ALBRL: Automatic Load-Balancing Architecture Based on Reinforcement Learning in Software-Defined Networking

Abstract

Due to the rapid development of network communication technology and the significant increase in network terminal equipment, the application of new network architecture software-defined networking (SDN) combined with reinforcement learning in network traffic scheduling has become an important focus of research. Because of network traffic transmission variability and complexity, the traditional reinforcement-learning algorithms in SDN face problems such as slow convergence rates and unbalanced loads. The problems seriously affect network performance, resulting in network link congestion and the low efficiency of inter-stream bandwidth allocation. This paper proposes an automatic load-balancing architecture based on reinforcement learning (ALBRL) in SDN. In this architecture, we design a load-balancing optimization model in high-load traffic scenarios and adapt the improved Deep Deterministic Policy Gradient (DDPG) algorithm to find a near-optimal path between network hosts. The proposed ALBRL uses the sampling method of updating the experience pool with the SumTree structure to improve the random extraction strategy of the empirical-playback mechanism in DDPG. It extracts a more meaningful experience for network updating with greater probability, which can effectively improve the convergence rate. The experiment results show that the proposed ALBRL has a faster training speed than existing reinforcement-learning algorithms and significantly improves network throughput.

Intelligent Bi-directional Relaying Communication for Edge Intelligence based Industrial IoT Networks

“…The effectiveness of TWRN was actually typically assessed in the literature [3,4]. Especially, outage opportunity was actually really analyzed in [5,6].…”

An Overview on Active Transmission Techniques for Wireless Scalable Networks

“…Computing force network deeply integrates computing and network, internally realizes computing endogenesis, externally provides computing services and reshapes the paradigm of the communication network [13][14][15]. The computing force network significantly improves the utilization of multi-dimensional resources such as communication, storage, and computing of the system through cloud, network and edge computing network collaboration, supports real-time and accurate computing power discovery, flexible dynamic scheduling of services, and ensures the consistency of user experience [16][17][18]. Wireless transmission is the basic means of computing power discovery and routing in a mobile computing network.…”

Energy-efficient and high-spectrum-efficiency wireless transmission

“…It has evolved from the narrow-band analog communication system in the 1980s to the advanced broadband digital communication system. The supported applications have also extended from pure voice communication to enhanced mobile broadband (EMBB), large scale machine type communications (MMTC) and ultra reliable and low latency communications (URLLC) [1][2][3][4]. Mobile communication has completely changed the world and has a profound impact on people's lives.…”

“…New services and new demands are the internal driving force for the evolution of communication technology. In the 6G era, the equipment access density will reach an astonishing 10 7 /km 2 , and the peak transmission rate will exceed 1Tbps [4]. Such massive equipment deployment and big data transmission will bring explosive growth in data traffic.…”