• Skip to primary navigation
  • Skip to main content
Carbon60

Carbon60

The Managed Cloud Difference

  • Show Search
  • Contact Us
  • Get Started
Hide Search
  • Cloud Adoption
    Cloud Adoption

    Starting or continuing on your cloud journey — whether public, private or hybrid — is a complex undertaking. But no matter your company size or industry, our cloud consulting experts can help with end-to-end solutions to plan, migrate and operate your business in the cloud.

    • Cloud Readiness Assessment

      Chart a new course for your IT environment with a Cloud Readiness Assessment. With a proven process, we take into consideration your technology, people and business strategy and tailor a public, private or hybrid cloud environment that will set your organization up for success.

      Learn more
    • Cloud Migration Services

      Cloud migration can transform your business and give you a competitive edge – when done properly. Our cloud experts will help you move complex workloads to the right cloud environment, the right way – tailored for your specific needs.

      Learn more
    • Cloud Launchpad
    • Modernization
    • Cloud Security & Compliance
  • Managed Cloud
    Managed Cloud

    Get the most out of the cloud and keep your IT team out of the weeds. Gain predictability and control around security, compliance, agility, reliability, performance – and cost – by tapping into our standard-setting managed cloud services.

    • Managed Private Cloud

      Safe, stable, fast, compliant, secure and fully managed – get a reliable and data sovereign cloud infrastructure platform for your applications.

      Learn more
    • Managed Public Cloud

      Experience matters. Whether you choose Managed AWS, Azure or Google Cloud, we can take care of the heavy lifting while you focus on your business.

      Learn more
    • Cloud Backup
    • Cloud Disaster Recovery
    • Security
    • Managed Public Cloud
    • Cloud Disaster Recovery
    • Applications
  • Industries
    Industries

    When it comes to financial services, healthcare, public sector and technology – there is simply no room for error or uncertainty when it comes to data security and compliance. There are specific and important considerations that we are well-versed in navigating. We’re trusted by governments and organizations to safely house mission-critical functions every day.

    • Financial Services

      Increase go-to-market speed, while meeting SOC2, PCI-DSS and OSFI B10 regulatory and organizational obligations.

      Learn more
    • Healthcare

      Get secure, scalable high-performance data, while improving the patient experience and addressing every compliance and privacy requirement.

      Learn more
    • Public Sector
    • Technology
  • Partners
    Partners

    Simply put – the right technology and the right platform is the one that’s right for your business. We’re highly certified and experienced in the major public clouds – so regardless of complexity, customization or preference – we’re well-equipped to have your back every step of the way.

    • AWS

      AWS Premier Partner with 100+ AWS certifications and counting.

      Learn more
    • Microsoft Azure

      Gold Microsoft Azure Partner with core competencies and certifications.

      Learn more
    • Google Cloud
    • VMware
  • Insights
    Insights

    Sharing knowledge and expertise is a big part of how we’ve evolved - and how we help our customers.

    • Blog

      Stay up to date with the latest trends and developments in the fast-moving world of digital transformation.

      Read
    • Events

      Make sure to join us for our next event and connect with cloud experts who have a lot to share.

      Attend
    • Resources

      Your toolkit to do a deeper dive with case studies, info sheets, checklists and more.

      Explore
  • About
    About

    We’re on a mission to bring digital transformation to more businesses, by making forward-thinking cloud strategy – and high-performance cloud services – more accessible.

    • Leadership

      Meet the leadership team who are driving our vision forward.

      Learn more
    • About Carbon60

      Learn more about who we are, and how we help our customers evolve with confidence.

      Learn more
    • Careers
    • News
  • Contact Us
  • Get Started

Automated Anomaly Detection and Optimization in Cloud Computing

February 8, 2012

There is an evolution happening in how organizations of all shapes and sizes consume business services.  More and more, business services are being consumed from either public or private “clouds”.  But as Kirill Sheynkman points out in “21 Experts Define Cloud Computing”:

“The ‘cloud’ model initially has focused on making the hardware layer consumable as on-demand compute and storage capacity. This is an important first step, but for companies to harness the power of the cloud, complete application infrastructure needs to be easily configured, deployed, dynamically-scaled and managed in these virtualized hardware environments.”

In other words, there is a big difference between an application that runs on a cloud and an application that is actually “cloud aware” and can take advantage of the dynamic environment in which it exists.  The challenge is that to be “cloud aware” an application must be able to scale well not just vertically but horizontally.  This adds a whole new level of complexity because the application now has to take into account cloud computing infrastructure elements, such as cache, storage, network, bus, management, cost, etc.

