ICT Sustainability

Improving Data Centre Energy Efficiency

The Australian Minister for Finance, released a Review of the Australian Government's Use of Information and Communication Technology (known as "The Gershon review"), 16 October 2008. The Gershon review provided high level proposals of how ICT operations should be managed in a large organisation and recommended the consolidation of data centres.

The European Commission issued a Code of Conduct for Data Centre Energy Efficiency in 2008. The EU Guidelines provide a detailed approach to implementing and assessing the energy saving in a data centre.

Evidence-based approach to ICT review

Sir Peter Gershon's review of Australian government ICT, including data centres provides a useful overview of ICT planning for a large organisation (Gershon 2008). Sustainability of ICT is covered in Recommendation 7 of the report. However, many other sections of the report are relevant to planning for sustainability.

The Gershon review employed an evidence-based approach, first assessing the current situation, to determine the scope and possible areas for improvements in efficiency and effectiveness.

Three phases of review:

1. Evidence gathering: Submissions were invited from key stakeholders in agencies and industry (112 submissions received). A survey was sent to 100 government agencies for ICT expenditure data: costs per desktop, websites, networks. Key applications including: human resources, financial management and grant management systems were quantified.Data was requested on energy consumption.
2. Consultation: Video conferences were held with agency heads as key stakeholders. Meetings were held with government ministers, agency staff and industry. Three visits were made to sites: one overseas and two to data centres in Canberra.
3. Analysis and reporting: Additional data from the Australian Bureau of Statistics 2002-03 Government Technology Survey, was used with meeting and survey data for findings. Recommendations were developed to address the findings and a report produced.

Seven Findings

The review identified the seven key findings:

1. Weak governance of ICT issues (ICT Governance) across the organisation was found, limiting the evaluation, direction and monitoring of projects.
2. Weak Agency governance was also found to be weak. There was limited organisational capability to commission and manage ICT projects.
3. Limited scrutiny: Agencies tended to take a "business as usual" (BAU) attitude to ICT funding, with inadequate scrutiny.
4. ICT Skills Building: While the ICT skills of staff were considered important, there was limited action to build these.
5. No Whole-of-government strategic plan for data centres: Each agency was was found to plans its own requirements for data centres, resulting in an estimated unnecessary extra $1B expenditure over 15 years.
6. Marketplace: The government ICT marketplace was found to be inefficient and ineffective. High transaction costs with onerous procurement processes and slow decision making was found. Prescriptive statements of requirement, which limits the range of solutions proposed by vendors were found.
7. Sustainability agenda: There was a significant disconnect between the Government's overall sustainability agenda and its ability to understand and manage energy costs and the carbon footprint of its ICT estate.

It should be noted that only the last of these findings "Sustainability agenda", mentions green ICT explicitly. However, they all have an effect on the ability of an organisation to incorporate sustainability in its planning. The report's primary finding was that the autonomy of the individual government agencies were the problem.

Key recommendations

The recommendations correspond to the key findings:

1. Strengthen pan-government governance: The report recommended a Ministerial Committee on ICT (equivalent to a company board committee), a Secretaries' ICT Governance Board (SIGB) to address key business issues with ICT and to limit opt-out from whole of government arrangements to those approved by the Ministerial Committee.
2. Strengthen Agency Governance: Use of common methodologies, including ITIL, were recommended. This is to including business domain activities (requirements definition and benefits realisation) as well as ICT.
3. Tighten the management of ICT business as usual funding: A reduction of 15% in ICT budgets was recommended with cross-agency and external benchmark comparisons to identify possible efficiency improvements. ICT Review Teams would identify the drivers of agency BAU costs, server utilisation and data centre efficiency and reduce the use of contractors.
4. Enhance the management of the APS ICT skills base: A whole-of-government ICT career structure was proposed, along with a whole-of-government strategic ICT workforce plan, identifying skills issues, recruitment, training, development and skills shortages.
5. Data Centres: Consolidation of the physical data centre infrastructure was recommended: buildings, heating, ventilation, air-conditioning and power supply. However, the report recommended keeping agencies' ICT equipment and databases in separately controlled and managed areas.
6. Improve the efficiency and effectiveness of the ICT marketplace: The report recommended whole-of-government panel arrangements for ICT commodity-based procurements and volume sourcing for software (including e-auctions). Strategic management of key suppliers would be used to deal the dominance of large suppliers.
7. Sustainability of ICT: The report proposed a whole-of-government ICT sustainability plan, in conjunction with the Department of the Environment, Water, Heritage and the Arts (DEWHA), to manage the carbon footprint of the Government's ICT activities.

Most of these recommendations effect the ability to increase the sustainability of of ICT in the organisation. Stronger governance arrangements should make it more feasible to have Green ICT included in the business planning and reporting.

A reduction in the "business-as-usual" budget would allow for initiatives in energy saving. Enhanced skills base would allow for green ICT training. Consolidated data centres would allow for more energy efficient cooling and power management practices. A more effective marketplace would allow suppliers to offer more innovative approaches to energy reduction and materials reuse.

One problem with the recommendations is the proposal to keep agencies' ICT equipment and databases in separately controlled and managed areas. This would limit the ability to share computer servers between agencies, thus reducing the amount of hardware needed and allowing it to operate at a more power efficient higher level of utilisation. The use of virtualisation, where hardware is physically shared, but logically partitioned, may be an acceptable. Also not covered by the report is the use of shared web based applications, where agencies can use the same applications, running on the same shared servers, but have only their own data presented to them via a web interface.

The issue of the dominance of large suppliers. is an issue for Green ICT. Implementing particular approaches to sustainability will be difficult , if these are not supported by the main suppliers. However, the report does not address the use of standards and open source design as a way to avoid vendor lock in. This is particularly useful for Green ICT with the use of formal standards and industry sponsored labelling of equipment and software.

The sustainability recommendation is discussed in detail below.

Sustainability of ICT Recommendation

The last recommendation of the report, Recommendation 7, deals with Sustainability of ICT. This is intended to address Key Finding 7, which was a disconnect between the Government's sustainability agenda and its ability to implement this for ICT. The report concentrates on management of energy costs and the carbon footprint of ICT. Other aspects of sustainability, such of materials use, toxic waste disposal and the use of ICT to reduce energy use in other processes is not addressed.

Disconnect in the sustainability agenda

Only 23 out of 72 agencies indicated they had an energy plan, of these, 13 included an ICT energy component in the plan. Only six agencies provided meaningful ICT energy use data.

For agencies which provided responses on ICT energy, consumption increased by 3%, from 162.4 gigawatts in 2006-07 to 167.6 gigawatts in 2007-08. But in the same period ICT energy costs increased 16%, from $18.1 million in 2006-07 to $21.0 million in 2007-08. This would suggest that cost of energy could be a significant incentive for agencies to introduce energy saving measures.

ICT sustainability plan

In response to the The Gershon review, an Australian Government ICT Sustainability Plan was prepared by the Department of the Environment, Water, Heritage and the Arts (2010).

Six mandatory environmental standards were set for to the purchase of ICT equipment and consumables by Australian government agencies:

1. EPEAT Silver
2. ENERGY STAR
3. Product take-back with reuse/recovery for mobile devices, toner cartridges and ICT equipment
4. Copy paper with minimum 50% recycled content
5. ICT suppliers to comply with the National Environment Protection (Used Packaging Materials) Measure (UPM NEPM)
6. Suppliers adopting an ISO 14001 environmental management system (EMS)

Agencies are required to submit their annual ICT energy consumption data to the Australian Government Information Management Office (AGIMO).

EU Code of Conduct for Data Centres

The European Commission, the executive arm of the European Union, issued a European Code of Conduct on Data Centres Energy Efficiency in 2008. These are intended to reduce, and assess the reduction, in the energy consumption in data centres.

The Code of Conduct is voluntary. It assumes that data centres have typically been designed with large tolerances for operational and capacity changes and this results in power consumption inefficiency. Only a small fraction of the power consumed by the data centre is actually used by the IT systems, most is used up by redundant power and cooling systems.

Focus of the Code of Conduct

1. IT Load: consumption of energy of the IT equipment in the data centre
2. Facilities Load: mechanical and electrical systems (chiller plant, fans, pumps) air conditioning units.

The Code of Conduct considers the data centre as a complete system, to optimise the IT system and the infrastructure together as 'facility efficiency'.

Data centre infrastructure efficiency Measure

The code defines one metric:

Data centre infrastructure efficiency (DCiE):

DCiE = (Main IT equipment energy consumption)/(Total facility energy consumption) * 100

A higher figure indicates better energy efficiency. A measure of 50% would indicate half the energy consumed by the data centre was used by the IT systems (a typical figure for existing centres). A theoretical figure of 100% would indicate that all the energy consumed by the data centre was used for IT (unlikely to be achieved).

Further metrics are under development:

IT productivity metric: An indicator of how efficiently the IT equipment provides useful IT services. This requires some measure of output of the centre, such as number of standard transactions performed, per unit of energy.

Total energy productivity metric: Relating the useful IT services to the total energy consumption of facility.

Best Practices for Data Centres

The Best Practice Guidelines (European Union Joint Research Centre, 2018) are a companion to the EU Code of Conduct on Data Centres to assist with measures to improve the energy efficiency

Expected Minimum Practices

A subset of the best practices are are defined as the expected minimum level of energy saving activity. These are the easiest techniques to apply to an existing data centre. Some practices are categorised as applying to New Software, Expected during any new software install or upgrade, for New IT Equipment, Expected for new or replacement IT equipment, During retrofit. Numeric values, indicating the effect of the measure are included.

Data Centre Utilisation, Management and Planning

The first measure covers management of a data centre:

• Group involvement: Establish an approval board containing representatives from all disciplines (software, IT, M&E). Require the approval of this group for any significant decision to ensure that the impacts of the decision have been properly understood and an effective solution reached. For example, this could include the definition of standard IT hardware lists through considering the M&E implications of different types of hardware. This group could be seen as the functional equivalent of a change board. Expected: Yes. Value: 3

Embedded energy is then considered:

• Consider the embedded energy in devices: Carry out an audit of existing equipment to maximise any unused existing capability by ensuring that all areas of optimisation, consolidation and aggregation are identified prior to new material investment. Expected: Yes. Value: 2

Matching resilience to business requirements is then recommended:

• Build resilience to business requirements: Only the level of resilience actually justified by business requirements and impact analysis should be built. 2N infrastructures are frequently unnecessary and inappropriate. Resilience for a small portion of critical services can be obtained using DR / BC sites. Expected: During retrofit. Value: 3

• Consider multiple levels of resilience: It is possible to build a single data centre to provide multiple levels of power and cooling resilience to different floor areas. Many co-location providers already deliver this, for example, optional 'grey' power feeds without UPS or generator back up. Expected: During retrofit. Value: 3

• Lean provisioning of power and cooling for a maximum of 18 months of data floor capacity: The provisioning of excess power and cooling capacity in the data centre drives substantial fixed losses and is unnecessary. Planning a data centre for modular (scalable) expansion and then building out this capacity in a rolling program of deployments is more efficient. This also allows the technology 'generation' of the IT equipment and supporting M&E infrastructure to be matched, improving both efficiency and the ability to respond to business requirements. Expected: During retrofit. Value: 3

The provisioning recommendations then go into increasing levels of technical detail.

In purchasing new IT equipment, it is recommended that energy efficiency be considered (this assumes the data centre and the equipment in it are run by the one entity):

• Multiple tender for IT hardware - Power: Include the Energy efficiency performance of the IT device as a high priority decision factor in the tender process. This may be through the use of Energy Star or SPECPower type standard metrics or through application or deployment specific user metrics more closely aligned to the target environment which may include service level or reliability components. The power consumption of the device at the expected utilisation or applied workload should be considered in addition to peak performance per Watt figures.

• Multiple tender for IT hardware - Basic operating temperature and humidity range: Include the operating temperature and humidity ranges of new equipment as high priority decision factors in the tender process. The minimum range, at the air intake to servers, is 18-27C and 5.5C dew point up to 15C dew point & 60% RH. The current relevant standard is the ASHRAE Recommended range for Class 1 Data Centers as described by ASHRAE in '2008 ASHRAE Environmental Guidelines for Datacom Equipment'.

McKinsey & Company on Data Centre Efficiency

McKinsey & Company in "Revolutionizing Data Centre Efficiency" (Kaplan, Forrest and Kindler, 2008) recommend the appointment of an Energy Czar and transferring financial accountability of data center assets from Corporate Real Estate to the CIO. These recommendations are driven by an economic analysis which concludes that ongoing server proliferation is resulting in far more expense power and cooling costs which must crowd out other IT initiatives unless IT gets a bigger slice of corporate revenue.

Some of the report's findings:

1. Data Centres (DC) make up one quarter of total ICT costs and rapid growth in the number and size of data centres creates two problems:
   1. Large cost: both Capital Expenditure (CapEx) and Operational Expenditure (OpEx) for Data Centres is large, quickly growing portion of total IT budget.
   2. Large CO₂e: For many organisations, Data Centres are the largest source of greenhouse gas emissions.
2. Causes for inefficiencies:
   1. Poor planning of demand and capacity,
   2. Asset management failings,
   3. Energy Disconnect, with Boards, CEOs and CFOs not holding the CIO accountable for energy use or greenhouse gas emissions.
3. Solutions for inefficiencies
   1. Integrate asset management as is done for corporate security,
   2. Mandate true Total Cost of Ownership (TCO),
   3. Appoint CIOs and internal "Energy Czars" (technology and operations mandate) to double energy efficiency by 2012.
4. Metrics to measure efficiencies
   1. The study proposes the Corporate Average Data Efficiency (CADE) metric for data centres across the corporate footprint,
   2. Industry groups to dialog with regulators to establish a benchmark or metrics to measure the individual and combined energy efficiency of corporate, public sector and 3rd party hosted data centres (for example, a similar benchmark is already implemented in the US automotive industry called 'CAFE').

Now Read

1. Executive Summary, Chapter 5: Recommendations, and Sustainability of ICT, from the Gershon Review (Gershon 2008)
2. Participant Guidelines and Registration Form (2016) and Best Practices (2018) from the European Commission's European Code of Conduct on Data Centres Energy Efficiency
3. Revolutionizing Data Centre Efficiency, from McKinsey & Company (Kaplan, Forrest and Kindler, 2008).

Questions

1. Apply EU Code of Conduct for data centre energy efficiency: Sir Peter Gershon recommended consolidating data centres. Could consolidation of data centres be applied to your organisation, or an organisation you are familiar with? Consolidation will not necessarily increase efficiency. How would you apply the EU Code of Conduct and Best Practice Guidelines for data centre energy efficiency?
2. How could ICT reduce government energy use?: The Gershon report discussed only energy saving targets for energy use by ICT systems. The "SMART 2020" report (The Climate Group's, 2008), also looked at how ICTs could improve energy efficiency in power transmission, buildings and the transportation of goods. Give an example of how ICT could reduce energy use in government business.

Next: Enterprise Architecture.

---

About the book: ICT Sustainability: Assessment and Strategies for a Low Carbon Future