Microsoft Technology Licensing, LLC

Srinivasan Iyengar

Ranveer Chandra

Shivkumar Kalyanaraman

Riyaz Pishori

Anirudh Badam

Weiwei Yang

Shadi Abdollahian Noghabi

Peeyush Kumar

Venkata N Padmanabhan

Upendra Singh

Lucien Werner

Anurag Ghosh

Anuj Rathore

Tanuja Hrishikesh Ganu

Asynchronously updating object detections within a video stream. A first set of objects associated a first frame include a first object detected by a first detection model. Object detection is initiated on a second frame by a second detection model. A second set of objects are identified as being associated with a third frame that is subsequent to the first frame in the video stream. The first object is included in the second set based on tracking the first object from the first frame to the third frame. A second object is identified within the second frame based on the second detection model. When the first object corresponds to the second object but has a different attribute, an attribute of the first object is updated. When the first object does not correspond to the second object, the second object is fast-tracked into the third frame.

Asynchronously updating object detections within a video stream

The techniques disclosed herein enable systems to enable multi-market optimization of renewable energies using data-driven models. To achieve this, a model retrieves a current state from a resource generation system and associated resource markets. The model can then compute a policy based on the state as well physical and technical constraints. The policy defines various actions that direct operation of the resource generation system such as resource production and dispatch to markets. Applying the policy to the resource generation results in a modified state which the model extracts along with a measure of optimality which quantifies the success of the policy. Based on these metrics, the model can generate an updated iteration of the policy defining a different set of actions. In this way, the model can gradually develop an optimal policy for controlling the resource generation system.

Multi-market resource dispatch optimization

A computer system that includes a plurality of compute clusters that are located at different geographical locations. Each compute cluster is powered by a local energy source at a geographical location of that compute cluster. Each local energy source has a pattern of energy supply that is variable over time based on an environmental factor. The computer system further includes a server system that executes a global scheduler that distributes virtual machines that perform compute tasks for server-executed software programs to the plurality of compute clusters of the distributed compute platform. To distribute virtual machines for a target server-executed software program, the global scheduler is configured to select a subset of compute clusters that have different complementary patterns of energy supply such that the subset of compute clusters aggregately provide a target compute resource availability for virtual machines for the target server-executed software program.

Distributed computing with variable energy source availability

Growing community of inventors

Bengaluru, India

Srinivasan Iyengar