Event mining for system and service management

Modern IT infrastructures are constructed by large scale computing systems and administered by IT service providers. Manually maintaining such large computing systems is costly and inefficient. Service providers often seek automatic or semi-automatic methodologies of detecting and resolving system issues to improve their service quality and efficiency. This dissertation investigates several data-driven approaches for assisting service providers in achieving this goal. The detailed problems studied by these approaches can be categorized into the three aspects in the service workflow: 1) preprocessing raw textual system logs to structural events; 2) refining monitoring configurations for eliminating false positives and false negatives; 3) improving the efficiency of system diagnosis on detected alerts. Solving these problems usually requires a huge amount of domain knowledge about the particular computing systems. The approaches investigated by this dissertation are developed based on event mining algorithms, which are able to automatically derive part of that knowledge from the historical system logs, events and tickets. ^ In particular, two textual clustering algorithms are developed for converting raw textual logs into system events. For refining the monitoring configuration, a rule based alert prediction algorithm is proposed for eliminating false alerts (false positives) without losing any real alert and a textual classification method is applied to identify the missing alerts (false negatives) from manual incident tickets. For system diagnosis, this dissertation presents an efficient algorithm for discovering the temporal dependencies between system events with corresponding time lags, which can help the administrators to determine the redundancies of deployed monitoring situations and dependencies of system components. To improve the efficiency of incident ticket resolving, several KNN-based algorithms that recommend relevant historical tickets with resolutions for incoming tickets are investigated. Finally, this dissertation offers a novel algorithm for searching similar textual event segments over large system logs that assists administrators to locate similar system behaviors in the logs. Extensive empirical evaluation on system logs, events and tickets from real IT infrastructures demonstrates the effectiveness and efficiency of the proposed approaches.^

Optimizing the radiation pattern of smart antennas using genetic algorithms

This work is directed towards optimizing the radiation pattern of smart antennas using genetic algorithms. The structure of the smart antennas based on Space Division Multiple Access (SDMA) is proposed. It is composed of adaptive antennas, each of which has adjustable weight elements for amplitudes and phases of signals. The corresponding radiation pattern formula available for the utilization of numerical optimization techniques is deduced. Genetic algorithms are applied to search the best phase-amplitude weights or phase-only weights with which the optimal radiation pattern can be achieved. ^ One highlight of this work is the proposed optimal radiation pattern concept and its implementation by genetic algorithms. The results show that genetic algorithms are effective for the true Signal-Interference-Ratio (SIR) design of smart antennas. This means that not only nulls can be put in the directions of the interfering signals but also simultaneously main lobes can be formed in the directions of the desired signals. The optimal radiation pattern of a smart antenna possessing SDMA ability has been achieved. ^ The second highlight is on the weight search by genetic algorithms for the optimal radiation pattern design of antennas having more than one interfering signal. The regular criterion for determining which chromosome should be kept for the next step iteration is modified so as to improve the performance of the genetic algorithm iteration. The results show that the modified criterion can speed up and guarantee the iteration to be convergent. ^ In addition, the comparison between phase-amplitude perturbations and phase-only perturbations for the radiation pattern design of smart antennas are carried out. The effects of parameters used by the genetic algorithm on the optimal radiation pattern design are investigated. Valuable results are obtained. ^

Optimization of adaptive traffic signal control with transit signal priority at isolated intersections using parallel genetic algorithms

