International Business Machines Corporation

Kyndryl, Inc.

Stefan A G Van Der Stockt

Jason L Anderson

Jeffrey L Coveyduc

Aaron K Baughman

Michael Perlitz

Gregory J Boss

Brian M O'Connell

Andrew Douglas Hately

Approaches for optimizing network demand forecasting models and network topology using hyperparameter selection are provided. An approach includes defining a pool of features that are usable in models that predict demand of network resources, wherein the pool of features includes at least one historical forecasting feature and at least one event forecasting feature. The approach also includes generating, using a computer device, an optimal model using a subset of features selected from the pool of features. The approach further includes predicting future demand on a network using the optimal model. The approach additionally includes allocating resources in the network based on the predicted future demand.

Hyperparameter and network topology selection in network demand forecasting

Intelligent lighting is provided to motorists traveling down a stretch of road by sequentially turning on adjacent lighting devices in a lighting segment only when required, such as when vehicles are approaching the lighting devices, and turning off the lighting devices or decreasing a light intensity output of the lighting devices to a predefined minimum lighting intensity output level when no vehicles are present. In addition, which bulb to use in a multi-bulb lighting device is determined, as well as the optimal lighting intensity level of the selected bulb. Further, it is determined which lighting devices in a lighting segment may be turned off or dimmed while maintaining a predefined minimum safe light/brightness level along a pathway associated with the lighting segment.

Intelligent and coordinated lighting of a lighting device

Virtual machines are allocated among servers in a virtual environment, whereby each virtual machine has a current placement. A current fitness score is calculated for each virtual machine based on its current placement. Proposed placement plans are then generated, each plan including a proposed placement of each virtual machine. For each plan, a plan score is created. Each plan score is created by calculating a proposed fitness score for each virtual machine based on a proposed placement of that virtual machine in accordance with that plan, generating a virtual machine score for each virtual machine based on a comparison of that virtual machine's current fitness score and proposed fitness score, and then combining the virtual machine scores. The plan scores are then compared, and a target plan is selected from among the plans. The virtual machines are then reallocated among the servers in accordance with the target proposed placement plan.

Placing virtual machines in a virtual environment

A system, method and program product for selecting an algorithm and feature set to solve a problem. A perpetual analytics system is disclosed that provides a genetic algorithm for jointly selecting an algorithm and feature set to solve a problem, comprising: an evolutionary computing engine for processing data encoded as chromosomes, wherein each chromosome encodes an algorithm and a feature set; a domain knowledge store that maintains a plurality of algorithms and a plurality of features; a system for applying a generation of chromosomes to a set of data to provide a set of results; and a fitness function for evaluating the set of results to rate a performance of each chromosome in the set of chromosomes; wherein the evolutionary computing engine is adapted to evolve a subset of the set of chromosomes into a new generation of chromosomes.

Growing community of inventors

Johannesburg, South Africa

Stefan A G Van Der Stockt