{"id":17647,"date":"2020-02-05T11:00:09","date_gmt":"2020-02-05T19:00:09","guid":{"rendered":"https:\/\/www.palada.net\/index.php\/2020\/02\/05\/news-11382\/"},"modified":"2020-02-05T11:00:09","modified_gmt":"2020-02-05T19:00:09","slug":"news-11382","status":"publish","type":"post","link":"http:\/\/www.palada.net\/index.php\/2020\/02\/05\/news-11382\/","title":{"rendered":"The Way to Predictive Analytics: Creating Data Infrastructure"},"content":{"rendered":"

Credit to Author: Guest Blogger| Date: Tue, 04 Feb 2020 20:32:52 +0000<\/strong><\/p>\n

Paradoxically, data center management<\/a> to date hasn\u2019t really involved data. Maintenance is based on arbitrary schedules, viewed and performed piecemeal at the equipment level and involves human intervention, i.e. the introduction of error. In the data center market<\/a>, we\u2019ve reached the point when redundancy only leads to degradation. Understanding the failure point is elusive because failure doesn\u2019t actually happen. Getting to predictive analytics requires data infrastructure and a systemic approach.<\/p>\n

This is what Schneider Electric and Compass Datacenters<\/a> are working on. We\u2019re considering the data center as a whole \u2014 as a complex system \u2014 not as individual assets. Individual analytics are overwhelming, and they don\u2019t show cause and effect. Let\u2019s say the gear fails, for example. What then is the impact on the UPS? Or how does adjusting the ambient temperature impact the performance of the electrical infrastructure?<\/p>\n

In other words, what\u2019s the cascading effect of any failure? It\u2019s unknowable unless the entire system is considered. We\u2019re building asset models based on the domain expertise, but as a system. The collective data will drive predictability. We\u2019ll connect as many data points as possible, and this data infrastructure will enable accumulation of data to build rules-based models.<\/p>\n

\"data <\/p>\n

Data Infrastructure First<\/h2>\n

The current lack of data infrastructure means there\u2019s not enough data to build high performance machine learning. Yet, this is the precursor to AI. The AI conversation tends to get carried away. AI in data centers doesn\u2019t really exist at this stage. We have to work on the basics first to deliver advanced analytics.<\/p>\n

Creating data infrastructure starts with the cloud. Then comes instrumenting and ensuring the telemetry is in place for the data center to aggregate as much data as possible. Essentially, the result will be a registry of all the assets in one place. A consistent asset model across the system will deliver higher value analytics, and that will allow us to better control the context to gain insight.<\/p>\n

Security is always a question when it comes to data, especially when we\u2019re talking about more and more data. But we can\u2019t let it be an obstacle. Of course, Schneider Electric equipment has been thoroughly cyber-tested at the ground level. A larger focus for building a secure data infrastructure, however, should be around people and processes because the majority of vulnerability falls in these areas.<\/p>\n

The Redundancy Dilemma<\/h2>\n

Data centers<\/a> involve a large footprint of equipment that\u2019s often heavily redundant \u00ad\u2014 sometimes triple. That means it never really fails. As the business of data centers ages and continues to expand at the same time, redundancy will become an issue that only analytics can address. In theory, we\u2019re talking about the concept of failure modes and effects analysis (FMEA).<\/p>\n

This is an approach that\u2019s been used in aerospace for years. It basically looks at every component within the system and analyzes what impact it would have in a particular failure mode in the system and what the effect would be on the overall system.<\/p>\n

Only a couple of points in any given system are critical to failure. It\u2019s not that other parts aren\u2019t important, but some things can fail and not affect the overall system performance. This is a novel idea for data centers and exactly what we are doing now.<\/p>\n

In data center management, we need the ability to use live data from the data center to understand how individual assets are performing within a system. Then we\u2019ll re-rate and create a risk hierarchy within the system against the overall potential for failure.<\/p>\n

In most industrial analytic applications, there\u2019s room to fail, and you may never see it. All that\u2019s apparent is performance degradation. Redundancy obscures how the assets are performing underneath. Data will tell the full story and potentially reduce redundancy, and thereby, capex.<\/p>\n

The Benefits of Predictive Analytics<\/h2>\n

Beyond reducing upfront costs and longer-term investment, analytics will decrease failures and interventions too. They\u2019ll provide visibility and improve asset performance for higher uptime and longer meantime between failure. Ultimately, risk will be lower and the life cycle optimized when applying data driven asset management, i.e. predictive analytics.<\/p>\n

