Resource allocation algorithm based on adaptive K nearest neighbor and deep learning in D2D communication
Aiming at the problem of poor communication service quality of Cell-Edge User(CEU)in high-density scenarios,a resource allocation algorithm based on adaptive K-nearest-neighbor and deep learning is proposed to maximize the sum rate of CEU by introducing D2D relaying technology.The algorithm first selects the communication mode of CEU based on adaptive K nearest neighbor algorithm,and proposes a cached content delivery scheme by combining the interference conditions.Then a deep neural network is used to construct a complex resource allocation neural network model for training and testing,in which the network inputs are reconstructed as channel gain matrices,and the transmit power is mapped to the network outputs for resource allocation.Finally,the simulation results show that the proposed algorithm improves the downlink sum rate by an average of 13.6%and 7.3%compared with the random algorithm and Q-learning algorithm,respectively,which effectively improves the communication quality of CEU and realizes higher data rates,under the premise of guaranteeing the quality of service of CEU.
万方数据
