In this article, we investigate intelligent anti-jamming communication method for wireless sensor networks. The stochastic game framework is introduced to model and analyze the multi-user anti-jamming problem, and a joint multi-agent anti-jamming algorithm (JMAA) is proposed to obtain the optimal anti-jamming strategy. In intelligent multi-channel blocking jamming environment, the proposed JMAA adopts multi-agent reinforcement learning to make online channel selection, which can effectively tackle the external malicious jamming and avoid the internal mutual interference among sensor nodes. The simulation results show that, the proposed JMAA is superior to the frequency-hopping method, the sensing-based method and the independent reinforcement learning. Specifically, the proposed JMAA has the higher average packet receive ratio than both the frequency-hopping method and the sensing-based method. Compared with the independent reinforcement learning, JMAA has faster convergence rate when reaching the same performance of average packet receive ratio. In addition, since the JMAA does not need to model the jamming patterns, it can be widely used for combating other malicious jamming such as sweep jamming and probabilistic jamming.

The novel technology based on reinforcement learning (RL) is considered as a promising direction to achieve cognitive and even intelligent anti-jamming communication. However, traditional RL converges slowly in the face of huge state-action space, while the performance improvement of deep RL depends on high-cost computing resources. Under unknown and dynamic malicious jamming attacks, it is still a major challenge to realize online anti-jamming communication through fast and autonomous learning. In this paper, we propose a fast anti-jamming scheme based on intra-domain knowledge reuse for distributed wireless networks. First, we introduce the Bisimulation Relation to measure the similarity of different state-action pairs in the communication anti-jamming problem, so as to build a bridge of knowledge reuse between state-action pairs. This similarity stems from the fact that the anti-jamming problem can be divided into two categories according to whether it successfully resists jamming attacks, in which different state-action pairs in the same category have similarities. Then, through the real-time update and reuse of state-action values, each node can independently learn the characteristics of dynamic environment and adjust the transmission strategy quickly, so as to avoid external malicious jamming and internal mutual interference. The simulation results show that our proposed scheme significantly accelerates the convergence speed and improves the network normalized throughput compared with the benchmark against unknown and dynamic jamming, and has remarkable agility and jamming memory.

Pulse jamming is one of the common malicious jamming patterns that can significantly reduce the of wireless communication’s reliability. This paper investigates the problem of anti-jamming communication in a random pulse jamming environment. In order to obtain the countermeasure in time domain, the Markov decision process (MDP) is employed to model and analyze the above problem, and a time-domain anti-pulse jamming algorithm (TDAA) based on reinforcement learning is proposed. The proposed algorithm learns from the dynamic interaction with the jamming environment to gradually approximate the optimal time-domain strategy. The optimal strategy enables the transmitter to switch between two states, i.e. "active" and "silent", to avoid random pulse jamming. In addition, a state estimation and adjustment method for the random pulse jamming environment is introduced to improve the robustness of the proposed TDAA. Simulation results show that, compared with continuous transmission, the proposed TDAA can effectively reduce the jamming collision ratio and significantly improve the normalized throughput. And compared with transmitting terminal Q-learning algorithm (TTQA), the proposed TDAA has higher time utilization ratio and normalized throughput.

Herein, a comprehensive review of the evolution of intelligent communication anti‐jamming techniques is provided. First, a clear definition of the concept and elaboration on the inherent connotations and capability characteristics of intelligent communication anti‐jamming is provided. Additionally, the initial construction of an intelligent communication anti‐jamming system architecture is outlined. Subsequently, the development of intelligent communication anti‐jamming is delved, tracing its progression from early‐stage adaptive anti‐jamming techniques to the more recent advancements in intelligent anti‐jamming, which are primarily based on game theory and machine learning. Moreover, the latest research findings in this domain are thoroughly examined and the existing challenges and bottlenecks that hinder current research progress are highlighted. Finally, several viable research directions for future studies in the field of intelligent anti‐jamming are proposed. The objective is to facilitate readers in gaining a comprehensive understanding of the concept, characteristics, and system architecture of intelligent communication anti‐jamming. Additionally, it is aimed to provide a comprehensive overview of the developmental process and current state of research, thereby furnishing conceptual and theoretical support for the design of more effective and practical intelligent communication anti‐jamming systems.

The intelligent antijamming algorithm based on deep reinforcement learning (DRL) has become a prominent focus in communication antijamming research. However, while DRL aims to accurately fit complex behavioral strategies, communication antijamming prioritizes the speed of strategy fitting. To bridge this gap, we introduce a novel reinforcement learning (RL) antijamming algorithm called broad Q-network (BQN), which merges a specialized flattened neural network, broad learning system (BLS), with the RL framework. First, a new RL algorithm architecture is proposed based on the characteristics of BLS using ridge regression for network updates. Subsequently, an experience memory and training matrix construction mechanism is introduced for sample collection and utilization during the strategy update phase. Finally, a communication-sensing-decision parallel time slot structure is employed, addressing the issues of lagging sensing results and delayed reward computation. Simulation results demonstrate that under the environments of comb sweep jamming, nonlinear sweep jamming, and intelligent blocking jamming, our BQN's convergence speed is more than 10, 5, and 2.5 times faster than that of the most popular deep Q-network algorithm, respectively. Compared to mainstream DRL algorithms, such as dueling double deep Q-network, dropout Q-function, and proximal policy optimization, BQN also achieves faster acquisition of effective multidomain antijamming strategies, encompassing the frequency, power, and rate domains, in three dynamic jamming environments.

Aiming at efficiently establishing the optimal transmission path in a wireless communication network in a malicious jamming environment, this paper proposes an anti-jamming algorithm based on Dyna-Q. Based on previous observations of the environment, the algorithm selects the optimal sequential node by searching the Q table to reduce the packet loss rate. The algorithm can accelerate the updating of the Q table based on previous experience. The Q table converges to the optimal value quickly. This is beneficial for the optimal selection of subsequent nodes. Simulation results show that the proposed algorithm has the advantage of faster convergence speed compared with the model-free reinforcement learning algorithm.