Abstract
The delivery of computing services — including storage, databases, networking, software, analytics, artificial intelligence (AI) and more — has started with Cloud Computing (CC) over the Internet, delivered from off-premise datacenters, running infrastructure at scale with a pay as you go service to their end customers. As the Internet of Everything (IoE) continues to evolve, parts of these services are migrating from the centralized locations (Cloud) to more decentralized locations closer to the end-user, e.g. Fog Computing (FC), Edge Computing (EC) and only recently on to the end-user device itself, the Mist Computing (MC). By 2025, Gartner predicts 75% of the data will be processed at the Edge. Applications are characterized by big data and near real-time processes in various areas, such as: energy management, highways, buildings, plant automation, supply chain, visual security, signage, and mobile-EC. Unlike for Cloud systems, reference frameworks and standards for FC and EC are still in an early stage of development or non-existant for MC.
As part of the European project BRAINE (a 28-partner consortium), a novel type of Edge MicroDataCenter (EMDC) providing cost-effective, powerful computing resources close to endusers and specifically designed for AI elaborations is being developed with very efficient cooling that nears being completely passive.
The present study concentrates on experimental validations of a new highly efficient, passive thermosyphon cooling system (patent pending by October 2023) thermally managing the level and uniformity of temperature for all the electronics in the package (no air cooling at all within the computer chassis). The primary objective is the cooling of 11 nodes (which include CPUs, FPGAs, GPUs and Storage) considering one heat sink evaporator per node. Presently, a first prototype as a simplified EMDC with 4 slots (i.e 4 nodes) has been fabricated and the entire thermosyphon cooling system evaluated. The experimental results are presented. The working fluids used are the new environmentally friendly refrigerants R1233zd(E) and R1234ze(E).
It is highlighted that BRAINE’s overall aim is to boost the development of the Edge framework and specifically energy-efficient hardware and AI-empowered software systems, capable of processing Big Data at the Edge, performing AI functions, supporting security, data privacy and sovereignty. Then, cooling is one of the most important aspect in this new technological challenge. In fact, our cooling system has no moving parts inside computer (solid-state) and our thermosyphon has an energy efficiency ratio of heat dissipation-to-cooling fan power up to 64-to-1.
