Adaptation of Frequency Hopping Interval for Radar Anti-Jamming Based on Reinforcement Learning

Ailiya,; Yi, Wei; Varshney, Pramod K.

doi:10.1109/tvt.2022.3197425

Cited by 30 publications

(11 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To simplify, we assume that the jammer could acquire a lot of frequency point information simultaneously within a PRI. In addition, regarding the problem of the interference and radar carrier frequency space being the same, we follow the literature [17] and assume that the enemy uses an electronic intelligence [31] system to obtain all of the available carrier frequencies of the radar. Overall, we assume that the jammer and the radar operate in the same frequency space, the jamming and radar pulses are synchronized in time, and the jammer is able to detect multiple radar frequencies within one PRI.…”

Section: The Model Of the Jammermentioning

confidence: 99%

“…Based on these results, we can see the advantages of LSTM in handling multi-layer historical observations. the Q-network structure consists of two FC layers, which is a common approach used in previous studies [16,17,19]. After stabilization, the PNI is 0.6, and the number of frequency hops is 44.…”

Section: The Performance Of Radar Adaptive Frequency Hoppingmentioning

confidence: 99%

“…However, in the time domain, the SINR does not exhibit such changes. The authors in [16,17] proposed the idea of designing reward functions based on signal power, ultimately achieving intelligent frequency hopping and efficient energy utilization using the adaptive frequency hopping (QFH) strategy. In [18], the authors redesigned the DQN network layers, replacing the Feed-Forward Neural (FFN) network with long shortterm memory (LSTM), resulting in significant improvements in adaptive frequency hopping for radar anti-jamming.…”

Section: Introductionmentioning

confidence: 99%

“…where n anti represents the number of successive times the radar has not been jammed; n keep represents the number of successive times the radar has used the current carrier frequency; and β 0 , β 1 , β 2 , and c are the hyperparameters. The interference judgment method is similar to the one outlined in the literature [17]. If the carrier frequency of the radar and the jammer collide, we judge that the radar has been interfered with.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Frequency Agile Anti-Interference Technology Based on Reinforcement Learning Using Long Short-Term Memory and Multi-Layer Historical Information Observation

Shi,

Guo,

Cong

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

In modern electronic warfare, radar intelligence has become increasingly crucial when dealing with complex interference environments. This paper combines radar agile frequency technology with reinforcement learning to achieve adaptive frequency hopping for radar anti-jamming. Unlike traditional reinforcement learning with Markov decision processes (MDPs), the interaction between radar and jammers occurs within the partially observable Markov decision processes (POMDPs). In this context, the partial observation information available to the agent does not strictly satisfy the Markov property. This paper uses multiple layers of historical observation information to solve this problem. Historical observations can be viewed as a time series, and time-sensitive networks are employed to extract the temporal information embedded within the observations. In addition, the reward function is optimized to facilitate the faster learning of the agent in the jammer sweep environment. This simulation shows that the optimization of the agent state, network structure, and reward function can effectively help the radar to resist jamming.

show abstract

Section: The Model Of the Jammermentioning

confidence: 99%

Section: The Performance Of Radar Adaptive Frequency Hoppingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Frequency Agile Anti-Interference Technology Based on Reinforcement Learning Using Long Short-Term Memory and Multi-Layer Historical Information Observation

Shi,

Guo,

Cong

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The development and maturity of RL-related theories have significantly enhanced radar situational awareness, autonomous learning, and decision-making capabilities [ 8 , 9 , 10 , 11 ]. Introducing RL into the radar antijamming field and optimizing radar antijamming strategies through collecting interaction information between radar and jammer can improve the intelligence of radar antijamming decision-making capability [ 12 , 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

AK-MADDPG-Based Antijamming Strategy Design Method for Frequency Agile Radar

Zhu,

Deng,

Dong

et al. 2024

Sensors

View full text Add to dashboard Cite

Frequency agility refers to the rapid variation of the carrier frequency of adjacent pulses, which is an effective radar active antijamming method against frequency spot jamming. Variation patterns of traditional pseudo-random frequency hopping methods are susceptible to analysis and decryption, rendering them ineffective against increasingly sophisticated jamming strategies. Although existing reinforcement learning-based methods can adaptively optimize frequency hopping strategies, they are limited in adapting to the diversity and dynamics of jamming strategies, resulting in poor performance in the face of complex unknown jamming strategies. This paper proposes an AK-MADDPG (Adaptive K-th order history-based Multi-Agent Deep Deterministic Policy Gradient) method for designing frequency hopping strategies in frequency agile radar. Signal pulses within a coherent processing interval are treated as agents, learning to optimize their hopping strategies in the case of unknown jamming strategies. Agents dynamically adjust their carrier frequencies to evade jamming and collaborate with others to enhance antijamming efficacy. This approach exploits cooperative relationships among the pulses, providing additional information for optimized frequency hopping strategies. In addition, an adaptive K-th order history method has been introduced into the algorithm to capture long-term dependencies in sequential data. Simulation results demonstrate the superior performance of the proposed method.

show abstract

Deep reinforcement learning based decision making for radar jamming suppression

Xiao,

Cao,

et al. 2024

Digital Signal Processing

View full text Add to dashboard Cite

Adaptation of Frequency Hopping Interval for Radar Anti-Jamming Based on Reinforcement Learning

Cited by 30 publications

References 34 publications

Frequency Agile Anti-Interference Technology Based on Reinforcement Learning Using Long Short-Term Memory and Multi-Layer Historical Information Observation

Frequency Agile Anti-Interference Technology Based on Reinforcement Learning Using Long Short-Term Memory and Multi-Layer Historical Information Observation

AK-MADDPG-Based Antijamming Strategy Design Method for Frequency Agile Radar

Deep reinforcement learning based decision making for radar jamming suppression

Contact Info

Product

Resources

About