International Business Machines Corporation

Saurav Basu

Ashish Verma

Yogish Sabharwal

Lloyd Alan Treinish

Jitendra Singh

Jayaram Kallapalayam Radhakrishnan

Vaibhav Saxena

Mukul Tewari

Sushain Pandit

Thomas George

Rashmi Mittal

Chandrasekar Radhakrishnan

In a method for intelligently executing predictive simulator, a processor may input a previous input vector of conditions for a predictive simulator collected at a first time into a machine-learning (ML) model. A processor may input a current input vector of conditions for the predictive simulator collected at a second time into the ML model. A processor may determine using the ML model, a binary similarity index. The binary similarity index represents a prediction of similarity between a first output from the predictive simulator based on the previous input and a second output from the predictive simulator based on the current input.

Intelligent execution of compute intensive numerical simulation models

One embodiment provides a method, including: receiving at least one deep learning job for scheduling and running on a distributed system comprising a plurality of nodes; receiving a batch size range indicating a minimum batch size and a maximum batch size that can be utilized for running the at least one deep learning job; determining a plurality of runtime estimations for running the at least one deep learning job; creating a list of optimal combinations of (i) batch sizes and (ii) numbers of the plurality of nodes for running both (a) the at least one deep learning job and (b) current deep learning jobs; and scheduling the at least one deep-learning job at the distributed system, responsive to identifying, by utilizing the list, that the distributed system has necessary processing resources for running both (iii) the at least one deep learning job and (iv) the current deep learning jobs.

Application aware resource allocation for deep learning job scheduling

Methods, systems, and computer program products for determining optimal compute resources for distributed batch based optimization applications are provided herein. A method includes obtaining a size of an input dataset, a size of a model, and a set of batch sizes corresponding to a job to be processed using a distributed computing system; computing, based at least in part on the set of batch sizes, one or more node counts corresponding to a number of nodes that can be used for processing said job; estimating, for each given one of the node counts, an execution time to process the job based on an average computation time for a batch of said input dataset and an average communication time for said batch of said input dataset; and selecting, based at least in part on said estimating, at least one of said node counts for processing the job.

Determining optimal compute resources for distributed batch based optimization applications

A computer-implemented method can include obtaining irrigation data. The method can further include obtaining a first set of watering rates. The method can further include generating a first set and a second set of soil moisture estimates. The first and second sets of soil moisture estimates can be based at least in part on the irrigation data. The method can further include obtaining a custom constraint and making a first determination that the first set of soil moisture estimates satisfies the custom constraint. The method can further include obtaining a moisture reference value in response to making the first determination. The moisture reference value can be based at least in part on the second set of soil moisture estimates. The method can further include making a second determination that the moisture reference value exceeds a first threshold, and generating an irrigation plan in response to making the second determination.

Irrigation planning system

Methods, systems, and computer program products for suggesting sensor placements are provided herein. A method includes simulating the concentration of a pollutant over an area covered by a sensor network grid by applying models to an emission inventory corresponding to the area; computing any discrepancy between the simulated concentration and historical data; applying scaling vectors to the first version to generate scaled versions of the emission inventory; re-simulating the concentration of the pollutant by applying the models to the scaled versions, and computing any discrepancy between the re-simulated concentrations and the historical data; identifying each scaling vector that corresponds with a discrepancy within a pre-determined range; applying the identified scaling vectors to an emission inventory value of each of the grid blocks to generate scaled emission inventory values; determining the grid blocks having high variability within scaled emission inventory values; and suggesting a sensor placement at the determined grid blocks.

Growing community of inventors

New Delhi, India

Saurav Basu