Universities struggle to provide both the quantity and diversity of compute resources that their researchers need when their researchers need them. Purchasing resources to meet peak demand for all resource types is cost prohibitive for all but a few institutions. Renting capacity on commercial clouds is seen as an alternative to owning. Commercial clouds though expect to be paid. The Campus Compute Cooperative (CCC) provides an alternative to purchasing capacity from commercial providers that provides increased value to member institutions at reduced cost. Member institutions trade their resources with one another to meet both local peak demand as well as provide access to resource types not available on the local campus that are available elsewhere. Participating institutions have dual roles. First as consumers of resources when their researchers use CCC machines, and second as producers of resources when CCC users from other institutions use their resources. In order to avoid the tragedy of the commons in which everyone only wants to use resources, the resource providers will receive credit when their resources are used by others. The consumer is charged based on the quality of service (high, medium, low) and the particulars of the resource provided (speed, interconnection network, memory, etc.). Account balances are cleared monthly. This paper describes solutions to both the technical and sociopolitical challenges of federating university resources and early results with the CCC. Technical issues include the security model, accounting, job specification/management and user interfaces. Socio-political issues include institutional risk management, how to manage market forces and incentives to avoid sub-optimal outcomes, and budget predictability.

In typical US homes, water heating is the largest energy consumer besides space heating and cooling, and it accounts for approximately 17% of residential energy consumption on average. In this paper, we propose and evaluate a new technique to reduce energy waste due to pipe loss: delivering lower temperature water whenever possible. We created a Smarter Water Heater (SWH) that uses data fusion techniques to infer 1) the fixture being used 2) the mixed water temperature at the fixture 3) the pipe volume for that fixture. After learning a model for each fixture, it solves a control optimization problem to decide when and at what temperature to deliver water to minimize energy use without sacrificing comfort of the user. We evaluated the SWH in three stages. First, we built a physical prototype and measured energy efficiency. We then deployed 18 sensors into a home's piping system for a 50-day in-situ study to stress test the SWH's sensing sub-system. Finally, we collected traces of hot water use from 5 different homes over 10 days each to determine how different water usage habits and piping structures affect energy savings. The results indicate that the SWH reduces total water heating energy by 8--14% with little to no effect on user comfort.