Reinforcement learning based inter-radio access technology load balancing under multi-carrier dynamic spectrum sharing

An apparatus, comprising:

• at least one processor;
• and
• at least one memory comprising computer program code,
• the at least one memory and the computer program code are configured, with the at least one processor to cause the apparatus at least to
• send, to a reinforcement learning load balancer, a load metric related to available resources of a carrier, wherein the load metric comprises a historic load metric and a predicted future load metric;
• receive updated carrier assignment parameters, updated uplink/downlink split proportions, and updated resource pool split proportions, wherein the updated carrier assignment parameters are dependent upon the load metric, and signal-to-interference-plus-noise ratio, receive signal strength, and power headroom distributions;
• and
• apply the updated carrier assignment parameters, the updated uplink/downlink split proportions, and the updated resource pool split proportions to a communication network,
• wherein the updated carrier assignment parameters are determined by a multi-stage deep-Q-network, and
• wherein the updated uplink/downlink split proportions and the updated resource pool split proportions are determined by a deep neural network based on the updated carrier assignment parameters and the predicted impact.

A method, comprising:

• receiving, at a reinforcement learning load balancer, a load metric related to available resources of a carrier, wherein the load metric comprises a historic load metric and a predicted future load metric, and wherein the reinforcement load balancer comprises a plurality of stages;
• calculating, based on the load metric, an update to carrier assignment parameters for a user;
• calculating, based on the load metric and signal-to-interference-plus-noise ratio, receive signal strength, and power headroom distributions, an update to uplink/downlink split proportions and resource pool split proportions;
• predicting an impact of the update to the carrier assignment parameters, the update to the uplink/downlink split proportions, and the update to the resource pool split proportions to the load metric;
• communicating the update to carrier assignment parameters, the update to uplink/downlink split proportions, and the update to resource pool split proportions to one or more radio resource managers of corresponding one or more radio access technologies for application to a communication network;
• calculating a Q-function value, and
• based on the Q-function value, passing the updated carrier assignment parameters, the updated uplink/downlink split proportions, and the updated resource pool split proportions to a succeeding stage of the plurality of stages.