The CATALYST project is the response to the EU EE-20-2017 Call to: Bring to market more energy efficient and integrated data centres.

Data Centres (DC) are among the largest yet increasing energy consumers, due to the rising digitization of human activities. RES integration and energy efficiency improvements have the potential to reduce significantly DC carbon footprint, while increasing at the same time the auto-consumed energy, thus improving DC security and resiliency of
supply against climate change. However, very few solutions, despite validated in lab, have been successfully deployed on operational DCs, mostly due to technological fragmentation, excessive CAPEX and lack of appropriate business models.

CATALYST will address these challenges through turning existing/new DCs into flexible multi-energy hubs, which can sustain investments in RES and energy efficiency by offering mutualized flexibility services to the smart energy grids (both electricity and heat grids). By leveraging on the outcomes of FP7 GEYSER and DOLPHIN projects, CATALYST will adapt, scale up, validate and deploy an innovative, adaptable technological and business framework aimed at i) exploiting available DC non-IT legacy assets (onsite RES/backup generation, UPS/batteries, cooling system thermal inertia, heat pump for waste heat reuse) to deliver simultaneous energy flexibility services to multi-energy coupled electricity/heat/IT load marketplaces ii) deploying Cross-DC cross-infrastructures (e.g. heat vs IT) IT workload orchestration, by combining heat-demand driven HPC geographical workload balancing, with traceable ICT-load migration between federated DCs to match IT demands with time-varying on-site RES (“follow the energy approach”) iii) providing marketplace-as-a-service tools to nurture novel ESCO2.0 business models. The adaptation and replication potential of CATALYST will be demonstrated through carrying out four different real life trials spanning through the full spectrum of DCs types (fully distributed DCs, HPC, co-location, legacy) and architectures (from large centralized versus decentralized micro-DCs).

The first task was to specify the details of the testing environments in which the CATALYST offerings will be deployed and tested and defined the required adaptation actions so that the CATALYST will be fine-tuned, tested and validated in the real-life DC trials. Moreover, it specified, procured and acquired any 3rd party hardware/software components and all the necessary additional equipment including sensors, controllers, water cooling systems, batteries, RES and other hardware modules to be procured and installed, in order to set-up the trials. Given that CATALYST will develop a rich set of tools for rendering DC environmentally friendly, this task defined a DC Data Management plan and ensure that all the developed tools will be tested at least in one test-bed and will define a comprehensive methodology and scenarios for testing, evaluating and demonstrating CATALYST outcomes.

Pilot #1: Green Pont Saint Martin DC

The Green Pont Saint Martin DC located in Italy has been testing scenarios specified in in other deliverables and validated in laboratory tests and will be used to validate the research results in real experiments with a continuous in-feed from real data to the simulation and vice versa. The pilot has been set-up according to the specifications defined in other tasks and the defined methodology will be adhered to evaluate the following green DC features:

• Energy savings from free-air cooling and from cold water from the aquifer (geothermal energy);

• DC offices’ Building heating based on geothermal hot water and surplus heat from DC;

• Energy Demand Side Management through energy heat reuse practices and backup generators usage;

• DR programs to reduce energy consumption (specific collaboration agreement is already in place);

• Load migration between the Green PSM, PSNC DC and legacy SiLO DC has been tested to a limited extent, due to mission critical business operations.

Pilot #2: Poznan Supercomputing Centre DC

The second pilot site is the Poznan Supercomputing Centre DC, located in Poland. The pilot has been set-up according to the CATALYST specifications and the defined methodology will be adhered to evaluate the following green DC features:

• Cold liquid closed loop for DC cooling;
• Transfer of heat from liquid loop to the water loop to provide heat to the DC offices;
• Simulate the interconnection of the water loop to provide district heating to the University campus;
• Interconnect RES (PV cells) and battery based UPS supported by diesel engines to maintain the DC uninterrupted
operation, stabilize the Smart Grid and offer electricity & flexibility services;

Pilot #3: Schuberg Philis DC

The third pilot site is the SBP carrier neutral DC, located in Amsterdam, once again the test-bed will be set-up according to the CATALYST specifications nd the defined methodology will be adhered to evaluate all CATALYST features. Emphasis will be on the evaluation of the benefits of:

• Reuse the warm air to provide heat to the DC offices;
• Reuse the warm air to pre-heat the diesel UPS engines;
• Provide a comparison between battery based and dynamic rotating UPS;
• Reuse the cold drinking water to provide energy-free (passive cooling) water cooling;
• Collaborate with ALD in electricity DR programs to offer flexibility/ancillary services and reduce energy consumption
and provide electricity back for Smart Grid stabilization from dynamic rotating UPS;
• Host IT load from the QRN fully distributed DCs if needed (especially during summer period);

Pilot #4: Distributed QRN DC

The fourth and final pilot is the Qarnot distributed compute network. In this task, QRN will use its installed HPC grid to implement CATALYST components, and especially IT load scheduling and migration. The pilot will first be tested at QRN distributed DC level and then extended to inter DC operations. QRN will focus its work to acknowledge the following characteristics within the CATALYST perspective:

• Stabilize the grid by forecasting heat needs and capacity;
• Balance IT loads by migrating VCs within and outside the virtual DC;
• Implement DR (electricity and IT load) for grid flexibility;
• Measure heat response and adequacy to temperature command.

Assessment and Replication Guidelines

During this task, the measurements collected from the CATALYST testing in the real-life test-beds will be elaborated and compared against historical data, in order to assess the CATALYST ecosystem performance and validate the success of the predictions. Comparison with the current situation as well as between the different test-beds will be carried out, in order to check the applicability and benefits of the concept in multiple domains. Any limitations detected and possible parameter tuning or design optimizations will be included in the deliverable of this task, summing up all the technical efforts of CATALYST. Finally, replication guidelines will be drawn based on the test results, the performance figures and the experience gained.

An extract of D7.4 Trials – Intitial Results has been published

The initial results from the pilots has been published in the library as D7.4