Power and Frequency Selection optimization in Anti-Jamming Communication: A Deep Reinforcement Learning Approach

This paper studies the problem of anti-jamming in selecting communication frequency and power by using deep reinforcement learning (DRL) algorithm. In existing works, the anti-jamming methods are considered in frequency domain or power domain only. With the development of communication devices, more and more communication devices have the ability to switch communication frequency and adjust power simultaneously. To be specifically, the anti-jamming problem can be considered in both frequency and power domains. In this paper, we formulate the anti-jamming problem as a Markov decision process (MDP). And we use DRL algorithm to cope with the problem. The results of simulation show that the proposed algorithm achieves high throughput and with lower power.

[1]  Alagan Anpalagan,et al.  Anti-Jamming Communications Using Spectrum Waterfall: A Deep Reinforcement Learning Approach , 2017, IEEE Communications Letters.

[2]  Charalampos Konstantopoulos,et al.  A survey on jamming attacks and countermeasures in WSNs , 2009, IEEE Communications Surveys & Tutorials.

[3]  Bo Li,et al.  Optimal anti-jamming strategy in sensor networks , 2012, 2012 IEEE International Conference on Communications (ICC).

[4]  Léon Bottou,et al.  Stochastic Gradient Descent Tricks , 2012, Neural Networks: Tricks of the Trade.

[5]  Ying-Chang Liang,et al.  Applications of Deep Reinforcement Learning in Communications and Networking: A Survey , 2018, IEEE Communications Surveys & Tutorials.

[6]  Xin Liu,et al.  A heterogeneous information fusion deep reinforcement learning for intelligent frequency selection of HF communication , 2018, China Communications.

[7]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[8]  Tuomas Sandholm,et al.  Power napping with loud neighbors: optimal energy-constrained jamming and anti-jamming , 2014, WiSec '14.

[9]  Alvin S. Lim,et al.  Jamming and anti-jamming techniques in wireless networks: a survey , 2014, Int. J. Ad Hoc Ubiquitous Comput..

[10]  K. J. Ray Liu,et al.  Anti-Jamming Games in Multi-Channel Cognitive Radio Networks , 2012, IEEE Journal on Selected Areas in Communications.

[11]  Lajos Hanzo,et al.  A Survey on Wireless Security: Technical Challenges, Recent Advances, and Future Trends , 2015, Proceedings of the IEEE.

[12]  P. Dayan,et al.  Reward, Motivation, and Reinforcement Learning , 2002, Neuron.

[13]  Alagan Anpalagan,et al.  A Hierarchical Learning Solution for Anti-Jamming Stackelberg Game With Discrete Power Strategies , 2017, IEEE Wireless Communications Letters.

[14]  Jie Zhang,et al.  On the Performance of Deep Reinforcement Learning-Based Anti-Jamming Method Confronting Intelligent Jammer , 2019, Applied Sciences.