Optimization of adaptive traffic signal timing is one of the most complex problems in traffic control systems. This dissertation presents a new method that applies the parallel genetic algorithm (PGA) to optimize adaptive traffic signal control in the presence of transit signal priority (TSP). The method can optimize the phase plan, cycle length, and green splits at isolated intersections with consideration for the performance of both the transit and the general vehicles. Unlike the simple genetic algorithm (GA), PGA can provide better and faster solutions needed for real-time optimization of adaptive traffic signal control. ^ An important component in the proposed method involves the development of a microscopic delay estimation model that was designed specifically to optimize adaptive traffic signal with TSP. Macroscopic delay models such as the Highway Capacity Manual (HCM) delay model are unable to accurately consider the effect of phase combination and phase sequence in delay calculations. In addition, because the number of phases and the phase sequence of adaptive traffic signal may vary from cycle to cycle, the phase splits cannot be optimized when the phase sequence is also a decision variable. A "flex-phase" concept was introduced in the proposed microscopic delay estimation model to overcome these limitations. ^ The performance of PGA was first evaluated against the simple GA. The results show that PGA achieved both faster convergence and lower delay for both under- or over-saturated traffic conditions. A VISSIM simulation testbed was then developed to evaluate the performance of the proposed PGA-based adaptive traffic signal control with TSP. The simulation results show that the PGA-based optimizer for adaptive TSP outperformed the fully actuated NEMA control in all test cases. The results also show that the PGA-based optimizer was able to produce TSP timing plans that benefit the transit vehicles while minimizing the impact of TSP on the general vehicles. The VISSIM testbed developed in this research provides a powerful tool to design and evaluate different TSP strategies under both actuated and adaptive signal control. ^

Design strategies for an artificial neural network based algorithm for automatic incident detection on major arterial streets

Traffic incidents are non-recurring events that can cause a temporary reduction in roadway capacity. They have been recognized as a major contributor to traffic congestion on our nation’s highway systems. To alleviate their impacts on capacity, automatic incident detection (AID) has been applied as an incident management strategy to reduce the total incident duration. AID relies on an algorithm to identify the occurrence of incidents by analyzing real-time traffic data collected from surveillance detectors. Significant research has been performed to develop AID algorithms for incident detection on freeways; however, similar research on major arterial streets remains largely at the initial stage of development and testing. This dissertation research aims to identify design strategies for the deployment of an Artificial Neural Network (ANN) based AID algorithm for major arterial streets. A section of the US-1 corridor in Miami-Dade County, Florida was coded in the CORSIM microscopic simulation model to generate data for both model calibration and validation. To better capture the relationship between the traffic data and the corresponding incident status, Discrete Wavelet Transform (DWT) and data normalization were applied to the simulated data. Multiple ANN models were then developed for different detector configurations, historical data usage, and the selection of traffic flow parameters. To assess the performance of different design alternatives, the model outputs were compared based on both detection rate (DR) and false alarm rate (FAR). The results show that the best models were able to achieve a high DR of between 90% and 95%, a mean time to detect (MTTD) of 55-85 seconds, and a FAR below 4%. The results also show that a detector configuration including only the mid-block and upstream detectors performs almost as well as one that also includes a downstream detector. In addition, DWT was found to be able to improve model performance, and the use of historical data from previous time cycles improved the detection rate. Speed was found to have the most significant impact on the detection rate, while volume was found to contribute the least. The results from this research provide useful insights on the design of AID for arterial street applications.

Algorithms for scheduling parallel batch processing machines with non-identical job ready times

This research is motivated by a practical application observed at a printed circuit board (PCB) manufacturing facility. After assembly, the PCBs (or jobs) are tested in environmental stress screening (ESS) chambers (or batch processing machines) to detect early failures. Several PCBs can be simultaneously tested as long as the total size of all the PCBs in the batch does not violate the chamber capacity. PCBs from different production lines arrive dynamically to a queue in front of a set of identical ESS chambers, where they are grouped into batches for testing. Each line delivers PCBs that vary in size and require different testing (or processing) times. Once a batch is formed, its processing time is the longest processing time among the PCBs in the batch, and its ready time is given by the PCB arriving last to the batch. ESS chambers are expensive and a bottleneck. Consequently, its makespan has to be minimized. ^ A mixed-integer formulation is proposed for the problem under study and compared to a formulation recently published. The proposed formulation is better in terms of the number of decision variables, linear constraints and run time. A procedure to compute the lower bound is proposed. For sparse problems (i.e. when job ready times are dispersed widely), the lower bounds are close to optimum. ^ The problem under study is NP-hard. Consequently, five heuristics, two metaheuristics (i.e. simulated annealing (SA) and greedy randomized adaptive search procedure (GRASP)), and a decomposition approach (i.e. column generation) are proposed—especially to solve problem instances which require prohibitively long run times when a commercial solver is used. Extensive experimental study was conducted to evaluate the different solution approaches based on the solution quality and run time. ^ The decomposition approach improved the lower bounds (or linear relaxation solution) of the mixed-integer formulation. At least one of the proposed heuristic outperforms the Modified Delay heuristic from the literature. For sparse problems, almost all the heuristics report a solution close to optimum. GRASP outperforms SA at a higher computational cost. The proposed approaches are viable to implement as the run time is very short. ^

