Abstract: An information handling system stores a multiple machine learning (ML) models. The system receives a job request that includes input parameters and constraints for a job associated with the job request. Based on the input parameters and the constraints, the system identifies first and second ML models available to execute the job. The system also generates a first score for the first ML model and a second score for the second ML model. Based on the first score being greater than the second score, the system provides the job to a compute resource associated with the first ML model.

Abstract: An information handling system launches an installer of a software package at an information handling system and the software package includes an artificial intelligence model plugin and a dependency. The information handling system also determines whether the artificial intelligence model plugin can be executed on the information handling system. In addition, the information handling system installs the artificial intelligence model plugin in response to a determination that the artificial intelligence model plugin can be executed on the information handling system. Further, the information handling system loads the artificial intelligence model plugin and the dependency in an isolated load environment of a model management framework at runtime.

Abstract: In auto-configuration of dense mesh networks an Information Handling System (IHS) runs an advertisement service when the IHS is powered on and transmits a wireless local area network beacon information element that includes wireless node IHS specific information. The IHS dynamically scales transmit power of advertisement packets, from a low power. In response to the IHS finding a cluster host, the IHS accepts configuration of the IHS with an identification for a cluster of the cluster host and a frequency channel within the cluster. In response to the IHS not finding a cluster host, the IHS identifies as a new (cluster) host IHS and defines an identification for the new cluster. The cluster identification may be a Basic Secure Set (BSS) color field of the information element. Defining the identification for a cluster may use a distributed cluster policy, or may use a centralized managed cluster policy.

Abstract: Systems and methods described herein may provide a system that enables game play or other application sessions from a set of candidate game hosts and environments to consumption devices of a user's choice while the user moves about their home between the different environments. The system may employ methods to determine where a user is located within the home, availability and selection of candidate game hosting and target environments, homing and direction of related I/O and audio-visual (AV) content for consumption. The solution accommodates multiple users simultaneously within the home, whether in single player, multiplayer using the same screen, or multiplayer using separate screen games. The solution may configure AV and input/output (I/O) such that multiple users can consume one or multiple games in the home simultaneously, whether in separate locations or when seated together in front of the same consumption device.

Abstract: In auto-configuration of dense mesh networks an Information Handling System (IHS) runs an advertisement service when the IHS is powered on and transmits a wireless local area network beacon information element that includes wireless node IHS specific information. The IHS dynamically scales transmit power of advertisement packets, from a low power. In response to the IHS finding a cluster host, the IHS accepts configuration of the IHS with an identification for a cluster of the cluster host and a frequency channel within the cluster. In response to the IHS not finding a cluster host, the IHS identifies as a new (cluster) host IHS and defines an identification for the new cluster. The cluster identification may be a Basic Secure Set (BSS) color field of the information element. Defining the identification for a cluster may use a distributed cluster policy, or may use a centralized managed cluster policy.

Abstract: Implementing interference avoidance for high density ad hoc networks may include creating ad hoc Wireless Local Area Network (WLAN) clusters (WLAN pico-nets) of Information Handling Systems (IHSs) with nonoverlapping channels, enabling each IHS to have a high bandwidth wireless interface, and isolating nearby ad hoc WLAN clusters, using a Basic Secure Set (BSS) color field to associate IHSs within an ad hoc WLAN cluster (which may be preconfigured for each ad hoc WLAN cluster). Physical separation of ad hoc WLAN clusters may be optimized, minimizing cochannel interference, such as through use of dynamic threshold calculations. Nearby ad hoc WLAN clusters may be further isolated by dynamically adjusting transmit power control to isolate nearby ad hoc WLAN clusters, and/or by scaling channel width, such as through Dynamic Throughput Scalar calculations.

Abstract: Systems and methods described herein may provide a system that enables game play or other application sessions from a set of candidate game hosts and environments to consumption devices of a user's choice while the user moves about their home between the different environments. The system may employ methods to determine where a user is located within the home, availability and selection of candidate game hosting and target environments, homing and direction of related I/O and audio-visual (AV) content for consumption. The solution accommodates multiple users simultaneously within the home, whether in single player, multiplayer using the same screen, or multiplayer using separate screen games. The solution may configure AV and input/output (I/O) such that multiple users can consume one or multiple games in the home simultaneously, whether in separate locations or when seated together in front of the same consumption device.

Abstract: Systems and methods described herein may provide a system that enables the dynamic assignment of network resources between multiple workloads executing on a network. A computing device may receive workload information relating to a plurality of workloads executing within a network. The computing device may use the workload information to determine engagement and dependency predictions for the plurality of workloads and resource predictions for the plurality of workloads. Based on the workload information and the engagement and dependency predictions, the computing device may determine workload priority predictions for the plurality of workloads. The computing device may assign, based on the resource predictions and workload priority predictions, network resources of the network to the plurality of workloads.