Anti-interference wireless communication method based on deep reinforcement learning

Abstract

The invention relates to a wireless communication technology, in particular to an anti-interference wireless communication method based on deep reinforcement learning. The method comprises the following steps: using two convolutional neural networks: one convolutional neural network calculates a value function, and the other convolutional neural network performs action selection based on a calculation result of the value function; adopting priority experience sampling in an experience playback stage, so that experience samples with higher priorities are sampled preferentially, updating parameters of the convolutional neural network based on the experience samples, and updating the priorities of all the experience samples through calculation of the updated convolutional neural network; adopting a forward action reservation strategy, designing a Gaussian-like function to judge the value of the current action, and dynamically adjusting and controlling the probability that the current action is continuously executed. According to the method, the optimal sending power and the optimal communication frequency band can be intelligently selected, the learning speed of the whole system is improved, and the optimal sending mode can be learned under the condition that a third-party attacker model is unknown.

Description

technical field [0001] The invention relates to wireless communication technology, in particular to an anti-jamming wireless communication method based on deep reinforcement learning. Background technique [0002] In wireless communication, the frequency band used by the sending device to send information to the receiving device is very vulnerable to third-party attacks, which greatly reduces communication efficiency. Among many attacks, blocking attack is the most important attack method. Jamming attackers attack multiple frequency bands at the same time with a certain power through frequency scanning and other methods. Since the frequency band under attack is unknown, the strategy of random frequency hopping to select the communication frequency band becomes very inefficient. Therefore, efficient intelligent frequency band selection technology becomes an urgent need. At the same time, most of the current sending devices use constant power to send signals, which will bec...

AI Technical Summary

Problems solved by technology

The disadvantages of this invention application are: 1), without knowing the specific frequency band attacked by the attacker, the communication efficiency of random frequency hopping technology cannot be guaranteed

2) The application for this invention is only applicable to communication scenarios where frequency hopping technology is used for frequency band selection, and channel adaptive selection of transmission power is not possible

The shortcoming that this scheme exists is: 1), it is difficult to regulate and optimize for the number n of extensions

The disadvantages of this solution are: 1) It is necessary to manually construct subsets of different frequency channels and transmission power combinations. Once the subset expands or the dimension increases, the amount of calculation will increase geometrically, making it difficult to apply to real-time communication applications; 2. ), the invention needs to iteratively calculate the metric value within the time range T, and the calculation process of the metric value is relatively complicated, and the running speed is very slow; 3), the invention uses a traditional reinforcement learning algorithm, which requires a large amount of memory for state value calculation Storage, when the dimension of the problem expands, the invention is difficult to implement

However, the frequency hopping method is difficult to select the optimal frequency band, and the traditional reinforcement learning method cannot quickly find the optimal strategy when the action set is large, and they can only be applied to the situation of constant attack

Images