Abstract: An approach for managing workload deployment in a distributed network, including edge computing is provided. The approach includes deploying several modules, such as, EMM (energy management module), LDM (localized deployment manager) and EDM (edge deployment manager). These modules will be constantly monitoring and managing the energy consumption at the edge nodes under their purview and communicate with other modules to develop a holistic energy management system (e.g., energy policies, energy algorithms, energy plans, etc.) to ensure the most effective energy management of workload is implemented.

Abstract: An action recommendation system uses reinforcement learning that provides a next action recommendation to a traffic controller to give to a vehicle pilot such as an aircraft pilot. The action recommendation system uses data of past human actions to create a reinforcement learning model and then uses the reinforcement learning model with current ABS-B data to provide the next action recommendation to the traffic controller. The action recommendation system may use an anisotropic reward function and may also include an expanding state space module that uses a non-uniform granularity of the state space.

Abstract: An approach for creating dynamic content. The approach receives advertiser data associated with activities of one or more advertisers and receives publisher data associated with activities of one or more publishers. The approach manages the one or more DSPs activities associated with the received advertiser data and publisher data. Furthermore, the approach manages the one or more SSPs activities associated with the received advertiser data, publisher data and the one or more DSPs activities and selects one or more advertisement for one or more website. Finally, the approach manages the one or more consumer behaviors associated with the selected one or more advertisement.

Abstract: An approach for creating dynamic content. The approach receives advertiser data associated with activities of one or more advertisers and receives publisher data associated with activities of one or more publishers. The approach manages the one or more DSPs activities associated with the received advertiser data and publisher data. Furthermore, the approach manages the one or more SSPs activities associated with the received advertiser data, publisher data and the one or more DSPs activities and selects one or more advertisement for one or more website. Finally, the approach manages the one or more consumer behaviors associated with the selected one or more advertisement.

Abstract: An action recommendation system uses reinforcement learning that provides a next action recommendation to a traffic controller to give to a vehicle pilot such as an aircraft pilot. The action recommendation system uses data of past human actions to create a reinforcement learning model and then uses the reinforcement learning model with current ABS-B data to provide the next action recommendation to the traffic controller. The action recommendation system may use an anisotropic reward function and may also include an expanding state space module that uses a non-uniform granularity of the state space.