Efficient asynchronous scheduling algorithms for cost-effective buffered crossbar switches

Buffered crossbar switches have recently attracted considerable attention as the next generation of high speed interconnects. They are a special type of crossbar switches with an exclusive buffer at each crosspoint of the crossbar. They demonstrate unique advantages over traditional unbuffered crossbar switches, such as high throughput, low latency, and asynchronous packet scheduling. However, since crosspoint buffers are expensive on-chip memories, it is desired that each crosspoint has only a small buffer. This dissertation proposes a series of practical algorithms and techniques for efficient packet scheduling for buffered crossbar switches. To reduce the hardware cost of such switches and make them scalable, we considered partially buffered crossbars, whose crosspoint buffers can be of an arbitrarily small size. Firstly, we introduced a hybrid scheme called Packet-mode Asynchronous Scheduling Algorithm (PASA) to schedule best effort traffic. PASA combines the features of both distributed and centralized scheduling algorithms and can directly handle variable length packets without Segmentation And Reassembly (SAR). We showed by theoretical analysis that it achieves 100% throughput for any admissible traffic in a crossbar with a speedup of two. Moreover, outputs in PASA have a large probability to avoid the more time-consuming centralized scheduling process, and thus make fast scheduling decisions. Secondly, we proposed the Fair Asynchronous Segment Scheduling (FASS) algorithm to handle guaranteed performance traffic with explicit flow rates. FASS reduces the crosspoint buffer size by dividing packets into shorter segments before transmission. It also provides tight constant performance guarantees by emulating the ideal Generalized Processor Sharing (GPS) model. Furthermore, FASS requires no speedup for the crossbar, lowering the hardware cost and improving the switch capacity. Thirdly, we presented a bandwidth allocation scheme called Queue Length Proportional (QLP) to apply FASS to best effort traffic. QLP dynamically obtains a feasible bandwidth allocation matrix based on the queue length information, and thus assists the crossbar switch to be more work-conserving. The feasibility and stability of QLP were proved, no matter whether the traffic distribution is uniform or non-uniform. Hence, based on bandwidth allocation of QLP, FASS can also achieve 100% throughput for best effort traffic in a crossbar without speedup.

Digital surveillance based on video CODEC System-on-a-Chip (SoC) platforms

Today, most conventional surveillance networks are based on analog system, which has a lot of constraints like manpower and high-bandwidth requirements. It becomes the barrier for today's surveillance network development. This dissertation describes a digital surveillance network architecture based on the H.264 coding/decoding (CODEC) System-on-a-Chip (SoC) platform. The proposed digital surveillance network architecture includes three major layers: software layer, hardware layer, and the network layer. The following outlines the contributions to the proposed digital surveillance network architecture. (1) We implement an object recognition system and an object categorization system on the software layer by applying several Digital Image Processing (DIP) algorithms. (2) For better compression ratio and higher video quality transfer, we implement two new modules on the hardware layer of the H.264 CODEC core, i.e., the background elimination module and the Directional Discrete Cosine Transform (DDCT) module. (3) Furthermore, we introduce a Digital Signal Processor (DSP) sub-system on the main bus of H.264 SoC platforms as the major hardware support system for our software architecture. Thus we combine the software and hardware platforms to be an intelligent surveillance node. Lab results show that the proposed surveillance node can dramatically save the network resources like bandwidth and storage capacity.

