Octury deep sparkle 212/13/2022 ![]() ![]() The mobile elements need an efficient moving strategy to minimize the data-gathering latency and energy consumption while maximizing the rate of gathering data. Due to multi-hope connectivity and energy constraint, mobile elements are sent to the network to collect data from these sensor nodes directly by one hope communication. Since wireless sensor networks consist of a few to several sensor nodes which are spatially distributed, the data collection in the networks is a difficult task. ![]() Wireless sensor networks allow efficient data collection and transmission in IoT environments. The number of iterations can be reduced to more than 50%, which proves the feasibility and effectiveness of the method applied to cognitive electronic jamming decision-making. The results reveal that compared with the traditional Q-learning algorithm, the improved Q-learning algorithm proposed in this paper can fully explore and efficiently utilize and converge the results to a better solution at a faster speed. The simulation experiment takes a multifunctional radar as an example to analyze the influence of exploration strategy and learning rate on decision-making performance. Then, a cognitive electronic jamming decision-making model is constructed, and the improved Q-learning algorithm’s specific steps are given. At the same time, the idea of stochastic gradient descent with warm restarts (SGDR) is introduced to improve the learning rate of the algorithm, which reduces the oscillation and improves convergence speed at the later stage of the algorithm iteration. First, the method adopts the simulated annealing (SA) algorithm’s Metropolis criterion to enhance the exploration strategy, balancing the contradictory relationship between exploration and utilization in the algorithm to avoid falling into local optima. ![]() In this paper, a cognitive electronic jamming decision-making method based on improved Q-learning is proposed to improve the efficiency of radar jamming decision-making. ![]()
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |