Sustainable energy demand side management for GREEN Data Centers

The use of the information and communications technologies (ICT), comprising communication devices and/or applications, Data Centres, Internet infrastructure, mobile devices, computer and network hardware and software and so on, has increased rapidly. Internet service providers such as Amazon, Google, Yahoo, etc., representing the largest stakeholders in the IT sector, constructed a large number of geographically distributed internet data centers (IDCs) to satisfy the growing demands and providing reliable low latency services to customers. These IDCs have a large number of servers, large-scale storage units, networking equipment, infrastructure, etc., to distribute power and provide cooling. The number of IDCs owned by the leading IT companies is drastically increasing every year. Due to large amount of energy implied and the related cost, IDCs can make a significant contribution to the energy efficiency by reducing energy consumption and power management of IT ecosystems. It was reported that IDCs consume 100 times more energy than conventional office buildings.
The GREENDC project contributes to greener data centres by developing a decision support system (DSS) that helps data centre managers predict energy demands better and evaluate strategies to minimize energy waste and CO2 emissions. The GREENDC DSS monitor the energy use of IDCs and propose dynamic cooling strategies to save energy consumption. GREENDC is implemented through knowledge exchange between two academic partners and two industrial partners. Academic partners transfer knowledge on energy forecasting and optimal operation strategies to industrial partners while industrial partners transfer their knowledge on data centre operations through secondment activities.

The first version of the GREENDC DSS (version 1.0) was delivered in month 20. The DSS reads real-time data from data centres with regards to the performance and energy consumption of IT and cooling devices. Based on read data, the DSS estimates and optimises workload and energy consumption of the devices within the data centres. A simulation model was also designed to simulate trade-off relationships between energy consumptions by IT and cooling devices. The GREENDC DSS version 1.0 were tested by DC managers at Turksat and DAVID for further improvement. The feedback from the managers were summarised in the deliverable D1.2 GREENDC Feedback Report.
Based on the user feedback in D1.2 the second version of the GREENDC DSS (version 2.0) was delivered in month 40 as originally planned. The main changes in the version 2.0 includes improved user interfaces and the development of a dynamic cooling component. The new user interfaces present diagram of the data centres to present monitoring information such as temperatures in multiple places of data centres, energy consumption by different types of cooling and computing devices, and workloads of server racks. More graphic analysis of those data is also added. The dynamic cooling component provides dynamic set points of cooling devices as the workloads of the server racks changes during a work day. This can remove cooling waste by increasing setpoints of cooling devices when workloads of servers are low.
The evaluation of the GREENDC DSS version 2.0 was conducted by TSAT DC managers for user experiences of the system (new user interfaces) in month 66. On the other hand, the DSS was also tested by DC managers of the Royal Thai Navy (RTN) to evaluate the optimal cooling device operation schedules in month 67 and 68.
The GREENDC project made good progress to disseminate project results. A project web site and twitter page were established and are being used as the main channel for the dissemination of the project outcomes. Total 14 papers were presented in international conferences and four papers in professional events. Four papers were published international journals, one accepted, and one is under a review process. The success story of the GREENDC project was published on the EUROPA web site (https://ec.europa.eu/research/infocentre/article_en.cfm?artid=51406). For communication activities, Twenty RISE ambassador activities were implemented, and two open day events were organized.
The training of early stage researchers via various knowledge transfer mechanisms is continuously provided through the secondment activities. The consortium implemented total 253 knowledge exchange activities during the project duration. PhD students who were involved in the secondments and training activities was now working at UN to work in Thailand in the area of sustainability, Lecturer at UBRUN, a post-doctor in the University of Cardiff in the UK, a government institute in Turkey after their graduations.

The scientific outcome of the GREENDC project is the decision support system (DSS) that use real-time data from data centres and provide DC managers with strategies to reduce energy consumption. The experiment conducted in Royal Thai Navy indicates that the dynamic cooling approach can save energy consumption by 32.5% compared with the static cooling approach currently adopted by their data centre. Turksat who hosted the field trials of the DSS decided to use the DSS in their current DC rooms based on the successful outcomes. They are going to use the DSS for the new data centre facility recently built in another location. It was also reported that the use of the proposed approach improved the attitude of the data centre managers to be energy efficient.
The GREENDC project also helped career developments of the staff members of the consortium partners. Total 7 PhD students who participated to the secondment activities were successful to have professional posts after their involvement in the project. They are now working at UN, Universities in the UK and Turkey, and governmental institutes.

Periodic Reporting for period 2 - GREENDC (Sustainable energy demand side management for GREEN Data Centers)

Verwandte Dokumente

Diese Seite teilen

Herunterladen