Edward A. Billard

Effects of delayed communication in dynamic group formation

We investigate how delayed communication affects the dynamic formation of groups in distributed systems, where all decision-making agents join the same group because each expects to improve its own performance. For example, distributed job schedulers may form a group to utilize the idle resources of other members within the group. Forming a group is a search problem and we examine agents that use the feedback mechanism of stochastic learning automata to carry out this search. Although a group formation may have the potential for synergy, the agents must successfully coordinate their actions within the group relevant to the application. For example, job schedulers who form a group must still balance the load among the shared resources; that is, the collective actions of the schedulers need to be coordinated and greedy schedulers who all pick the same processor may not be successful. Agents may find that working alone is more desirable since their actions need not be coordinated and the results of their own actions are more predictable. An additional challenge to the search problem is to cope with the delay in communication between the agents. The purpose of this study is to model systems where agents adaptively search for compatible co-workers, under the constraint of delayed communication. With insufficient communication, the agents decide to work alone (and receive a modest benefit) but, with sufficient communication, the agents make the more advantageous decision to work together. >

Adaptive coordination in distributed systems with delayed communication

A new model for distributed decision making, distributed game automata, focuses on how communication affects the quality of decisions. The goal is to limit communication between decision makers such that overhead costs are reduced but good decisions still result. Learning automata play repeated games with payoffs quantifying the performance in a distributed application. Each automatons view of the global state is periodically updated by communication from other automata of their local state (i.e. current strategy probabilities). Because of infrequent communication and transmission delays, received state information may become stale: an example game illustrates the mutually conflicting decisions that can result. Simulation and analytic results show there exists a maximum communication delay before decision quality begins to suffer, however, with sufficient communication, the agents adapt to a coordinated policy. >

Dynamic scope of control in decentralized job scheduling

Each job scheduling agent in large decentralized load balancing systems generally has a set of remote hosts (i.e., its scope of control) to consider for offloading when the local load is too high. Typically, each agents scope of control includes all the hosts in the system. The potential performance benefits of limiting the size of each agents scope of control are investigated. The larger the scope of control, the less often state information can lower the quality of load balancing decisions. The smaller the scope of control, the less opportunity an agent has for finding a lightly loaded host for offloading. Agents adaptively modify their scope of control over time based on feedback regarding the success of load balancing decisions and act as a self-organizing system to efficiently share available processing power.<<ETX>>

Operating system scenarios as Use Case Maps

This paper summarizes the analysis, design, implementation, and performance analysis of an object-oriented operating system. The analysis applies Use Case Maps (UCMs) to provide a high-level abstraction of the behavior scenarios for state transition, character output, network access, and disk access. The UCM for state transitions is converted into a queueing network for simulation study of I/O-bound versus CPU-bound systems. An overview of the later stages emphasizes UML for architecture and detailed collaboration, as well as Java examples. The performance of the disk sub-system is analyzed by instrumenting the Java code, and the results show that design choices can affect the throughput.

Chaotic behavior of learning automata in multi-level games under delayed information

Distributed decision makers are modeled as players in a game with two levels. High level decisions concern the game environment and determine the willingness of the players to form a coalition (or group). Low level decisions involve the actions to be implemented within the chosen environment. Decisions are made using probability distributions which are updated using a learning automaton scheme. A player has knowledge of another players likelihood of making a particular decision but this information is delayed, perhaps due to network broadcasts or other environmental influences. These delays create the potential for instabilities in the decision making process and particular parameter settings can lead to period-doubling and the onset of chaos.

Probabilistic coalition formation in distributed knowledge environments

In a distributed system, a group of agents have a potential for improved performance depending on their ability to utilize shared resources. This potential synergy raises the question of whether agents should work together in a system-wide group, i.e., a coalition, or whether they should work alone. In general, there is uncertainty as to whether a coalition will form; this uncertainty can arise for various reasons, such as adaptive strategies of the agents or random faults in the system. In this paper, we present a model for performance based upon the probability of coalition formation. The results indicate a limit in potential performance for adaptive agents and, in particular, the global and local maxima along with regions of nonstability. In addition, the model shows how performance is affected by the knowledge environment of the distributed system, that is, the architecture of the system with respect to the distribution of information. Four environments are examined as illustrations of these general categories of information distribution: global information; inaccessible information; local information residing in autonomous agents; and information residing in a master control agent. The results show the distinctions between the environments with respect to probabilistic coalition formation and also demonstrate the loss in environments without communication as compared to a baseline communication environment. >

Load balancing to adjust for proximity in some network topologies

Each job scheduler in large decentralized load balancing systems generally must consider whether it is advantageous to offload jobs to remote computation servers when the local load is too high. Although processing power may appear to be available at a very distant server, two problems arise due to the transmission delay between the scheduler and server. Predictably, the response time of the job is adversely affected as the job spends valuable time in transit, but a more subtle problem involves the value, or reliability, of the state information regarding job queues. The longer the delay between scheduler and server, the less a scheduler should value the state information of the server (given that the state changes over time). We examine the performance of schedulers in topologies with different average proximity and show a probabilistic algorithm that allows schedulers to dynamically form efficient clusters in the network.

Q-Sim: a GUI for a queueing simulator using Tcl/Tk

A design and implementation are presented for a graphical user interface to a batch queueing simulator, illustrating the benefits of using a high-level script language. Rapid development was made possible with the use of Tcl/Tk scripts to implement the entire interface. The script implements a dynamic display of job and queue movement along with graphs of statistical behaviors. A message system is used to control the interaction between the human interface and the batch simulator.

Laboratory exercises using a graphical user interface to a queueing simulator

The study of queueing systems presents mathematical barriers to the novice, although the phenomena of queues can be readily observed in everyday life. In addition, English-speaking faculty have language barriers to surmount with Japanese students. This paper describes a graphical user interface to allow quick and easy comprehension of the dynamical behavior of queues. The interface is implemented using Tcl/Tk, a high-level Window programming script language that allows for the rapid development of educational software. An outline is presented for a set of exercises for a lower division laboratory. This material is also appropriate for laboratories associated with courses in operating systems, queueing systems, and performance evaluation.

Stabilizing distributed queuing systems using feedback based on diversity

The Huberman-Hogg model of computational ecosystems is applied to resources with queues. The previous theoretical results indicate that instabilities, due to delayed information, can be controlled by adaptive mechanisms, particularly schemes which employ diverse past horizons. A stochastic learning automaton, with rewards based on queuing parameters, is implemented to test the theoretical results. The effects of the learning step size and horizon are shown for systems with various delays and traffic intensities. The instabilities are controlled with appropriate choices of parameters and reward mechanism. Long horizons permit nonadaptive agents to achieve similar results, with the possible loss of responsiveness to dynamic environments.