Performance of Scheduling Policies in Adversarial Networks with Non-synchronized Clocks

In this paper we generalize the Continuous Adversarial Queuing Theory (CAQT) model (Blesa et al. in MFCS, Lecture Notes in Computer Science, vol. 3618, pp. 144–155, 2005) by considering the possibility that the router clocks in the network are not synchronized. We name the new model Non Synchronized CAQT (NSCAQT). Clearly, this new extension to the model only affects those scheduling policies that use some form of timing. In a first approach we consider the case in which although not synchronized, all clocks run at the same speed, maintaining constant differences. In this case we show that all universally stable policies in CAQT that use the injection time and the remaining path to schedule packets remain universally stable. These policies include, for instance, Shortest in System (SIS) and Longest in System (LIS). Then, we study the case in which clock differences can vary over time, but the maximum difference is bounded. In this model we show the universal stability of two families of policies related to SIS and LIS respectively (the priority of a packet in these policies depends on the arrival time and a function of the path traversed). The bounds we obtain in this case depend on the maximum difference between clocks. This is a necessary requirement, since we also show that LIS is not universally stable in systems without bounded clock difference. We then present a new policy that we call Longest in Queues (LIQ), which gives priority to the packet that has been waiting the longest in edge queues. This policy is universally stable and, if clocks maintain constant differences, the bounds we prove do not depend on them. To finish, we provide with simulation results that compare the behavior of some of these policies in a network with stochastic injection of packets.

Performance of Scheduling Policies in Adversarial Networks with Non-synchronized Clocks

In this paper we generalize the Continuous Adversarial Queuing Theory (CAQT) model (Blesa et al. in MFCS, Lecture Notes in Computer Science, vol. 3618, pp. 144–155, 2005) by considering the possibility that the router clocks in the network are not synchronized. We name the new model Non Synchronized CAQT (NSCAQT). Clearly, this new extension to the model only affects those scheduling policies that use some form of timing. In a first approach we consider the case in which although not synchronized, all clocks run at the same speed, maintaining constant differences. In this case we show that all universally stable policies in CAQT that use the injection time and the remaining path to schedule packets remain universally stable. These policies include, for instance, Shortest in System (SIS) and Longest in System (LIS). Then, we study the case in which clock differences can vary over time, but the maximum difference is bounded. In this model we show the universal stability of two families of policies related to SIS and LIS respectively (the priority of a packet in these policies depends on the arrival time and a function of the path traversed). The bounds we obtain in this case depend on the maximum difference between clocks. This is a necessary requirement, since we also show that LIS is not universally stable in systems without bounded clock difference. We then present a new policy that we call Longest in Queues (LIQ), which gives priority to the packet that has been waiting the longest in edge queues. This policy is universally stable and, if clocks maintain constant differences, the bounds we prove do not depend on them. To finish, we provide with simulation results that compare the behavior of some of these policies in a network with stochastic injection of packets.

A dual-band priority assignment algorithm for dynamic QoS resource management

Future high-quality consumer electronics will contain a number of applications running in a highly dynamic environment, and their execution will need to be efficiently arbitrated by the underlying platform software. The multimedia applications that currently execute in such similar contexts face frequent run-time variations in their resource demands, originated by the greedy nature of the multimedia processing itself. Changes in resource demands are triggered by numerous reasons (e.g. a switch in the input media compression format). Such situations require real-time adaptation mechanisms to adjust the system operation to the new requirements, and this must be done seamlessly to satisfy the user experience. One solution for efficiently managing application execution is to apply quality of service resource management techniques, based on assigning and enforcing resource contracts to applications. Most resource management solutions provide temporal isolation by enforcing resource assignments and avoiding any resource overruns. However, this has a clear limitation over the cost-effective resource usage. This paper presents a simple priority assignment scheme based on uniform priority bands to allow that greedy multimedia tasks incur in safe overruns that increase resource usage and do not threaten the timely execution of non-overrunning tasks. Experimental results show that the proposed priority assignment scheme in combination with a resource accounting mechanism preserves timely multimedia execution and delivery, achieves a higher cost-effective processor usage, and guarantees the execution isolation of non-overrunning tasks.

Multi-hazard analysis and identification of priority settlements for land management in Haiti

Seismic hazard study in “La Hispaniola” island in connection with the land tenure situation in the region, in order to define priority areas with a high risk, where some land management recommendations are proposed. The seismic hazard assessment has been carried out following the probabilistic method with a seismogenic zonation and including the major faults of the region as independent units. In order to identify the priority areas, it has taken into account, besides the seismic hazard study, the map of changes of static Coulomb failure stress and the landslide hazard map.

