Abstract: We apply the techniques of deep reinforcement learning (RL) to the problem of coverage and capacity optimisation (CCO) in wireless networks. This is motivated by the idea that the type of combinatorial optimisation problems encountered in wireless networks are somewhat analogous to strategy games, for which deep RL has already proven to be an effective approach. We use a computer simulation of a small wireless network to generate synthetic data to train a deep Q network (DQN), and evaluate the performance of the DQN with further simulations. We compare the performance of the DQN with a conventional model-based approach. The results show that the DQN achieves slightly better performance than the conventional method, without the need for an explicit model of the environment. The performance is shown to be further improved by using the DQN within a search algorithm.

Abstract: Methods and a system are provided for enhanced long-term evolution scheduling. A ranking is constructed for one or more users scheduled on one or more resource blocks. A layer mapping is generated, using a finite modulation and coding scheme, utilizing the ranking of each of the one or more users for the one or more resource blocks. An enhanced ranking is determined, using a finite constraint on a buffer for each of the one or more users, for the one or more resource blocks utilizing the layer mapping. The enhanced ranking is deployed into a schedule for the one or more resource blocks being utilized by each of the one or more users. Bandwidth usage is optimized in the one or more resource blocks by utilizing the schedule.

Abstract: A method and transmitting device are provided for coordinated multi-point transmission scheduling by a transmitting device over one or more heterogeneous wireless networks that include a set of clusters. Each of the clusters has a set of transmission points for serving a set of user equipment devices. The method includes determining constraints imposed on any of the user equipment devices. The method further includes receiving channel state information feedback from the user equipment devices. The method also includes obtaining user weights and buffer sizes. The method additionally includes iteratively determining a weighted sum of user rates based on the constraints, the channel state information feedback, the user weights, and the buffer sizes. The iteratively determining step determines the weighted sum of user rates based on an initial weighted sum of user rates determined for the user equipment devices without the constraints.

Abstract: Methods and a system are provided for enhanced long-term evolution scheduling. A ranking is constructed for one or more users scheduled on one or more resource blocks. A layer mapping is generated, using a finite modulation and coding scheme, utilizing the ranking of each of the one or more users for the one or more resource blocks. An enhanced ranking is determined, using a finite constraint on a buffer for each of the one or more users, for the one or more resource blocks utilizing the layer mapping. The enhanced ranking is deployed into a schedule for the one or more resource blocks being utilized by each of the one or more users. Bandwidth usage is optimized in the one or more resource blocks by utilizing the schedule.

Abstract: A method and transmitting device are provided for coordinated multi-point transmission scheduling by a transmitting device over one or more heterogeneous wireless networks that include a set of clusters. Each of the clusters has a set of transmission points for serving a set of user equipment devices. The method includes determining constraints imposed on any of the user equipment devices. The method further includes receiving channel state information feedback from the user equipment devices. The method also includes obtaining user weights and buffer sizes. The method additionally includes iteratively determining a weighted sum of user rates based on the constraints, the channel state information feedback, the user weights, and the buffer sizes. The iteratively determining step determines the weighted sum of user rates based on an initial weighted sum of user rates determined for the user equipment devices without the constraints.