Robots in the data center: how can artificial intelligence be useful?

In the process of digital transformation of the economy, humanity has to build more and more data processing centers. The data centers themselves must also be transformed: issues of their resiliency and energy efficiency are more important than ever. Objects consume a huge amount of electricity, and failures of the critical IT infrastructure placed in them cost the business dearly. Artificial intelligence and machine learning technologies come to the aid of engineers - in recent years they are increasingly being used to create more advanced data centers. This approach increases the level of availability of facilities, reduces the number of failures and reduces operating costs.

How it works?

Artificial intelligence and machine learning technologies are used to automate operational decisions based on data collected from various sensors. As a rule, such tools are integrated with systems of the DCIM class (Data Center Infrastructure Management) and allow to predict the occurrence of emergency situations, as well as optimize the work of IT equipment, engineering infrastructure and even service personnel. Very often, manufacturers offer data center owners cloud services that accumulate and process data from many customers. Such systems summarize the experience of operating different data centers, so they work better than local products.

IT infrastructure management

HPE is promoting the InfoSight predictive analysis cloud service to manage IT infrastructure built on Nimble Storage and HPE 3PAR StoreServ storage systems, HPE ProLiant DL / ML / BL servers, HPE Apollo rack systems and HPE Synergy platform. InfoSight analyzes the readings of the sensors installed in the equipment, processing more than a million events per second and constantly learning. The service not only identifies malfunctions, but also predicts possible problems with the IT infrastructure (equipment failures, storage capacity exhaustion, virtual machine performance decrease, etc.) even before they occur. For predictive analytics, VoltDB software using autoregressive prediction models and probabilistic methods is deployed in the cloud. A similar solution is available for Tegile Systems' hybrid storage systems: IntelliCare Cloud Analytics cloud service monitors the status, performance, and resource usage of devices. The artificial intelligence and machine learning technologies also use the Dell EMC in their high-performance computing solutions. There are many similar examples; almost all leading manufacturers of computing equipment and data storage systems are following this path.

Power and Cooling

Another field of application of AI in data centers is related to the management of engineering infrastructure and, above all, cooling, the share of which in the total energy consumption of an object can exceed 30%. Google was one of the first to think about smart cooling: in 2016, together with DeepMind, it developed an artificial intelligence system for monitoring individual components of the data center, which reduced energy consumption for air conditioning by 40%. Initially, she only gave hints to the staff, but was subsequently modified and can now control the cooling of the machine rooms independently. A neural network deployed in the cloud processes data from thousands of internal and external sensors: it makes decisions based on server load, temperature, as well as wind speed on the street and many other parameters. The instructions offered by the cloud system are sent to the data center, and there they are once again checked for safety by local systems, while the staff can always disable the automatic mode and begin to manage the cooling manually. Nlyte Software, together with the IBM Watson team, has created a solution that collects data on temperature and humidity, energy consumption and IT equipment utilization. It allows you to optimize the work of engineering subsystems and does not require a connection to the cloud infrastructure of the manufacturer - if necessary, the solution can be deployed directly in the data center.

Other examples

Innovative smart solutions for data centers on the market a lot and constantly appear new. Wave2Wave has created a robotic fiber optic cable switching system to automate the organization of cross-connects at the Meet Me Room nodes within the data center. The system developed by the ROOT Data Center and LitBit uses AI to monitor redundant power plants, and Romonet made a self-learning software solution for optimizing the infrastructure. Solutions created by Vigilent use machine learning to predict failures and optimize the temperature conditions in the data center premises. The introduction of artificial intelligence, machine learning and other innovative technologies in data centers began relatively recently, but today it is one of the most promising areas of development for the industry. Modern data centers have become too large and complex to effectively manage them manually.