Herramienta de apoyo a la docencia en sistemas operativos

El proyecto fin de carrera de herramienta de apoyo a la docencia en Sistemas Operativos quiere ayudar al alumno a entender el funcionamiento de un planificador a corto plazo. Lo hace mediante una representación gráfica de procesos que ocupan o el procesador o distintas unidades de entrada/salida mientras transcurre el tiempo. El tiempo está dividido en ciclos de reloj de un procesador, a lo que a continuación se referirá como unidades de tiempo. Los procesos están definidos por su nombre, la instante de entrada que entran al sistema, su prioridad y la secuencia de unidades de tiempo en el procesador y unidades de entrada/salida que necesitan para terminar su trabajo. El alumno puede configurar el sistema a su gusto en cuanto al número y comportamiento de las unidades de entrada/salida. Puede definir que una unidad solo permita acceso exclusivo a los procesos, es decir que solo un proceso puede ocuparla simultáneamente, o que permita el acceso múltiple a sus recursos. El alumno puede construir un planificador a corto plazo propio, integrarlo en el sistema y ver cómo se comporta. Se debe usar la interfaz Java proporcionada para su construcción. La aplicación muestra datos estadísticos como por ejemplo la eficiencia del sistema (el tiempo activo de la CPU dividido por el tiempo total de la simulación), tiempos de espera de los procesos, etc. Se calcula después de cada unidad de tiempo para que el alumno pueda ver el momento exacto donde la simulación tomó un giro inesperado. La aplicación está compuesta por un motor de simulación que contiene toda la lógica y un conjunto de clases que forman la interfaz gráfica que se presenta al usuario. Estos dos componentes pueden ser reemplazados siempre y cuando se mantenga la definición de sus conectores igual. La aplicación la he hecho de manejo muy simple e interfaz fácil de comprender para que el alumno pueda dedicar todo su tiempo a probar distintas configuraciones y situaciones y así entender mejor la asignatura. ABSTRACT. The project is called “Tool to Support Teaching of the Subject Operating Systems” and is an application that aims to help students understand on a deeper level the inner workings of how an operating system handles multiple processes in need of CPU time by the means of a short-term planning algorithm. It does so with a graphical representation of the processes that occupy the CPU and different input/output devices as time passes by. Time is divided in CPU cycles, from now on referred to as time units. The processes are defined by their name, the moment they enter the system, their priority and the sequence of time units they need to finish their job. The student can configure the system by changing the number and behavior of the input/output devices. He or she can define whether a device should only allow exclusive access, i.e. only one process can occupy it at any given time, or if it should allow multiple processes to access its resources. The student can build a planning algorithm of his or her own and easily integrate it into the system to see how it behaves. The provided Java interface and the programming language Java should be used to build it. The application shows statistical data, e.g. the efficiency of the system (active CPU time divided by total simulation time) and time spent by the processes waiting in queues. The data are calculated after passing each time unit in order for the student to see the exact moment where the simulation took an unexpected turn. The application is comprised of a simulation motor, which handles all the logic, and a set of classes, which is the graphical user interface. These two parts can be replaced individually if the definition of the connecting interfaces stays the same. I have made the application to be very easy to use and with an easy to understand user interface so the student can spend all of his or her time trying out different configurations and scenarios in order to understand the subject better.

Incorporating equity into transport planning: utility, priority and sufficiency approaches

The analysis addresses the issue of transport equity and explores three different approaches to equity in transport: utilitarianism, sufficientarianism and prioritarianism. Each approach calls for a different treatment of the benefits reaped by different population groups in the assessment of transport investments or policies. In utilitarianism, which underlies much of the current practice of transport project appraisal, all benefits receive the same weight, irrespective of the recipient of the benefits. In both sufficientarianism and prioritarianism, benefits are weighed in distinct ways, depending on the characteristics of the recipients. The three approaches are illustrated using a fictive case study, in which three different transport investment are assessed and compared to each other. Finally, the assessment of transport investments will be explored using the cost-effectiveness analysis (CEA). The CEA assesses the distributional effects of transport investments for utilitarism, sufficientarism and prioritarism approaches and addresses distinct needs associated with different population groups in respect to their transport