In vivo tissue diagnosis for myocardial infarction using optical spectroscopy with novel spectral interpretation algorithms

In recent decades, the rapid development of optical spectroscopy for tissue diagnosis has been indicative of its high clinical value. The goal of this research is to prove the feasibility of using diffuse reflectance spectroscopy and fluorescence spectroscopy to assess myocardial infarction (MI) in vivo. The proposed optical technique was designed to be an intra-operative guidance tool that can provide useful information about the condition of an infarct for surgeons and researchers. ^ In order to gain insight into the pathophysiological characteristics of an infarct, two novel spectral analysis algorithms were developed to interpret diffuse reflectance spectra. The algorithms were developed based on the unique absorption properties of hemoglobin for the purpose of retrieving regional hemoglobin oxygenation saturation and concentration data in tissue from diffuse reflectance spectra. The algorithms were evaluated and validated using simulated data and actual experimental data. ^ Finally, the hypothesis of the study was validated using a rabbit model of MI. The mechanism by which the MI was induced was the ligation of a major coronary artery of the left ventricle. Three to four weeks after the MI was induced, the extent of myocardial tissue injury and the evolution of the wound healing process were investigated using the proposed spectroscopic methodology as well as histology. The correlations between spectral alterations and histopathological features of the MI were analyzed statistically. ^ The results of this PhD study demonstrate the applicability of the proposed optical methodology for assessing myocardial tissue damage induced by MI in vivo. The results of the spectral analysis suggest that connective tissue proliferation induced by MI significantly alter the characteristics of diffuse reflectance and fluorescence spectra. The magnitudes of the alterations could be quantitatively related to the severity and extensiveness of connective tissue proliferation.^

Efficiency and power density improvement of grid-connected hybrid renewable energy systems utilizing high frequency-based power converters

High efficiency of power converters placed between renewable energy sources and the utility grid is required to maximize the utilization of these sources. Power quality is another aspect that requires large passive elements (inductors, capacitors) to be placed between these sources and the grid. The main objective is to develop higher-level high frequency-based power converter system (HFPCS) that optimizes the use of hybrid renewable power injected into the power grid. The HFPCS provides high efficiency, reduced size of passive components, higher levels of power density realization, lower harmonic distortion, higher reliability, and lower cost. The dynamic modeling for each part in this system is developed, simulated and tested. The steady-state performance of the grid-connected hybrid power system with battery storage is analyzed. Various types of simulations were performed and a number of algorithms were developed and tested to verify the effectiveness of the power conversion topologies. A modified hysteresis-control strategy for the rectifier and the battery charging/discharging system was developed and implemented. A voltage oriented control (VOC) scheme was developed to control the energy injected into the grid. The developed HFPCS was compared experimentally with other currently available power converters. The developed HFPCS was employed inside a microgrid system infrastructure, connecting it to the power grid to verify its power transfer capabilities and grid connectivity. Grid connectivity tests verified these power transfer capabilities of the developed converter in addition to its ability of serving the load in a shared manner. In order to investigate the performance of the developed system, an experimental setup for the HF-based hybrid generation system was constructed. We designed a board containing a digital signal processor chip on which the developed control system was embedded. The board was fabricated and experimentally tested. The system's high precision requirements were verified. Each component of the system was built and tested separately, and then the whole system was connected and tested. The simulation and experimental results confirm the effectiveness of the developed converter system for grid-connected hybrid renewable energy systems as well as for hybrid electric vehicles and other industrial applications.

Web Based Bicycle Trip Planning for Broward County, Florida

To promote the use of bicycle transportation mode in times of increasing urban traffic congestion, Broward County Metropolitan Planning Organization funded the development of a Web-based trip planner for cyclists. This presentation demonstrates the integration of the ArcGIS Server 9.3 environment with the ArcGIS JavaScript Extension for Google Maps API and the Google Local Search Control for Maps API. This allows the use of Google mashup GIS functionality, i.e., Google local search for selection of trip start, trip destination, and intermediate waypoints, and the integration of Google Maps base layers. The ArcGIS Network Analyst extension is used for the route search, where algorithms for fastest, safest, simplest, most scenic, and shortest routes are imbedded. This presentation also describes how attributes of the underlying network sources have been combined to facilitate the search for optimized routes.

