Browsing by Subject "Dynamic optimization"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Dynamic optimization of energy systems with thermal energy storage(2013-08) Powell, Kody Merlin; Edgar, Thomas F.Thermal energy storage (TES), the storage of heat or cooling, is a cost-effective energy storage technology that can greatly enhance the performance of the energy systems with which it interacts. TES acts as a buffer between transient supply and demand of energy. In solar thermal systems, TES enables the power output of the plant to be effectively regulated, despite fluctuating solar irradiance. In district energy systems, TES can be used to shift loads, allowing the system to avoid or take advantage of peak energy prices. The benefit of TES, however, can be significantly enhanced by dynamically optimizing the complete energy system. The ability of TES to shift loads gives the system newfound degrees of freedom which can be exploited to yield optimal performance. In the hybrid solar thermal/fossil fuel system explored in this work, the use of TES enables the system to extract nearly 50% more solar energy when the system is optimized. This requires relaxing some constraints, such as fixed temperature and power control, and dynamically optimizing the over a one-day time horizon. In a district cooling system, TES can help equipment to run more efficiently, by shifting cooling loads, not only between chillers, but temporally, allowing the system to take advantage of the most efficient times for running this equipment. This work also highlights the use of TES in a district energy system, where heat, cooling and electrical power are generated from central locations. Shifting the cooling load frees up electrical generation capacity, which is used to sell power to the grid at peak prices. The combination of optimization, TES, and participation in the electricity market yields a 16% cost savings. The problems encountered in this work require modeling a diverse range of systems including the TES, the solar power plant, boilers, gas and steam turbines, heat recovery equipment, chillers, and pumps. These problems also require novel solution methods that are efficient and effective at obtaining workable solutions. A simultaneous solution method is used for optimizing the solar power plant, while a static/dynamic decoupling method is used for the district energy system.Item Exploiting language abstraction to optimize memory efficiency(2010-08) Sartor, Jennifer Bedke; McKinley, Kathryn S.; Blackburn, Stephen M.; Hirzel, Martin; Keckler, Stephen W.; Witchel, EmmettThe programming language and underlying hardware determine application performance, and both are undergoing revolutionary shifts. As applications have become more sophisticated and capable, programmers have chosen managed languages in many domains for ease of development. These languages abstract memory management from the programmer, which can introduce time and space overhead but also provide opportunities for dynamic optimization. Optimizing memory performance is in part paramount because hardware is reaching physical limits. Recent trends towards chip multiprocessor machines exacerbate the memory system bottleneck because they are adding cores without adding commensurate bandwidth. Both language and architecture trends add stress to the memory system and degrade application performance. This dissertation exploits the language abstraction to analyze and optimize memory efficiency on emerging hardware. We study the sources of memory inefficiencies on two levels: heap data and hardware storage traffic. We design and implement optimizations that change the heap layout of arrays, and use program semantics to eliminate useless memory traffic. These techniques improve memory system efficiency and performance. We first quantitatively characterize the problem by comparing many data compression algorithms and their combinations in a limit study of Java benchmarks. We find that arrays are a dominant source of heap inefficiency. We introduce z-rays, a new array layout design, to bridge the gap between fast access, space efficiency and predictability. Z-rays facilitate compression and offer flexibility, and time and space efficiency. We find that there is a semantic mismatch between managed languages, with their rapid allocation rates, and current hardware, causing unnecessary and excessive traffic in the memory subsystem. We take advantage of the garbage collector's identification of dead data regions, communicating information to the caches to eliminate useless traffic to memory. By reducing traffic and bandwidth, we improve performance. We show that the memory abstraction in managed languages is not just a cost to be borne, but an opportunity to alleviate the memory bottleneck. This thesis shows how to exploit this abstraction to improve space and time efficiency and overcome the memory wall. We enhance the productivity and performance of ubiquitous managed languages on current and future architectures.