Due to their promise for supporting applications society cares about and their unique blend of distributed systems and networking issues, wireless sensor networks (SN) have become an active research area. Most current SN use an arrangement of nodes with limited capabilities. Given SN device technology trends, we believe future SN nodes will have the computational capability of today's handhelds, and communication capabilities well beyond today's 'motes'. Applications will demand these increased capabilities in SN for performing computations in-network on higher bit-rate streaming data. We focus on interesting fusion applications such as automated surveillance. These applications combine one or more input streams via synthesis, or fusion, operations in a hierarchical fashion to produce high-level inference output streams. For SN to successfully support fusion applications, they will need to be constructed to achieve application throughput and latency requirements while minimizing energy usage to increase application lifetime. This thesis investigates novel middleware mechanisms for improving application lifetime while achieving required latency and throughput, in the context of a variety of SN topologies and scales, models of potential fusion applications, and device radio and CPU capabilities. We present a novel architecture, DFuse, for supporting data fusion applications in SN. Using a DFuse implementation and a novel simulator, MSSN, of the DFuse middleware, we investigate several middleware mechanisms for managing energy in SN. We demonstrate reasonable overhead for our prototype DFuse implementation on a small iPAQ SN. We propose and evaluate extensively an elegant distributed, local role-assignment heuristic that dynamically adapts the mapping of a fusion application to the SN, guided by a cost function. Using several studies with DFuse and MSSN, we show that this heuristic scales well and enables significant lifetime extension. We propose and evaluate with MSSN a predictive CPU scaling mechanism for dynamically optimizing energy usage by processors performing fusion. The scaling heuristic seeks to make the ratio of processing time to communication time for each synthesis operation conform to an input parameter. We show how tuning this parameter trades latency degradation for improved lifetime. These investigations demonstrate MSSN's utility for exposing tradeoffs fundamental to successful SN construction.

The Multicore Multithreaded Microprocessor maximizes parallelism on a chip for the optimal system performance, such that its popularity is growing rapidly in high-performance computing. It increases the complexity in resource distribution on a chip by leading it to two directions: isolation and unification. On one hand, multiple cores are implemented to deliver the computation and memory accessing resources to more than one thread at the same time. Nevertheless, it limits the threads’ access to resources in different cores, even if extensively demanded. On the other hand, simultaneous multithreaded architectures unify the domestic execu- tion resources together for concurrently running threads. In such an environment, threads are greatly affected by the inter-thread interference. Moreover, the impacts of the complicated distribution are enlarged by variation in workload behaviors. As a result, the microprocessor requires an adaptive management scheme to schedule threads throughout different cores and coordinate them within cores. In this study, an adaptive thread management scheme was proposed, integrating both hardware and software approaches. The instruction fetch policy at the hardware level took the responsibility by prioritizing domestic threads, while the Operating System scheduler at the software level was used to pair threads dynami- vi cally to multiple cores. The tie between them was the proposed online linear model, which was dynamically constructed for every thread based on data misses by the regression algorithm. Consequently, the hardware part of the proposed scheme proactively granted higher priority to the threads with less predicted long-latency loads, expecting they would better utilize the shared execution resources. Mean- while, the software part was invoked by such a model upon significant changes in the execution phases and paired threads with different demands to the same core to minimize competition on the chip. The proposed scheme was compared to its peer designs and overall 43% speedup was achieved by the integrated approach over the combination of two baseline policies in hardware and software, respectively. The overhead was examined carefully regarding power, area, storage and latency, as well as the relationship between the overhead and the performance.

Dynamic real-time distributed systems are characterized by significant run-time uncertainties at the mission and system levels. Typically, processing and communication latencies in such systems do not have known upper bounds and event and task arrivals and failure occurrences are non-deterministically distributed. This thesis proposes adaptive resource management heuristic techniques for periodic tasks in dynamic real-time distributed systems with the (soft real-time) objective of minimizing missed deadline ratios. The proposed resource management techniques continuously monitor the application tasks at run-time for adherence to the desired real-time requirements, detects timing failures or trends for impending failures (due to workload fluctuations), and dynamically allocate resources by replicating subtasks of application tasks for load sharing. We present "predictive" resource allocation algorithms that determine the number of subtask replicas that are required for adapting the application to a given workload situation using statistical regression theory. The algorithms use regression equations that forecast subtask timeliness as a function of external load parameters such as number of sensor reports and internal resource load parameters such as CPU utilization. The regression equations are determined off-line and on-line from application profiles that are collected off-line and on-line, respectively. To evaluate the performance of the predictive algorithms, we consider algorithms that determine the number of subtask replicas using empirically determined functions. The empirical functions compute the number of replicas as a function of the rate of change in the application workload during a "window" of past task periods. We implemented the resource management algorithms as part of a middleware infrastructure and measured the performance of the algorithms using a real-time benchmark. The experimental results indicate that the predictive, regression theory-based algorithms generally produce lower missed deadline ratios than the empirical strategies under the workload conditions that were studied. / Master of Science