<p>We study techniques to enforce and provision differentiated service levels in <i>Computational Grid</i> systems. The Grid offers simplified provisioning of peak-capacity for applications with computational requirements beyond local machines and clusters, by sharing resources across organizational boundaries. Current systems have focussed on access control, i.e., managing who is allowed to run applications on remote sites. Very little work has been done on providing differentiated service levels for those applications that are admitted. This leads to a number of problems when scheduling jobs in a fair and efficient way. For example, users with a large number of long-running jobs could starve out others, both intentionally and non-intentionally. We investigate the requirements of High Performance Computing (HPC) applications that run in academic Grid systems, and propose two models of service-level management. Our first model is based on global real-time quota enforcement, where projects are granted resource quota, such as CPU hours, across the Grid by a centralized allocation authority. We implement the SweGrid Accounting System to enforce quota allocated by the Swedish National Allocations Committee in the SweGrid production Grid, which connects six Swedish HPC centers. A flexible authorization policy framework allows provisioning and enforcement of two different service levels across the SweGrid clusters; high-priority and low-priority jobs. As a solution to more fine-grained control over service levels we propose and implement a <i>Grid</i> <i>Market </i>system, using a market-based resource allocator called Tycoon. The conclusion of our research is that although the Grid accounting solution offers better service level enforcement support than state-of-the-art production Grid systems, it turned out to be complex to set the resource price and other policies manually, while ensuring fairness and efficiency of the system. Our Grid Market on the other hand sets the price according to the dynamic demand, and it is further incentive compatible, in that the overall system state remains healthy even in the presence of strategic users.</p>

The market for off-grid solar solutions in Kenya has developed rapidly the recent years. The growth has required capital and access to finance, which has been mainly provided by foreign investors. This thesis examines the perceived risks on the market for off-grid solar solutions in Kenya through a series of interviews with actors engaged in the market. The purpose of the thesis is to investigate the access to capital and highlight the perceived risks that might constrain a continued positive development of the market in Kenya. The findings of this thesis categorize the perceived risks on the market as political, economic, social, technological, legal and environmental (see full report table 2 in section 8 for sub categories). The companies engaged in the market for off-grid solar solutions should be differentiated based on their business model. This since their different value chains entails specific in risks. This study uses two modified value chains to highlight the differences in retail and distribution between the two defined market segments: product and utility. The product segment includes small-scale solar products often referred to as PICO-products and Solar-Home-Systems (SHS), which by being sold on installment now provides basic electricity to a growing number of people in Kenya. The utility segment includes minigrids with solar energy as power supply. This segment is subject to specific regulations regarding installations and operations, which is one of the main contributing factors to the difference in risks compared to the product segment. The other main factor is the way the respective segment distributes and retails their products/electricity. The distribution for the product segment is done by regular land transportation and customer interaction through sales agents, providing basic access to electricity. While the minigrids uses a local distribution grid to provide access to electricity. This leads to specific risks within the categorizes social, technological and legal risk. This study shows that the lack of understanding of the different market segments and their context specific risks, pose a risk to the market reputation and the local actors access to finance. The absence of knowledge about the difference in risks causes generalizations to be done, both from financiers who might place their funding elsewhere, and the customers who might choose other solutions than solar to fulfill their energy needs. The uncertainty of the future development and the position of the national regulations on the market together with the two segments creates barriers for future access to finance. Access that is required to build and boost the market even further.

We study techniques to enforce and provision differentiated service levels in Computational Grid systems. The Grid offers simplified provisioning of peak-capacity for applications with computational requirements beyond local machines and clusters, by sharing resources across organizational boundaries. Current systems have focussed on access control, i.e., managing who is allowed to run applications on remote sites. Very little work has been done on providing differentiated service levels for those applications that are admitted. This leads to a number of problems when scheduling jobs in a fair and efficient way. For example, users with a large number of long-running jobs could starve out others, both intentionally and non-intentionally. We investigate the requirements of High Performance Computing (HPC) applications that run in academic Grid systems, and propose two models of service-level management. Our first model is based on global real-time quota enforcement, where projects are granted resource quota, such as CPU hours, across the Grid by a centralized allocation authority. We implement the SweGrid Accounting System to enforce quota allocated by the Swedish National Allocations Committee in the SweGrid production Grid, which connects six Swedish HPC centers. A flexible authorization policy framework allows provisioning and enforcement of two different service levels across the SweGrid clusters; high-priority and low-priority jobs. As a solution to more fine-grained control over service levels we propose and implement a Grid Market system, using a market-based resource allocator called Tycoon. The conclusion of our research is that although the Grid accounting solution offers better service level enforcement support than state-of-the-art production Grid systems, it turned out to be complex to set the resource price and other policies manually, while ensuring fairness and efficiency of the system. Our Grid Market on the other hand sets the price according to the dynamic demand, and it is further incentive compatible, in that the overall system state remains healthy even in the presence of strategic users. / QC 20101116