Anton Riabov, Zhen Liu, Joel L. Wolf, Philip S. Yu, Li Zhang, “New Algorithms for Content-Based Publication-Subscription Systems”, ICDCS 2003 - The 23rd International Conference on Distributed Computing Systems, May 2003, Providence, Rhode Island.

Abstract:
This paper introduces new algorithms specifically designed for content-based publication-subscription systems. Based on concepts borrowed from the spatial database literature, we develop an algorithm to match publications to subscribers in real-time. We also investigate the benefits of dynamically determining whether to unicast, multicast or broadcast information about the events over the network to the matched subscribers. We call this the distributionmethod problem. We demonstrate the quality of our algorithms via a number of realistic simulation experiments.

Avraham Leff, James T. Rayfield, Daniel Dias “Meeting Service Level Agreements In a Commercial Grid”, IEEE Internet Computing, July/August, 2003 (Special issue on Grid Computing).

Abstract:
In this paper we identify commercial grids as an emerging specialization of grid technology, and identify the need to define and satisfy service level agreements as a requirement of commercial grids. We show that service level agreements impose unique requirements on a commercial grid infrastructure, specifically the need for a dynamic offload infrastructure. We discuss the requirements that such an infrastructure must meet, and then describe a prototype implementation in detail.

Heiko Ludwig, Alexander Keller, Asit Dan, Richard King and Richard Franck, “A Service Level Agreement Language for Dynamic Electronic Services”, Electronic Commerce Research, Vol. 3, No. 1-2, January/April 2003.

Abstract:
This paper proposes a novel language for Service Level Agreements (SLAs) for dynamic and spontaneous electronic services. In a cross-organizational setting, it is important for customers of a service to obtain, monitor and enforce quality of service (QoS) guarantees by service providers, usually expressed in the form of SLAs. Since the supervision and management of SLAs and the provisioning of corresponding systems should be automated for economic reasons, we need a formal language to define an SLA. If, moreover, providers and customers want to sign custom-made SLAs, the SLA language, correspondingly, must provide a large degree of flexibility.
The SLA language described in this paper aims at providing the needed flexibility by means of an XML-based representation and a runtime system for SLAs. Using this language, parties to a SLA can describe how parameters are measured and computed from raw metrics, the guarantees they want with respect to those parameters and the involvement of third parties to, e.g., independently verify SLA compliance.

Jeffrey O. Kephart, David M. Chess, “The Vision of Autonomic Computing”, IEEE Computer 36(1): 41-50 (2003)

Abstract:
A 2001 IBM manifesto observed that a looming software complexity crisis—caused by applications and environments that number into the tens of millions of lines of code—threatened to halt progress in computing. The manifesto noted the almost impossible difficulty of managing current and planned computing systems, which require integrating several heterogeneous environments into corporate-wide computing systems that extend into the Internet.
Autonomic computing, perhaps the most attractive approach to solving this problem, creates systems that can manage themselves when given high-level objectives from administrators.

Liana Fong , Michael Kalantar, Don Pazel, German Goldszmidt, K. Appleby, T. Eilam ,S.Fakhouri, S. Krishnakumar, “Dynamic Resource Management in an eUtility”. Network Operations and Management Symposium. April 2002.

Abstract:
Océano is management software for a eUtility infrastructure capable of providing cost-effective, autonomic resource allocation for multiple customer or application domains, in response to existent performance and availability conditions. The Control Layer of Océano provides mechanisms to manage resources. This layer consists of a resource director and a set of resource managers. The resource director formulates resource configurations and coordinates their execution through resource managers. These resource managers maintain restore state and carry out detailed configuration tasks. This paper describes the Océano resource management model and its server and application deployment resource managers. A prototype of Océano has been developed and deployed on an 80 server platform, and has been tested with multiple domains and applications.

