Welcome to the InfoSci Platform
Reference Hub5
Deep Reinforcement Learning for Mobile Video Offloading in Heterogeneous Cellular Networks

Deep Reinforcement Learning for Mobile Video Offloading in Heterogeneous Cellular Networks

Nan Zhao, Chao Tian, Menglin Fan, Minghu Wu, Xiao He, Pengfei Fan
Copyright: © 2018 |Volume: 9 |Issue: 4 |Pages: 24
ISSN: 1937-9412|EISSN: 1937-9404|EISBN13: 9781522543312|DOI: 10.4018/IJMCMC.2018100103
Cite Article Cite Article

MLA

Zhao, Nan, et al. "Deep Reinforcement Learning for Mobile Video Offloading in Heterogeneous Cellular Networks." IJMCMC vol.9, no.4 2018: pp.34-57. http://doi.org/10.4018/IJMCMC.2018100103

APA

Zhao, N., Tian, C., Fan, M., Wu, M., He, X., & Fan, P. (2018). Deep Reinforcement Learning for Mobile Video Offloading in Heterogeneous Cellular Networks. International Journal of Mobile Computing and Multimedia Communications (IJMCMC), 9(4), 34-57. http://doi.org/10.4018/IJMCMC.2018100103

Chicago

Zhao, Nan, et al. "Deep Reinforcement Learning for Mobile Video Offloading in Heterogeneous Cellular Networks," International Journal of Mobile Computing and Multimedia Communications (IJMCMC) 9, no.4: 34-57. http://doi.org/10.4018/IJMCMC.2018100103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Heterogeneous cellular networks can balance mobile video loads and reduce cell arrangement costs, which is an important technology of future mobile video communication networks. Because of the characteristics of non-convexity of the mobile offloading problem, the design of the optimal strategy is an essential issue. For the sake of ensuring users' quality of service and the long-term overall network utility, this article proposes the distributive optimal method by means of multiple agent reinforcement learning in the downlink heterogeneous cellular networks. In addition, to solve the computational load issue generated by the large action space, deep reinforcement learning is introduced to gain the optimal policy. The learning policy can provide a near-optimal solution efficiently with a fast convergence speed. Simulation results show that the proposed approach is more efficient at improving the performance than the Q-learning method.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.