Machine Learning For Virtual Machine Migration Plan Generation


Figure 1 depicts a flow diagram of a process for including parallelism when generating a virtual machine migration plan according to an embodiment. Exemplary embodiments relate to using machine learning for virtual machine (VM) migration plan generation. Embodiments can enforce both a colocation and an anti-colocation policy using colocation and anti-colocation contracts. A VM migration plan can be created by processing a first mapping of VMs to hosts along with a second mapping of VMs to hosts. Pre-processing can be performed followed by machine search techniques with heuristics and pruning mechanisms to generate serialized optimal paths from the first state (i.e., an origin state) to a second state (i.e., a goal state).

[slides] @KineticaDB Informercial: #FinTech Analytitcs @CloudExpo #AI #BI #DX #InsurTech


The financial services market is one of the most data-driven industries in the world, yet it's bogged down by legacy CPU technologies that simply can't keep up with the task of querying and visualizing billions of records. In his session at 20th Cloud Expo, Karthik Lalithraj, a Principal Solutions Architect at Kinetica, discussed how the advent of advanced in-database analytics on the GPU makes it possible to run sophisticated data science workloads on the same database that is housing the rich information needed to drive trading decisions. With the unique multi-core architecture of the GPU, financial computations can be processed efficiently and quickly, making it ideal for financial services streaming datasets. He shared how several financial institutions' quantitative science groups are specifically using GPUs to accelerate analytics, deep learning/machine learning, and converging AI and BI. With over 18 years of software experience in a variety of roles and responsibilities, he takes a holistic view at software architecture with special emphasis on helping enterprise IT organizations improve their service availability, application performance and scale.

[session] Making IoT Smart at the Edge @ThingsExpo @GreenwaveSys #AI #ML #IoT #M2M #Sensors


Because IoT devices are deployed in mission-critical environments more than ever before, it's increasingly imperative they be truly smart. In his session at @ThingsExpo, John Crupi, Vice President and Engineering System Architect at Greenwave Systems, will discuss how IoT artificial intelligence (AI) can be carried out via edge analytics and machine learning technologies that enable things to process event data at the source, learn patterns of behavior over time for taking independent action, and deliver more accurate results in real-time. This opens the door to limitless possibilities, enabling businesses to make better decisions with far less effort. Speaker Bio John Crupi is Vice President and Engineering System Architect at Greenwave Systems, where he guides development on the edge-based visual analytics and real-time pattern discovery environment AXON Predict. He has over 25 years of experience executing enterprise systems and advanced visual analytics solutions.