Development of physics-based models and design optimization of power electronic conversion systems

The main objective for physics based modeling of the power converter components is to design the whole converter with respect to physical and operational constraints. Therefore, all the elements and components of the energy conversion system are modeled numerically and combined together to achieve the whole system behavioral model. Previously proposed high frequency (HF) models of power converters are based on circuit models that are only related to the parasitic inner parameters of the power devices and the connections between the components. This dissertation aims to obtain appropriate physics-based models for power conversion systems, which not only can represent the steady state behavior of the components, but also can predict their high frequency characteristics. The developed physics-based model would represent the physical device with a high level of accuracy in predicting its operating condition. The proposed physics-based model enables us to accurately develop components such as; effective EMI filters, switching algorithms and circuit topologies [7]. One of the applications of the developed modeling technique is design of new sets of topologies for high-frequency, high efficiency converters for variable speed drives. The main advantage of the modeling method, presented in this dissertation, is the practical design of an inverter for high power applications with the ability to overcome the blocking voltage limitations of available power semiconductor devices. Another advantage is selection of the best matching topology with inherent reduction of switching losses which can be utilized to improve the overall efficiency. The physics-based modeling approach, in this dissertation, makes it possible to design any power electronic conversion system to meet electromagnetic standards and design constraints. This includes physical characteristics such as; decreasing the size and weight of the package, optimized interactions with the neighboring components and higher power density. In addition, the electromagnetic behaviors and signatures can be evaluated including the study of conducted and radiated EMI interactions in addition to the design of attenuation measures and enclosures.

An epistemic event -based correlation scheme for pervasive network management

Computer networks produce tremendous amounts of event-based data that can be collected and managed to support an increasing number of new classes of pervasive applications. Examples of such applications are network monitoring and crisis management. Although the problem of distributed event-based management has been addressed in the non-pervasive settings such as the Internet, the domain of pervasive networks has its own characteristics that make these results non-applicable. Many of these applications are based on time-series data that possess the form of time-ordered series of events. Such applications also embody the need to handle large volumes of unexpected events, often modified on-the-fly, containing conflicting information, and dealing with rapidly changing contexts while producing results with low-latency. Correlating events across contextual dimensions holds the key to expanding the capabilities and improving the performance of these applications. This dissertation addresses this critical challenge. It establishes an effective scheme for complex-event semantic correlation. The scheme examines epistemic uncertainty in computer networks by fusing event synchronization concepts with belief theory. Because of the distributed nature of the event detection, time-delays are considered. Events are no longer instantaneous, but duration is associated with them. Existing algorithms for synchronizing time are split into two classes, one of which is asserted to provide a faster means for converging time and hence better suited for pervasive network management. Besides the temporal dimension, the scheme considers imprecision and uncertainty when an event is detected. A belief value is therefore associated with the semantics and the detection of composite events. This belief value is generated by a consensus among participating entities in a computer network. The scheme taps into in-network processing capabilities of pervasive computer networks and can withstand missing or conflicting information gathered from multiple participating entities. Thus, this dissertation advances knowledge in the field of network management by facilitating the full utilization of characteristics offered by pervasive, distributed and wireless technologies in contemporary and future computer networks.

