‎an artificial intelligence framework for supporting coarse-grained workload classification in complex virtual environments

We propose cloud-based machine learning tools for enhanced big data applications, where the mainidea is that of predicting the next workload occurring against the target cloud infrastructure via an innovativeensemble-based approach that combines the eectiveness of dierent well-known classifiers in order to enhance thewhole accuracy of the final classification, which is very relevant at now in the specific context of big data. the so-called workload categorization problem plays a critical role in improving the eciency and reliability of cloud-basedbig data applications. implementation-wise, our method proposes deploying cloud entities that participate in thedistributed classification approach on top of virtual machines, which represent classical commodity settings forcloud-based big data applications. given a number of known reference workloads, and an unknown workload, inthis paper we deal with the problem of finding the reference workload which is most similar to the unknown one.the depicted scenario turns out to be useful in a plethora of modern information system applications. we namethis problem as coarse-grained workload classification, because, instead of characterizing the unknown workload interms of finer behaviors, such as cpu, memory, disk, or network intensive patterns, we classify the whole unknownworkload as one of the (possible) reference workloads. reference workloads represent a category of workloads thatare relevant in a given applicative environment. in particular, we focus our attention on the classification problemdescribed above in the special case represented by virtualized environments. today, virtual machines (vms) havebecome very popular because they oer important advantages to modern computing environments such as cloudcomputing or server farms. in virtualization frameworks, workload classification is very useful for accounting,security reasons, or user profiling. hence, our research makes more sense in such environments, and it turns outto be very useful in a special context like cloud computing, which is emerging now. in this respect, our approachconsists of running several machine learning-based classifiers of dierent workload models, and then deriving thebest classifier produced by the dempster-shafer fusion, in order to magnify the accuracy of the final classification.experimental assessment and analysis clearly confirm the benefits derived from our classification framework. therunning programs which produce unknown workloads to be classified are treated in a similar way. a fundamentalaspect of this paper concerns the successful use of data fusion in workload classification. dierent types of metricsare in fact fused together using the dempster-shafer theory of evidence combination, giving a classification accuracyof slightly less than 80%. the acquisition of data from the running process, the pre-processing algorithms, andthe workload classification are described in detail. various classical algorithms have been used for classification toclassify the workloads, and the results are compared.