Abstract: The present application discloses a method and a device for user grouping and resource allocation in a NOMA-MEC system. The hybrid deep reinforcement learning algorithm proposed in the present application solves the hybrid problem of deep reinforcement learning that is difficult to deal with both discrete and continuous action spaces by using DDPG to optimize continuous actions and DQN to optimize discrete actions. Specifically, the algorithm determines a bandwidth allocation, an offloading decision, and a sub-channel allocation (user grouping) of the user device based on the user's channel state, in order to maximize the ratio of the computation rate to the consumed power of the system. The algorithm is well adapted to the dynamic characteristics of the environment and effectively improves the energy efficiency and spectrum resource utilization of the system.

Abstract: The present application discloses a method and a device for user grouping and resource allocation in a NOMA-MEC system. The hybrid deep reinforcement learning algorithm proposed in the present application solves the hybrid problem of deep reinforcement learning that is difficult to deal with both discrete and continuous action spaces by using DDPG to optimize continuous actions and DQN to optimize discrete actions. Specifically, the algorithm determines a bandwidth allocation, an offloading decision, and a sub-channel allocation (user grouping) of the user device based on the user's channel state, in order to maximize the ratio of the computation rate to the consumed power of the system. The algorithm is well adapted to the dynamic characteristics of the environment and effectively improves the energy efficiency and spectrum resource utilization of the system.

Abstract: There is provided a method that includes (a) receiving a unique identifier of a first entity, (b) constructing a family tree of entities that includes the first entity, (c) calculating a decision-making power score for each entity in the family tree in accordance with a rule, thus yielding decision-making power scores, (d) identifying a decision-making entity in the family tree, based on the decision-making power scores, thus yielding an identification of the decision-making entity, and (e) controlling a messaging system to direct a correspondence to a recipient, based on the identification of the decision-making entity. There is also provided a system that performs the method, and a storage device for storing instructions for a processor to perform the method.

Abstract: There is provided a method that includes (a) receiving a unique identifier of a first entity, (b) constructing a family tree of entities that includes the first entity, (c) calculating a decision-making power score for each entity in the family tree in accordance with a rule, thus yielding decision-making power scores, (d) identifying a decision-making entity in the family tree, based on the decision-making power scores, thus yielding an identification of the decision-making entity, and (e) controlling a messaging system to direct a correspondence to a recipient, based on the identification of the decision-making entity. There is also provided a system that performs the method, and a storage device for storing instructions for a processor to perform the method.