Next generation of recommender systems: Algorithms and applications

Personalized recommender systems aim to assist users in retrieving and accessing interesting items by automatically acquiring user preferences from the historical data and matching items with the preferences. In the last decade, recommendation services have gained great attention due to the problem of information overload. However, despite recent advances of personalization techniques, several critical issues in modern recommender systems have not been well studied. These issues include: (1) understanding the accessing patterns of users (i.e., how to effectively model users' accessing behaviors); (2) understanding the relations between users and other objects (i.e., how to comprehensively assess the complex correlations between users and entities in recommender systems); and (3) understanding the interest change of users (i.e., how to adaptively capture users' preference drift over time). To meet the needs of users in modern recommender systems, it is imperative to provide solutions to address the aforementioned issues and apply the solutions to real-world applications. ^ The major goal of this dissertation is to provide integrated recommendation approaches to tackle the challenges of the current generation of recommender systems. In particular, three user-oriented aspects of recommendation techniques were studied, including understanding accessing patterns, understanding complex relations and understanding temporal dynamics. To this end, we made three research contributions. First, we presented various personalized user profiling algorithms to capture click behaviors of users from both coarse- and fine-grained granularities; second, we proposed graph-based recommendation models to describe the complex correlations in a recommender system; third, we studied temporal recommendation approaches in order to capture the preference changes of users, by considering both long-term and short-term user profiles. In addition, a versatile recommendation framework was proposed, in which the proposed recommendation techniques were seamlessly integrated. Different evaluation criteria were implemented in this framework for evaluating recommendation techniques in real-world recommendation applications. ^ In summary, the frequent changes of user interests and item repository lead to a series of user-centric challenges that are not well addressed in the current generation of recommender systems. My work proposed reasonable solutions to these challenges and provided insights on how to address these challenges using a simple yet effective recommendation framework.^

Web Based Bicycle Trip Planning for Broward County, Florida

To promote the use of bicycle transportation mode in times of increasing urban traffic congestion, Broward County Metropolitan Planning Organization funded the development of a Web-based trip planner for cyclists. This presentation demonstrates the integration of the ArcGIS Server 9.3 environment with the ArcGIS JavaScript Extension for Google Maps API and the Google Local Search Control for Maps API. This allows the use of Google mashup GIS functionality, i.e., Google local search for selection of trip start, trip destination, and intermediate waypoints, and the integration of Google Maps base layers. The ArcGIS Network Analyst extension is used for the route search, where algorithms for fastest, safest, simplest, most scenic, and shortest routes are imbedded. This presentation also describes how attributes of the underlying network sources have been combined to facilitate the search for optimized routes.

Design Strategies for an Artificial Neural Network Based Algorithm for Automatic Incident Detection on Major Arterial Streets

Traffic incidents are non-recurring events that can cause a temporary reduction in roadway capacity. They have been recognized as a major contributor to traffic congestion on our national highway systems. To alleviate their impacts on capacity, automatic incident detection (AID) has been applied as an incident management strategy to reduce the total incident duration. AID relies on an algorithm to identify the occurrence of incidents by analyzing real-time traffic data collected from surveillance detectors. Significant research has been performed to develop AID algorithms for incident detection on freeways; however, similar research on major arterial streets remains largely at the initial stage of development and testing. This dissertation research aims to identify design strategies for the deployment of an Artificial Neural Network (ANN) based AID algorithm for major arterial streets. A section of the US-1 corridor in Miami-Dade County, Florida was coded in the CORSIM microscopic simulation model to generate data for both model calibration and validation. To better capture the relationship between the traffic data and the corresponding incident status, Discrete Wavelet Transform (DWT) and data normalization were applied to the simulated data. Multiple ANN models were then developed for different detector configurations, historical data usage, and the selection of traffic flow parameters. To assess the performance of different design alternatives, the model outputs were compared based on both detection rate (DR) and false alarm rate (FAR). The results show that the best models were able to achieve a high DR of between 90% and 95%, a mean time to detect (MTTD) of 55-85 seconds, and a FAR below 4%. The results also show that a detector configuration including only the mid-block and upstream detectors performs almost as well as one that also includes a downstream detector. In addition, DWT was found to be able to improve model performance, and the use of historical data from previous time cycles improved the detection rate. Speed was found to have the most significant impact on the detection rate, while volume was found to contribute the least. The results from this research provide useful insights on the design of AID for arterial street applications.