A Q-Learning Based Downlink Scheduling Algorithm for Multiple Traffics in 5G NR Systems

Author(s):  
Zhi-Qian Hong ◽  
Heru Susanto ◽  
Fang-Yie Leu
2021 ◽  
Vol 11 (20) ◽  
pp. 9360
Author(s):  
Kaibin Li ◽  
Zhiping Peng ◽  
Delong Cui ◽  
Qirui Li

Task scheduling is key to performance optimization and resource management in cloud computing systems. Because of its complexity, it has been defined as an NP problem. We introduce an online scheme to solve the problem of task scheduling under a dynamic load in the cloud environment. After analyzing the process, we propose a server level agreement constraint adaptive online task scheduling algorithm based on double deep Q-learning (SLA-DQTS) to reduce the makespan, cost, and average overdue time under the constraints of virtual machine (VM) resources and deadlines. In the algorithm, we prevent the change of the model input dimension with the number of VMs by taking the Gaussian distribution of related parameters as a part of the state space. Through the design of the reward function, the model can be optimized for different goals and task loads. We evaluate the performance of the algorithm by comparing it with three heuristic algorithms (Min-Min, random, and round robin) under different loads. The results show that the algorithm in this paper can achieve similar or better results than the comparison algorithms at a lower cost.


Long Term Evolution- Advanced (LTE-A) networks have been introduced in Third Generation Partnership Project (3GPP) release – 10 specifications, with an objective of obtaining a high data rate for the cell edge users, higher spectral efficiency and high Quality of service for multimedia services at the cell edge/Indoor areas. A Heterogeneous network (HetNet) in a LTE-A is a network consisting of high power macro-nodes and low power micro-nodes of different cell coverage capabilities. Due to this, non-desired signals acting as interference exist between the micro and macro nodes and their users. Interference is broadly classified as cross-tier and co-tier interference. The cross tier interference can be reduced by controlling the base station transmit power while the co-tier interference can be reduced by proper resource allocation among the users. Scheduling is the process of optimal allocation of resources to the users. For proper resource allocation, scheduling is done at the Main Base station (enodeB). Some LTE-A downlink scheduling algorithms are based on transmission channel quality feedback given by user equipment in uplink transmission. Various scheduling algorithms are being developed and evaluated using a network simulator. This paper presents the performance evaluation of the Adaptive Hybrid LTE-A Downlink scheduling algorithm. The evaluation is done in terms of parameters like user’s throughput (Peak, Average, and Edge), Average User’s spectral efficiency and Fairness Index. The evaluated results of the proposed algorithm is compared with the existing downlink scheduling algorithms such as Round Robin, Proportional Fair, Best Channel Quality Indicator (CQI) using a network simulator. The comparison results show the effectiveness of the proposed adaptive Hybrid Algorithm in improving the cell Edge user’s throughput as well the Fairness Index.


2014 ◽  
Vol 11 (01) ◽  
pp. 53-63 ◽  
Author(s):  
Mahnaz Sotoudeh Bahreyni ◽  
Vahid Sattari-naeini

Sign in / Sign up

Export Citation Format

Share Document