To deal with the co-channel interference in Device-to-Device （D2D） communication-empowered cellular networks， the sum rate of D2D links was maximized through joint channel allocation and power control while satisfying the power constraints and the Quality-of-Service （QoS） requirements of cellular links. In order to efficiently solve the mixed-integer non-convex programming problem corresponding to the above resource allocation， the original problem was transformed into a Markov decision process， and a Deep Deterministic Policy Gradient （DDPG） algorithm-based mechanism was proposed. Through offline training， the mapping relationship from the channel state information to the optimal resource allocation policy was directly built up without solving any optimization problems， so it could be deployed in an online fashion. Simulation results show that compared with the exhausting search-based mechanism， the proposed mechanism reduces the computation time by 4 orders of magnitude （99.51%） at the cost of only 9.726% performance loss.

In the Unmanned Aerial Vehicle （UAV）-assisted and Non-Orthogonal Multiple Access （NOMA）-enabled data collection system， the total energy efficiency of all sensors is maximized by jointly optimizing the three-dimensional placement design of the UAVs and the power allocation of sensors under the ground-air probabilistic channel model and the quality-of-service requirements. To solve the original mixed-integer non-convex programming problem， an energy efficiency optimization mechanism was proposed based on convex optimization theory， deep learning theory and Harris Hawk Optimization （HHO） algorithm. Under any given three-dimensional placement of the UAVs， first， the power allocation sub-problem was equivalently transformed into a convex optimization problem. Then， based on the optimal power allocation strategy， the Deep Neural Network （DNN） was applied to construct the mapping from the positions of the sensors to the three-dimensional placement of the UAVs， and the HHO algorithm was further utilized to train the model parameters corresponding to the optimal mapping offline. The trained mechanism only involved several algebraic operations and needed to solve a single convex optimization problem. Simulation experimental results show that compared with the travesal search mechanism based on particle swarm optimization algorithm， the proposed mechanism reduces the average operation time by 5 orders of magnitude while sacrificing only about 4.73% total energy efficiency in the case of 12 sensors.