DCMS: The key component of software-defined data center and digital twin initiatives

[ServicesExperts]

Data center management services are crucial to any software-defined data center and digital twin deployments. Here’s a useful way to visualize the four levels of DCMS.

by Pascal Lecoq, Director, Worldwide Data Center Technology Services Practice, HPE Pointnext Services

When discussing software-defined and digital twin solutions in an enterprise IT framework, one can find as many definitions of these as there are players or integrators in the market. It is therefore almost impossible for CIOs to make up their minds and determine a pragmatic approach and solution that will eventually be successful in providing all of the functions and features that were initially required to support the company’s IT transformation strategy and roadmap.

Our own experience at HPE is that setting the scene through a data center management services (DCMS) approach is a must. It’s a prerequisite for any successful software-defined data center (SDDC) or digital twin implementation.

In a nutshell, DCMS is a straightforward implementation and integration of software suites, processes, procedures and organizations that will provide the foundations of the SDDC layers.

Let’s focus first on their software suites. Their fundamental purpose is to provide the ability to measure and manage data about all active components in a data center, end-to-end, including IT infrastructure, network, applications and facilities. One common mistake, almost always encountered, is to consider either IT infrastructure or facilities infrastructure as separate elements because they’re operated and managed at the company level by two independent organizations. Building a bridge between IT and facilities is crucial, and several management layers will be involved to get deeper measurement, supervision, and management and operations intelligence.

A full DCMS approach, as an SDDC/digital twin foundation, is composed of four layers, each one addressed through tools, processes, procedures and organizational components. This mapping is represented in Figure 1 below:

 Figure 1. An integrated framework for data center management services: The DCMS pyramid

Layer 1: Data collection and supervision. This layer is almost always available, even if it’s not tuned for DCMS. We’re talking here about data center supervision and monitoring tools such as BMS (building management systems) for facilities, or IT supervision suites. At the same level comes dedicated software that delivers intelligence at the distribution layers, such as intelligent rack PDU systems, or intelligent network cabling systems. Systems that supervise middleware – such as the virtualization layer, containerization layer, network management, database management, etc. – are also part of the loop. In addition, data can be collected dynamically in real time thru the right API, or statically through batch import of preformatted data coming from an external system.

Layer 2: Operational management. Successful, competitive, and agile enterprises efficiently run data centers that deliver the right service level and capacity at the right time, and at a reasonable cost. Without strong knowledge, processes and operational know-how from trained staff—and given today’s constantly changing processing environments—the large-scale capital that enterprises invest in a data center likely will not yield a satisfying operations performance.

The main issue is that an experienced labor force that can effectively and efficiently operate next-generation data centers is not expanding at the same rate that data centers are being built.

HPE Pointnext Services provides Operations Management Consulting to help our customers develop and maintain well-run data center operations to meet service-level objectives. It offers governance rules; operational intelligence and procedures; runbook-based documentation; staff selection guides and training; and performance measurement indicators for new and existing data centers. It adopts a systematic and multistep approach to assess and evaluate the existing data center operation status. The service develops missing processes, adapts existing documentation elements for operations and processes, and bundles them together into a central, easy-to-access and use data center operations document package called the “DC runbook.”

I’ll talk about HPE datacenter consulting services in more detail in an upcoming blog.

Layer 3: Intelligent management. The third and key layer is data center infrastructure management (DCIM). DCIM systems bridge the gap between IT and facility management of data centers by creating an IT and facility asset database that’s directly linked to space, power and cooling on the facility side and to compute, storage and networking on the IT side. This allows the system to optimize provisioned infrastructure; accurately and quickly deploy new systems with related power and network connectivity; and perform accurate capacity planning so that the data center is ready for the future.

DCIM traditionally follows the premise of designing, building and operating the data center for reliability. However, the new paradigm is to manage the data center not only for reliability but also for efficiency. In this regard, it is not possible to manage what is not measured. The reliability and efficiency of the data center cannot be sustained – given the daily operation of installs, moves, adds and changes (IMACs) – without an IT-facility integration tool such as DCIM.

DCIM enables energy efficiency because it is a holistic solution that tracks and manages both facility- and IT-based assets such as cabinets, servers, network switches, cable plant infrastructure, UPS systems, PDUs, rack PDUs, CRAC units, and more. Where possible, these assets should be tracked in real-time via established protocols such as SNMP and Modbus. DCIM is also designed to manage the optimum location, physical connectivity and logical relationships among the various IT and facility assets.

I’ll do a deeper dive into DCIM in my next post.

Layer 4: Energy Efficiency. This fourth layer will complete the picture for a SDDC-ready and digital twin system. The global DC efficiency is measured, managed and reported on top of the first three layers of this model via a service portal.

This comes with inventory/asset management, configuration management, capacity management, integration management, intelligent dashboards and reports. The portal delivers the right information for the right decision to the right stakeholders at the Executive, Operational, and Business levels, as shown in Figure 2 below:

Figure 2: Supply of information about energy efficiency to decision-makers

Having the whole DCMS framework without this intelligent service portal, which will publish data and gather user requests, is a mistake, and will likely lead to the misuse or “no-use” of the system.

On top of this, the digital twin will complete the SDDC integration by allowing 3D real-time modelling and simulation of data center operations and performance.

The portal will be the user interface with all the SDDC software bricks in order to access the data center comprehensive service catalog, manage user access and security, generate intelligent dashboards and reports and much more.

HPE Pointnext Services can help you build every layer of the DCMS pyramid and put your software-defined data center on a strong foundation. Learn more about technology services consulting from HPE Pointnext Services.

Learn more about software-defined infrastructure solutions from HPE.

Pascal Lecoq is a Director at HPE Pointnext Services, in charge of the Worldwide Datacenter Technology Services Practice. He focuses on Advisory, Professional and Operations Consulting Services, which include data center transformation and consolidation programs. These services feature strategic advisory consulting from edge to cloud; concept and detailed design; and implementation and commissioning services. Pascal also focuses on data center assessments and capacity planning, and operations consulting. His expertise includes solution offerings such as modular data centers from Micro DCs to PODs (data centers in containers), datacenter management services, and datacenter as a service.

Services Experts
Hewlett Packard Enterprise

twitter.com/HPE_Pointnext
linkedin.com/showcase/hpe-pointnext-services/
hpe.com/pointnext