Abstract :
Summary form only given. There has been a lot of water pass under the bridge since the term grid computing was introduced by Foster and Kesselman in the middle of 90s. Since then the grid concept has evolved, losing its initial high-performance computing flavor. Currently there is an increasing number of researchers that looks at the grid as "A fully distributed, dynamically reconfigurable, scalable and autonomous infrastructure to provide location independent, pervasive, reliable, secure and efficient access to a coordinated set of services encapsulating and virtualizing resources (computing power, storage, instruments, data, etc.) in order to generate knowledge". This grid definition is the outcome of an internal brainstorming exercise conducted recently in the CoreGrid (http://www.coregrid.net/) Executive Committee. Moreover, several researchers envision that economics principle will guide in the future the development of grid-aware applications: an open market of services and resources will become available to the developer, who will choose to use computing time and software solutions from different vendors, sold at different prices, with different performance and QoS. In this light the great majority of complex software applications will, in the mid-long term, be dynamically built by composing services which will be available in an open market of services and resources. In this sense, the grid might be conceived as a world-wide cyber-utility populated by self-* cooperating services which interact as in a complex and gigantic software ecosystem. This will lead to a new style of application development based on software services, which will in turn need the expansion of existing practice regarding service location, standardization, semantics of services, certification, and others. After an introduction on the current European strategies on grid technologies, and on the most recent 1ST FP6 funded European projects, this talk presents the outcome of a group of inde- - pendent experts convened by the European Commission with the objective to draw visions of the future for European grids, and in particular about possible evolutions of GRTDs towards service oriented knowledge utilities
Keywords :
grid computing; CoreGrid; European strategies; QoS; grid computing; grid-aware applications; self-* cooperating services; service oriented knowledge utilities; world-wide cyberutility; Application software; Bridges; Distributed computing; Distributed power generation; Grid computing; Instruments; Mesh generation; Pervasive computing; Resource virtualization; Secure storage;
