The EC DG Information Society and Media, Software & Service Architectures and Infrastructures convened an expert group on CLOUD Computing in 2009. The group has produced a report that outlines the future directions of Cloud Computing research. The findings of the final report of the group of experts and the orientations for future research in cloud computing will be presented and discussed on 26 January 2010, in Brussels.
The group was moderated by Burkhard Neidecker-Lutz of SAP Research and the author representing ERCIM. The rapporteur is Lutz Schubert of HLRS at Stuttgart and Maria Tsakali, the official responsible from the European Commission. After several meetings of the group, one open meeting and much internet-based discussion a final report has been produced. It will be presented at an event organised by the EC DG Information Society and Media, Software & Service Architectures and Infrastructures on 26 January 2010 in Brussels http://cordis.europa.eu/fp7/ict/ssai/events-20100126-cloud-computing_en.html.
The report characterises different kinds of CLOUDs (both existing and future) and suggests the open research issues that need to be addressed. While recognising that CLOUDs are being used now, both privately within an organization and as a service external to an organization, the report indicates a much greater possible utilisation if the research issues (which address limitations of CLOUDs as seen from an end-user perspective) have solutions provided.
CLOUDs offer potentially unlimited scalability (both up and down) and virtualization of resources so system management issues are hidden from the end-user. CLOUDs can offer IaaS (infrastructure as a service), PaaS (platform as a service), AaaS (application(s) as a service) or a totally outsourced ICT capability. The use of CLOUD services can reduce greatly the carbon footprint of an organization due to the efficiencies of a datacenter environment and so can claim ‘green ICT’ credentials.
The major technological concerns which act as barriers to take-up of CLOUD computing centre on (a) security, trust and privacy; (b) lack of standardization and therefore supplier lock-in; (c) insufficient virtualization to provide real hiding of systems management (especially in resource sharing/failover); (d) data movement and management; (e) programming models to provide the required elasticity; (f) systems / services development methods.
There are also non-technological concerns, mainly (a) business / economic / cost models for CLOUD computing (including ‘green ICT’ aspects) that are robust and realistic; (b) legalistic issues concerning data processing in another country or multiple countries and/or using an outsourced service.
The report identifies three areas where Europe could become prominent in CLOUDs: (1) large companies – especially but not exclusively the telecommunications industry – could provide CLOUD services; (2) development by companies (especially SMEs) of services for the CLOUD environment leading to an open market in CLOUD services matching that in goods, services, human capital and knowledge; (3) provision of business model and legalistic services (including ‘green ICT’) to accompany the use of CLOUD computing. The report requests the EC (a) to support R&D in the technological aspects and (b) to set up the required governance framework for CLOUDs to be effective in Europe. Subsidiary recommendations include the provision of testbeds, joint collaboration groups across academia and industry, standardisation and open source reference implementation (rather like W3C) and the promotion of open source solutions.
So, what is all the fuss about? People ask if CLOUDs are not the same as one or many of: Cluster computing, GRIDs, Future Internet, the Internet of Things or SOA (Service Oriented Architecture). The answer is – as usual – yes and no! Basically CLOUDs provide a new perspective on ICT provision for an organisation. The CLOUDs technological solution (virtualization, resource sharing, elasticity) allows organisations to do their ICT differently.
Internal CLOUDs allow the organization to optimise ICT in one datacenter (almost certainly replicated – probably externally - for business continuity) and so increase server utilisation and allowing server hibernation or switch off in periods of low demand. This reduces capital expenditure and associated maintenance / systems administration. It also reduces energy consumption. Departments in the organization buy services provided in the CLOUD so having better cost-management of their ICT; similarly the ICT department is more efficient.
External CLOUDs allow the organisation to outsource some or all of its IT to another organisation providing the service (and probably providing such a service to several other organisations). This leaves the organisation to concentrate on its primary business and treat ICT as a utility service.
In both cases there is a shift in accounting for ICT from a CAPEX (Capital expenditure) dominated state to an OPEX (Operational expenditure) state. This means that an organisation has neither to reduce its liquid capital not take out expensive loans to procure ICT but can ‘pay as you go’.
Interestingly, this concept links up with recent work on Data and Information Spaces where problems of integration across heterogeneity in data and information – not unlike in infrastructural ICT resources – are at least partially overcome by the ‘pay as you go’ philosophy.
CLOUDs provide a real opportunity for European business. However, for this to be realised there are research issues to be addressed both technological and non-technological. With the strong background in Europe in the relevant technologies and in dealing with legal and cultural heterogeneity the challenges surely will be met and the problems overcome.