {\rm{ = 1}}$ 切片1需求 (5 ms, 200 kbit/s) 切片2需求 (10 ms, 500 kbit/s) 切片3需求 (50 ms, 1 Mbit/s)
下載: 導出CSV
-
唐倫, 張亞, 梁榮, 等. 基于網(wǎng)絡切片的網(wǎng)絡效用最大化虛擬資源分配算法[J]. 電子與信息學報, 2017, 39(8): 1812–1818 doi: 10.11999/JEIT161322TANG Lun, ZHANG Ya, LIANG Rong, et al. Virtual resource allocation algorithm for network utility maximization based on network slicing[J]. Journal of Electronics&Information Technology, 2017, 39(8): 1812–1818 doi: 10.11999/JEIT161322 SALLENT O, PEREZ-ROMERO J, FERRUS R, et al. On radio access network slicing from a radio resource management perspective[J]. IEEE Wireless Communications, 2017, 24(5): 166–174 doi: 10.1109/MWC.2017.1600220WC PARSAEEFARD S, DAWADI R, DERAKHSHANI M, et al. Joint user-association and resource-allocation in virtualized wireless networks[J]. IEEE Access, 2016, 4: 2738–2750 doi: 10.1109/ACCESS.2016.2560218 BEGA D, GRAMAGLIA M, BANCHS A, et al. Optimising 5G infrastructure markets: The business of network slicing[C]. IEEE Conference on Computer Communications, Atlanta, USA, 2017: 1–9. AKPAKWU G A, SILVA B J, HANCKE G P, et al. A survey on 5G networks for the internet of things: Communication technologies and challenges[J]. IEEE Access, 2018, 6: 3619–3647 doi: 10.1109/ACCESS.2017.2779844 ZHANG Zihan, XIA Qinghong, YU Guanding, et al. Power control, user scheduling and resource allocation for downlink NOMA systems with imperfect channel state information[C]. 2017 9th International Conference on Wireless Communications and Signal Processing, Nanjing, China, 2017: 1–6. ZHU Jianyue, WANG Jiaheng, HUANG Yongming, et al. On optimal power allocation for downlink non-orthogonal multiple access systems[J]. IEEE Journal on Selected Areas in Communications, 2017, 35(12): 2744–2757 doi: 10.1109/JSAC.2017.2725618 FANG Fang, ZHANG Haijun, CHENG Julian, et al. Joint user scheduling and power allocation optimization for energy efficient NOMA systems with imperfect CSI[J]. IEEE Journal on Selected Areas in Communications, 2017, 35(12): 2874–2885 doi: 10.1109/JSAC.2017.2777672 DAWADI R, PARSAEEFARD S, DERAKHSHANI M, et al. Power-efficient resource allocation in NOMA virtualized wireless networks[C]. IEEE Global Communications Conference, Washington D.C., USA, 2016: 1–6. ZHANG Qi, ZHU Quanyan, ZHANI M F, et al. Dynamic service placement in geographically distributed clouds[C]. 2012 IEEE 32nd International Conference on Distributed Computing Systems, Macau, China, 2012: 526–535. ISLAM S M R, AVAZOV N, DOBRE O A, et al. Power-domain Non-Orthogonal Multiple Access (NOMA) in 5G systems: potentials and challenges[J]. IEEE Communications Surveys&Tutorials, 2017, 19(2): 721–742 doi: 10.1109/COMST.2016.2621116 CHEN Tianyi, MOKHTARI A, WANG Xin, et al. Stochastic averaging for constrained optimization with application to online resource allocation[J]. IEEE Transactions on Signal Processing, 2017, 65(12): 3078–3093 doi: 10.1109/TSP.2017.2679690 POWELL W B. Approximate Dynamic Programming: Solving the Curses of Dimensionality[M]. NJ, Princeton: Wiley, 2007: 129–144. FANG Fang, ZHANG Haijun, CHENG Julian, et al. Energy-efficient resource scheduling for NOMA systems with imperfect channel state information[C]. IEEE International Conference on Communications, Paris, France, 2017: 1–5. RAI R, ZHU H, and WANG Jiangzhou. Resource scheduling in Non-Orthogonal Multiple Access (NOMA) based cloud-RAN systems[C]. 2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON), New York City, USA, 2017: 418–422. -
圖(7) / 表(3)
計量
- 文章訪問數(shù): 1617
- HTML全文瀏覽量: 693
- PDF下載量: 44
- 被引次數(shù): 0
下載:
