What if your data center was smart enough to help you proactively optimize your operations, such as automatically alerting you when systems are over-consuming power or need to be updated or retired? Artificial intelligence (AI) and machine learning (ML) technologies are making digital infrastructure smarter and more intuitive throughout every industry.
At Equinix, we’ve made a real investment in AI/ML technologies and techniques to optimize our International Business Exchange™ (IBX®) data centers and global business operations. AI/ML-based development helps us expedite products and service delivery, empowers us to reach our sustainability goals, and arms us with insights that drive efficiency improvements across our global platform.
Let’s look at how AI/ML models are being used to create real value for data center operators and their users in these six areas, with illustrations of how Equinix has harnessed the power of AI/ML to realize greater data center optimization and efficiency, and enhance the user experience for our global employees and customers.
Leaders’ guide to digital infrastructure
Learn how 50%+ of the Fortune 500 have leveraged Platform Equinix to implement and capitalize on their digital-first strategies.DOWNLOAD THE GUIDE
1. Energy Efficiency and Sustainability
In the global fight against climate change, businesses are working to reduce the impact of their IT infrastructure on the environment and become carbon-neutral or carbon-positive in their operations. Sustainability has become such a priority across companies around the world, investors, employees, partners and customers are now considering a company’s sustainability rating before getting involved with them.
A low power usage effectiveness (PUE), or the ratio of total facility power and energy consumed by IT equipment, addresses both energy efficiency and sustainability metrics. As does low water usage effectiveness (WUE), which is the ratio of annual site water usage and the energy consumed by IT equipment.
AI/ML models optimize a data center’s energy efficiency by:
- Proactively managing the PUE of your data center and assessing the impact of the ongoing manual changes in the operating parameters of data center assets.
- Identifying the best set of operating parameters for individual or group assets to minimize energy consumption while achieving the desired physical impact from each asset (i.e., maintaining optimal temperature, humidity, etc.).
- Predicting and optimizing your WUE so you can operate your data center in a more sustainable manner.
Meeting global data center energy demands while achieving sustainability objectives presents IT operators with some unique challenges — from finding clean and renewable energy sources to managing power and cooling through adaptive intelligent control systems. At Equinix, we are advancing a bold environmental agenda through a range of commitments, which include reaching our goal of 100% clean and renewable energy usage across our global portfolio (in 2021 we reached 95%) and becoming climate-neutral in our global operations by 2030.
We leverage AI/ML to develop PUE optimization models that recommend optimal operating parameters for assets based on a “state of the asset” digital twin (a digital version, or “twin”, of a physical asset). Through these models, we can forecast power and space capacity in our IBX data centers and ensure customer requirements for specific megawatt thresholds are met.
We are also incorporating greater visibility into our customers’ cabinet-level energy consumption via our IBX SmartView DCIM APIs. The direct benefit to our customers is that they can move their IT into a “ready-made” sustainable data center with a digital infrastructure platform that gives them valuable data, which helps them regulate their own energy usage and meet their sustainability goals.
2. Asset Performance Management
Asset performance management (APM) includes data capture, integration, visualization and analytics for the sole purpose of improving the reliability and availability of physical assets.
AI/ML models for APM have been demonstrated to:
- Extend the useable life of an asset by proactively detecting and fixing asset operating parameters that may reduce its usability (e.g., fans changing speed too frequently).
- Predict when an asset needs maintenance based on its operating conditions. It can also tell you when to move from scheduled to predictive maintenance to lower costs and improve customer and employee satisfaction by reducing unplanned outages.
- Learn normal operating conditions, such as energy usage, for individual and group assets and then identify anomalous operating conditions by monitoring real-time data streams.
Aging or poorly functioning assets can be a huge drain on power and also the cause of system failures and user dissatisfaction if not quickly identified. We’ve developed anomaly detection models that predict assets with anomalous operating conditions to improve an asset’s lifetime, reduce costs and lower energy consumption. These optimizations have also helped to improved our customer and employee satisfaction by contributing to our industry-leading reliability (99.9999% average uptime) in our data center operations.
3. Capacity Management and Planning
As business requirements change, many companies are dealing with limited resources to address fluctuating compute, storage or networking capacity needs over time. Over or under provisioning data center capacity for IT infrastructure can lead to greater waste and increased costs. Leveraging AI/ML technologies will enable you to efficiently manage and plan the resources you need (i.e., space, power and cooling) to maximize revenue, reduce TCO, and be more sustainable today and in the future.
AI/ML models provide valuable data to:
- Learn space layout and optimize the sellable/useable space in a data center, while maintaining the constraints around temperature, humidity, etc.
- Plan from current and past data center power usage and optimize near-term and predict/prescribe future power consumption.
As mentioned above, we are leveraging AI/ML modeling to assess our current and future capacity and power needs to better meet our customers’ changing business requirements. By proactively anticipating our customers’ colocation and digital infrastructure needs, we can be ready for them wherever they want to do business.
4. Customer Relationship Management
The Equinix 2022 Global Tech Trends Survey (GTTS) report shows 83% of IT leaders want to improve customer experience and 81% want to improve employee user experience.
Enhance your customer/user experience by using AI/ML models to:
- Balance the supply and demand, capacity and operating constraints of your data center to better serve internal users and external customers.
- Identify user dissatisfaction or customers at risk of leaving so your support and sales organization can proactively work to retain them.
- Recommend potential customer connection opportunities, within and across data centers, to leverage critical digital or business services in a secure and low-latency manner.
By leveraging AI/ML modeling, you will gain greater insights into how to better align your solutions to customers’ needs/desires. We’ve developed intelligent models that are helping our marketing teams identify customer requirements via the analysis of approximately 100 different input types. By doing this, we can see repeatable customer use cases and more readily offer solutions that best meet their needs.
Cyber-attacks, security breaches and data leaks were the top threats to business success, as discussed in the video, “Top Trends, Challenges and Opportunities Impacting Digital Leaders Globally.” Digital leaders are looking to AI/ML technologies to greatly improve their data center security posture by closing seen and unseen gaps in their security controls.
Protect your equipment and data using AI/ML models for capturing:
- Video analytics that monitor and flag suspicious activities around your data center and within or near customer cages via video surveillance analysis.
- Cage/cabinet access data that model and detect anomalous access patterns for customer access.
Data center security requires both physical and virtual controls to cover an ever-expanding attack surface. In addition to our advanced security equipment, techniques and procedures, AI/ML models that analyze video streams and logs from our equipment in our IBX data centers will detect anomalies, making our data centers and our customers’ equipment and data even more secure.
6. Productivity Improvements
Improving data center workflows and processes using AI/ML technologies will increase user satisfaction and productivity and, ultimately, give you valuable insights for optimizations that will future-proof your data center.
AI/ML models have been shown to effectively:
- Facilitate incident management by clustering events in similar topics to more quickly solve new incidents based on past learnings and best practices.
- Reduce data center work ticket processing time by parsing details of customer work and more quickly send them to the right team.
Reducing the number of manual processes and improving productivity through AI/ML techniques results in more quickly responding to your customers’ needs. At Equinix, we’ve eliminated manual approvals for approximately two-thirds of our transactions through workflow automation, expediting our business processes and our customer response time. We’re also using natural language processing (NLP) in our intelligent automated ticket routing as a proof-of-concept in our Equinix Smart Hands® remote data center management. By quickly classifying support requests via NLP, we can improve the customer experience with faster responses.
These are just a few examples of how AI and ML are currently being applied at Equinix, with more to come in the future.
Learn more about future-proofing your data center infrastructure by reading the Leaders’ Guide to Digital Infrastructure.
And check out this Equinix, NVIDIA and Dell Technologies webinar on Understanding the AI/ML ROI Models.
 Omdena, “The Ultimate MLOps Guide: How to Master MLOps for ML Engineers and Data Scientists,” Lukasz Murawski, Lead Machine Learning Engineer at Equinix, April 22, 2022.