Melissa J. Buco, Rong N. Chang, Laura Zaihua Luan, Christopher Ward, Joel L. Wolf, Philip S. Yu, Tevfik Kosar, Syed Umair Shah, “Managing eBusiness on Demand SLA Contracts in Business Terms Using the Cross-SLA Execution Manager SAM”, ISADS 2003 - International Symposium on Autonomous Decentralized Systems, April, 2002, Pisa, Italy.

Abstract:
It is imperative for a competitive e-business service provider to be positioned to manage the execution of its service level agreement (SLA) contracts in business terms (e.g., minimizing financial penalties for service-level violations, maximizing service-level measurement based customer satisfaction metrics). This paper briefly describes the design rationale of an integrated set of business-oriented service level management (SLM) technologies under development in the SAM project at IBM T.J. Watson Research Center. The e-business SLA execution manager SAM, (1) enables the provider to deploy an effective means of capturing and managing contractual SLA data as well as provider-facing non-contractual SLM data; (2) assists service personnel to prioritize the processing of action-demanding quality management alerts as per provider’s SLM objectives; and (3) automates the prioritization and execution management of approved SLM processes on behalf of the provider, including assigning SLM tasks to service personnel.

Ron Levy, Jay Nagarajao, Giovanni Pacifici, Mike Spreitzer, Asser Tantawi, and Alaa Youssef , “Performance management For Cluster Based Web Services”, Received Best Paper Award at IM 2003, March 2003.

Abstract:
We present an architecture and prototype implementation of a performance management system for cluster-based web services. The system supports multiple classes of web services traffic and allocates server resources dynamically so to maximize the expected value of a given cluster utility function in the face of fluctuating loads. The cluster utility is a function of the performance delivered to the various classes, and this leads to differentiated service. In this paper we will use the average response time as the performance metric. The management system is transparent: it requires no changes in the client code, the server code, or the network interface between them. The system performs three performance management tasks: resource allocation, load balancing, and server overload protection. We use two nested levels of management mechanism. The inner level centers on queuing and scheduling of request messages. The outer level is a feedback control loop that periodically adjusts the scheduling weights and server allocations of the inner level. The feedback controller is based on an approximate first-principles model of the system, with parameters derived from continuous monitoring. We focus on SOAP-based web services. We report experimental results that show the dynamic behavior of the system.

Stefan Tai, Thomas A. Mikalsen, Isabelle Rouvellou, Stanley M. Sutton Jr., “Conditional Messaging: Extending Reliable Messaging with Application Conditions”, Proceedings of the 22nd IEEE International Conference on Distributed Computing Systems (ICDCS 2002, Vienna, Austria), IEEE, pp 123-132, July 2002.  

Abstract:
Standard messaging middleware guarantees the delivery of messages to intermediary destinations like message queues, but does not guarantee the receipt or the processing of a message by final recipients. Conditional messaging is an extension to standard messaging middleware that addresses this shortcoming by allowing an application to define, monitor, and evaluate various conditions on messages, such as time constraints on the receipt or the processing of a message by a set of final recipients. In this paper, we introduce the notion of conditional messaging, and present the design and implementation of a flexible and reliable system that supports conditional messaging for use in Java 2 Enterprise Edition and message queuing environments. Our solution uniquely shifts the responsibilities for implementing the management of conditions on messages from the application to the middleware. We further discuss the grouping of multiple conditional messages into atomic units-of-work, which can also integrate requests to transactional resources like distributed objects using object middleware. Conditional messaging serves to implement various kinds of backward dependencies for distributed object transactions that integrate messaging.

Abstract:
This paper presents a general knowledge model for propagating information in a content-based publish-subscribe system. The model is used to derive an efficient and scalable protocol for exactly-once delivery to large numbers (tens of thousands per broker) of content-based subscribers in either publisher order or uniform total order. Our protocol allows intermediate content filtering at each hop, but requires persistent storage only at the publishing site. It is tolerant of message drops, message reorderings, node failures, and link failures, and maintains only ``soft'' state at intermediate nodes. We evaluate the performance of our implementation both under failure-free conditions and with fault injection.