The broader goal is to replicate across multiple locations and geographies. The full value lies in comparing mission critical environments to each other to get benchmarking \u2013 that\u2019s the eventual goal. The larger the volume of data, the better we\u2019ll get at it.<\/p>\n

Learn more about Schneider\u2019s full portfolio of software and services solutions<\/a> for colocation providers.<\/p>\n

<\/em>Adil Attlassy, Compass Datacenters<\/strong><\/p>\n

Adil Attlassy serves as Compass\u2019 Chief Technical Officer. Mr. Attlassy is widely respected as a thought leader in IT infrastructure who has been at the forefront of data center trends over the past two decades. Prior to joining Compass, Adil served as the General Manager of Global Site and Network Acquisition for Microsoft. Before Microsoft, Mr. Attlassy held the position of Chief Development Officer for IO. In that role, he was directly responsible for global site selection and development, and he oversaw the company\u2019s data center procurement and supply chain engagement. Prior to IO, Adil held executive positions for Digital Realty Trust in the U.S., UK and Singapore. Mr. Attlassy holds a DUT from Institut de Technologie, Mulhouse, France, a BS in Mechanical Engineering from California State<\/p>\n

<\/p>\n

Wendi Runyon, Schneider Electric\u00a0<\/strong><\/p>\n

As Vice President of Strategy and Business Development, Wendi runs strategy and business development for Schneider Electric\u2019s Secure Power and Data Center business in North America. Her team is responsible for understanding the NAM market and competitive landscape, developing the strategy, bridging the gap between strategy and execution, and defining metrics of success. Additionally, her team runs the regional business development efforts that clearly defines strategy execution by strategic initiative, develops new routes to market, identifies offers gaps to execute strategy and then liaisons between execution teams and other Schneider Business Units or Lines of Business to drive collaboration and execution. Wendi holds an MBA degree from Emory University and a Bachelor of Science in Industrial Engineering from Pennsylvania State University. She currently sits on the Industrial & Professional Advisory Council (IPAC) Board for Penn State\u2019s College of Engineering as well as the Diversity & Inclusion NAM Employee Resource Group Board.<\/p>\n

<\/div>\n

The post The Way to Predictive Analytics: Creating Data Infrastructure<\/a> appeared first on Schneider Electric Blog<\/a>.<\/p>\n

http:\/\/blog.schneider-electric.com\/feed\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Credit to Author: Guest Blogger| Date: Tue, 04 Feb 2020 20:32:52 +0000<\/strong><\/p>\n

Paradoxically, data center management to date hasn\u2019t really involved data. Maintenance is based on arbitrary schedules, viewed and performed piecemeal at the equipment level and involves human intervention, i.e. the… Read more »<\/a><\/p>\n

The post The Way to Predictive Analytics: Creating Data Infrastructure<\/a> appeared first on Schneider Electric Blog<\/a>.<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"colormag_page_container_layout":"default_layout","colormag_page_sidebar_layout":"default_layout","footnotes":""},"categories":[12389,12388],"tags":[10245,12390,19426,12391,12403,19955,24138,12547],"class_list":["post-17647","post","type-post","status-publish","format-standard","hentry","category-scadaics","category-schneider","tag-ai","tag-colocation","tag-compass-datacenters","tag-data-center","tag-data-center-management","tag-data-center-market","tag-data-infrastructure","tag-predictive-analytics"],"_links":{"self":[{"href":"http:\/\/www.palada.net\/index.php\/wp-json\/wp\/v2\/posts\/17647","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/www.palada.net\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.palada.net\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.palada.net\/index.php\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"http:\/\/www.palada.net\/index.php\/wp-json\/wp\/v2\/comments?post=17647"}],"version-history":[{"count":0,"href":"http:\/\/www.palada.net\/index.php\/wp-json\/wp\/v2\/posts\/17647\/revisions"}],"wp:attachment":[{"href":"http:\/\/www.palada.net\/index.php\/wp-json\/wp\/v2\/media?parent=17647"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.palada.net\/index.php\/wp-json\/wp\/v2\/categories?post=17647"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.palada.net\/index.php\/wp-json\/wp\/v2\/tags?post=17647"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}