Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Achieving Hiding and Smart Anti-Jamming Communication: A Parallel DRL Approach against Moving Reactive Jammer

Yangyang Li, Yuhua Xu, Wen Li, Guoxin Li, Zhibing Feng, Songyi Liu, Jiatao Du, Xinran Li

TL;DR

This work tackles anti-jamming under moving reactive jammers by jointly optimizing frequency agility and spread-spectrum parameters using a parallel DRL framework. By decomposing the action space into two parallel networks (frequency and spreading factor) atop a CNN backbone, the method mitigates the curse of dimensionality and accelerates convergence without relying on $ ext{ε}$-greedy exploration. The design enforces coordinated decisions through interconnected rewards and uses soft-target updates to stabilize learning, achieving about a 90% enhancement in normalized throughput relative to baselines. The approach demonstrates robustness across channel models and jamming patterns, offering a practical pathway for real-time anti-jamming in adversarial wireless environments.

Abstract

This paper addresses the challenge of anti-jamming in moving reactive jamming scenarios. The moving reactive jammer initiates high-power tracking jamming upon detecting any transmission activity, and when unable to detect a signal, resorts to indiscriminate jamming. This presents dual imperatives: maintaining hiding to avoid the jammer's detection and simultaneously evading indiscriminate jamming. Spread spectrum techniques effectively reduce transmitting power to elude detection but fall short in countering indiscriminate jamming. Conversely, changing communication frequencies can help evade indiscriminate jamming but makes the transmission vulnerable to tracking jamming without spread spectrum techniques to remain hidden. Current methodologies struggle with the complexity of simultaneously optimizing these two requirements due to the expansive joint action spaces and the dynamics of moving reactive jammers. To address these challenges, we propose a parallelized deep reinforcement learning (DRL) strategy. The approach includes a parallelized network architecture designed to decompose the action space. A parallel exploration-exploitation selection mechanism replaces the $\varepsilon $-greedy mechanism, accelerating convergence. Simulations demonstrate a nearly 90\% increase in normalized throughput.

Achieving Hiding and Smart Anti-Jamming Communication: A Parallel DRL Approach against Moving Reactive Jammer

TL;DR

This work tackles anti-jamming under moving reactive jammers by jointly optimizing frequency agility and spread-spectrum parameters using a parallel DRL framework. By decomposing the action space into two parallel networks (frequency and spreading factor) atop a CNN backbone, the method mitigates the curse of dimensionality and accelerates convergence without relying on -greedy exploration. The design enforces coordinated decisions through interconnected rewards and uses soft-target updates to stabilize learning, achieving about a 90% enhancement in normalized throughput relative to baselines. The approach demonstrates robustness across channel models and jamming patterns, offering a practical pathway for real-time anti-jamming in adversarial wireless environments.

Abstract

This paper addresses the challenge of anti-jamming in moving reactive jamming scenarios. The moving reactive jammer initiates high-power tracking jamming upon detecting any transmission activity, and when unable to detect a signal, resorts to indiscriminate jamming. This presents dual imperatives: maintaining hiding to avoid the jammer's detection and simultaneously evading indiscriminate jamming. Spread spectrum techniques effectively reduce transmitting power to elude detection but fall short in countering indiscriminate jamming. Conversely, changing communication frequencies can help evade indiscriminate jamming but makes the transmission vulnerable to tracking jamming without spread spectrum techniques to remain hidden. Current methodologies struggle with the complexity of simultaneously optimizing these two requirements due to the expansive joint action spaces and the dynamics of moving reactive jammers. To address these challenges, we propose a parallelized deep reinforcement learning (DRL) strategy. The approach includes a parallelized network architecture designed to decompose the action space. A parallel exploration-exploitation selection mechanism replaces the -greedy mechanism, accelerating convergence. Simulations demonstrate a nearly 90\% increase in normalized throughput.

Paper Structure

This paper contains 15 sections, 1 theorem, 26 equations, 14 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Works
  3. System Model and Problem Formulation
  4. System Model
  5. Problem Formulation
  6. The proof of the Markov Decision Process
  7. A Parallel DRL Exploration Free Anti-jamming Strategy
  8. Network Architecture, Input and Output
  9. Training Process
  10. Simulation Results
  11. Different scenarios for testing algorithm
  12. Details for Networks
  13. Performance Comparison
  14. Time Complexity
  15. Conclusion

Key Result

Theorem 1

In our case, if the set of actions $\mathbf{A}$ employed aligns with the set of optimal actions $\mathbf{A}^*$, and if a sufficiently large retrospective value $H$ can be recorded, then this process is considered a Markov Decision Process.

Figures (14)

  • Figure 1: System model.
  • Figure 2: The illustration of the algorithm steps.
  • Figure 3: Comparison of the designed mechanism and the $\varepsilon$-greedy mechanism.
  • Figure 4: The simultaneously update of our design.
  • Figure 5: The locations of transceivers and patrol route of jammer
  • ...and 9 more figures

Theorems & Definitions (1)

  • Theorem 1