Print

Reinforcement Learning for Predictive Failure-detection and Proactive Data Management on Digital Storage Systems
Details
Locations:Cyprus
Start Date:Oct 1, 2020
End Date:Feb 23, 2022
Sectors: Information & Communication Technology
Description
Programme(s):
H2020-EU.2.3. - INDUSTRIAL LEADERSHIP - Innovation In SMEs
H2020-EU.2.3.2.2. - Enhancing the innovation capacity of SMEs
Topic(s): INNOSUP-02-2019-2020 - European SME innovation Associate - pilot
Call for proposal: H2020-INNOSUP-2018-2020
Funding Scheme: CSA-LSP - Coordination and support action Lump sum
Grant agreement ID: 957149
Project description:
Saving data by spotting soon-to-fail storage devices Physical infrastructure is expanding to meet the fast-growing demand for greater mobile connectivity. There are currently more than 2 billion connected computers and 30 billion smartphones, wearables and connected devices. The amount of data becomes enormous, demanding support from an ever-increasing hardware infrastructure. In such an environment, hardware failures become the norm, which may result in data losses and higher maintenance costs. The EU-funded PREFAIL project will assist in securing an innovation associate to design solutions for proactively identifying soon-to-fail storage devices, protecting users from data losses and enhancing data maintenance at the storage providers.
Objective:
As the Digital Transformation of Europe, and the rest of the world, is rapidly picking up pace, the underlying physical infrastructure is similarly expanding to keep up with demand generated by over 2 billion connected computers and more than 30 billion smartphones, wearables and IoT devices. Nevertheless, Internet applications and services remain prone to inevitable hardware failures, that lead to data losses and increased maintenance costs. The primary problem lies with the cost of implementing data redundancy by constantly adding expensive hardware to cater to the needs of traditional data replication approaches (e.g. by always keeping copies of a file on multiple servers).
With the assistance of an Innovation Associate specializing in Machine Learning, Algolysis Ltd aspires to extend its cloud-based storage device monitoring service (DriveNest - www.drivenest.com) with a robust state-of-the-art failure prediction engine. Reliably identifying soon-to-fail storage devices can be a transformative capability across the ICT sector, as a range of proactive data management and mitigation services can be built on top.