Automated horizontal scaling of applications in a cloud computing environment is a complex problem.  One fundamental road block is the inability of current monitoring/management systems to adequately capture the current state and predict the future state of an application and the cloud computing infrastructure in which it is running.  Both are fundamental to automating the horizontal scaling of applications in the cloud.  Today’s monitoring/management tools generally rely on experts to configure thresholds manually on single data streams and then trigger an alert or workflow if the threshold is exceeded.  This approach is woefully inadequate for managing large, dynamic systems, such as cloud computing applications and infrastructures.  This has been widely recognized and the source of numerous academic efforts, including IBM Research’s autonomic computing initiative.

Attempts to overcome this roadblock and create an adequate picture of the current and likely future state of a cloud and thereby allow intelligent self-management have focused on advanced anomaly and machine learning techniques.  Both techniques are important fields of research and have been treated within diverse areas.  A lot of theoretical work has been done and there are many available components such as high performance message buses, real time data correlation engines, and efficient machine learning algorithms which can be leveraged to create functional solutions. Commercially, these components have already found themselves applied to advanced financial and medical analysis solutions.

One commercial product that stands out in the market as potential solution for automating the horizontal scaling of cloud applications is VMWare’s vSphere Distributed Resource Scheduler (DRS).  VMWare claims that DRS can, on a continuous basis, “intelligently allocate available (cloud) resources among virtual machines according to business needs.”  It does this by pre-defined resource allocation rules, predictive usage algorithms, continuous monitoring of physical and virtual machine resource usage, and the triggering of automated administrative workflows.  Although DRS is arguably the most sophisticated cloud optimization solution on the market today, its scope is very limited: 1) DRS is a VMware-only tool; 2) its purpose is to optimize the placement of VMs on a cluster and not optimize application performance; 3) it is not Service Level Objective (SLO) aware; 4) its workload optimization logic considers only CPU and RAM utilization metrics and not I/O or network latency which are critical to application-level performance.  Each of these limitations rule out DRS as a tool for creating truly “cloud aware” applications capable of intelligently scaling horizontally and, thereby, of taking advantage of the one of the key benefits of cloud computing.

To begin to apply anomaly detection and machine learning techniques and systems in the context of creating “cloud aware” applications, we suggest the following basic design principles/requirements:

The solution:

  • Must automate the optimal horizontal scaling of stateless and stateful cloud applications in reference to pre-defined SLOs and other standard affinity, availability, and costing rules
  • Must be able to detect, log and alert on anomalous patterns across multiple, real time, multivariate data streams.
  • Must be (as much as possible) application and cloud agnostic.
  • Must be able to respond quickly to workload spikes and scale back more slowly.
  • Should use a modular control framework based on Model-Predict-Control (MPC) principles that uses a model of the system and its current state to compute the (near) optimal sequence of actions of the system that maintain the desired constraints using short timelines and an iterative methodology.
  • Reference signals to the control framework should be based on multi-dimensional workload calculations, including: CPU utilization, RAM utilization, I/O latency, and network latency.  Should be able to add additional factors.
  • The control framework should use Machine Learning (ML) algorithms to automate system modeling to a) predict probability of an action will achieve desired SLOs and identify complex patterns.
  • The control framework should have a loose-coupled event-driven architecture where all main modules are publishers or subscribers to a high performance message bus/event broker.
  • The control framework should use a high performance Complex Event Processing (CEP) engine to aggregate and normalize multiple, real-time data streams

The Carbon60 Blog anomaly detection, cloud aware, cloud computing

Related posts

Availability and Performance Monitoring: A Cloud Hosting Primer

January 31, 2012

Accelerating Web Sites and Applications: a Cloud Caching Primer

January 31, 2012

Navigating Private, Public and Hybrid Cloud Hosting

July 20, 2016

Subscribe to receive Carbon60 news

Stay up to date on insights, blog articles, events and services from Carbon60 delivered to your inbox.

Subscribe
Carbon60
  • Cloud Adoption
    • Cloud Readiness Assessment
    • Cloud Migration Services
    • Cloud Launchpad
    • Modernization
    • Cloud Security & Compliance
  • Managed Cloud
    • Managed Private Cloud
    • Managed Public Cloud
    • Cloud Backup
    • Cloud Disaster Recovery
    • Security
    • Applications
  • Industries
    • Financial Services
    • Healthcare
    • Public Sector
    • Technology
Follow us on LinkedIn Follow us on Twitter Follow us on YouTube

© Copyright Carbon60 2023

  • Privacy Policy
  • Terms & Conditions
  • Contact Us