Research Challenges of Autonomic ComputingIntroductionComplexity SolutionThe Purpose of The PaperObjectivesResearch FrameworkAutonomic ElementsAutonomic SystemsHuman InteractionSlide 10Autonomic Element ChallengesSpecific Autonomic ElementsElement InteroperationSlide 14Monitoring and AnalysisEvent CorrelationRule ExecutionOptimizationPlanningSlide 20Autonomic Element ArchitectureAutonomic Element Architecture (cont.)Autonomic Element Tools and PrototypesSlide 24Autonomic System ChallengesTechnologiesSystem Self-ConfigurationSystem Self-HealingSystem Self-OptimizationSystem Self-ProtectionSlide 31System ArchitectureSlide 33System ScienceSlide 35Interfacing with HumansPoliciesConclusionResearch Challenges of Autonomic ComputingAuthor: Jeffrey O. KephartPresented by: Djuradj Babich01/13/19Research Challenges of Autonomic Computing 2IntroductionCharacteristics of IT environments:ComplexHeterogeneous (hardware, middleware, software)Difficult to integrate, install, configure, tune, and maintainWithin few years, will become impossible to administer01/13/19Research Challenges of Autonomic Computing 3Complexity SolutionSystems comprised of self-managing components.Self: Configuring, Healing, Optimizing, ProtectingManaging done in accordance with high-level objectives specified by humans.01/13/19Research Challenges of Autonomic Computing 4The Purpose of The PaperIntroduce IBM’s Autonomic Computing Initiative (ACI).Decompose the grand challenge of autonomic computing into several of its constituent scientific and engineering challenges.Provide pointers to initial efforts to address these challenges.01/13/19Research Challenges of Autonomic Computing 5ObjectivesDescribe a research frameworkPresent a subset of challenges:•Autonomic Element Challenges•Autonomic System Challenges•Human-Computer ChallengesConclusion01/13/19Research Challenges of Autonomic Computing 6Research FrameworkHelpful in defining, describing, and growing IBM’s current autonomic computing research programResearch space divided into 3 parts:•Autonomic Elements•Autonomic Systems•Human-Computer Interactions01/13/19Research Challenges of Autonomic Computing 7Autonomic ElementsBasic building blocks of autonomic systemsTheir mutual interactions produce self-managing behavior of autonomic systems.Three sub-branches distinguished within:•Specific Autonomic Elements•Generic Autonomic Element Technologies•Generic Autonomic Element Architectures, Tools, and Prototypes.01/13/19Research Challenges of Autonomic Computing 8Autonomic SystemsComposed of autonomic elements Three sub-branches distinguished within:•Autonomic System Technologies•Autonomic System Architectures and Prototypes•Autonomic System Science01/13/19Research Challenges of Autonomic Computing 9Human InteractionManaging done in accordance with high-level objectives specified by humans.Two sub-branches distinguished within:•Human Studies•Policy01/13/19Research Challenges of Autonomic Computing 10ObjectivesDescribe a research frameworkPresent a subset of challenges:•Autonomic Element Challenges•Autonomic System Challenges•Human-Computer ChallengesConclusion01/13/19Research Challenges of Autonomic Computing 11Autonomic Element ChallengesSpecific Autonomic Elements•Improving the self-managing capability of specific componentsGeneric Autonomic Element Technologies•Applicable technologies (monitoring, forecasting, event correlation, rule execution, optimization, planning)Generic Autonomic Element Architectures, Tools, and Prototypes.•Internal structure, helpful tools, and implementations01/13/19Research Challenges of Autonomic Computing 12Specific Autonomic ElementsMore self-managing componentsEmphasis: servers, DBMS, storage systemsChallenges numerous, but well-understoodNew challenge introduced by IBM’s ACI:•Achieve effective interoperation by the autonomic elements01/13/19Research Challenges of Autonomic Computing 13Element InteroperationElements situated in autonomic systemsCooperative intercommunication and interaction between elements essentialRequirements:•Standard interface (system architecture)•Ability to generate and supply needed info to other components•Ability to request and use info from other components01/13/19Research Challenges of Autonomic Computing 14Autonomic Element ChallengesSpecific Autonomic Elements•Improving the self-managing capability of specific componentsGeneric Autonomic Element Technologies•Applicable technologies (monitoring, forecasting, event correlation, rule execution, optimization, planning)Generic Autonomic Element Architectures, Tools, and Prototypes.•Internal structure, helpful tools, and implementations01/13/19Research Challenges of Autonomic Computing 15Monitoring and AnalysisCommon methods for collecting and representing monitored data and log files.•Challenge: standardization•Solution effort: Common Base Event (OASIS Web Services Distributed Management Technical Committee)Rule and correlation engines for analyzing monitored data and log files.•Challenge: set of rules and/or correlation expressions for condition description•Complication: correlation across multiple components•Solution effort: modeling, machine learning01/13/19Research Challenges of Autonomic Computing 16Event CorrelationCorrelation extraction between low-level system measurements and high-level Service Level Objectives is based on modeling:•Map potential actions into probable outcomes•Forecast future demand and plan accordingly•Access models of other system componentsChallenges: •Learn and readjust the models continually on the fly.•Adjust quickly to observations with a minimum of data and training time.•Adapt to conditions that are noisy and prone to fluctuations.01/13/19Research Challenges of Autonomic Computing 17Rule ExecutionRule authoring should be based on some form of machine learning, based on system-level goals coupled with historical observationChallenges:•Random exploration•Several hundred tunable parameters•Learning process convergence01/13/19Research Challenges of Autonomic Computing 18OptimizationOptimization challenges overlap a good deal with those of learning.Challenge:•NonstationarityLandscape changes due to effects such as:•Changing workload•Adaptive behavior by other autonomic elements01/13/19Research Challenges of
View Full Document