Abstract In massive MIMO systems, energy efficiency (EE) and spectral efficiency (SE) can be balanced by tuning the number of the transmit antennas and the transmit power. However, two key parameters i.e. the modulation order and the bit‐error‐rate (BER) are seldom considered in the conventional EE‐SE tradeoff for the massive MIMO systems. To address this problem, the throughput‐based EE (TEE) and SE (TSE) tradeoff for both the conventional massive MIMO and the full‐dimensional (FD) massive MIMO systems are investigated. Firstly, a TEE and TSE tradeoff problem is formulated and the transition property of the modulation order is analysed. The analysis reveals that due to the discrete property of the modulation order, the TEE‐TSE tradeoff curve is continuously non‐differentiable at the transition point of the modulation order. By utilising the transition property, a modified normal‐boundary‐intersection particle‐swarm‐optimisation (NBI‐PSO) algorithm is developed to solve the TEE‐TSE problem effectively. From the numerical results, it is found that the throughput‐based problem has a relatively smaller EE and SE on the Pareto front than the capacity‐based one and selecting an improper combination of the modulation order, the transmit power and the number of the antennas may cause the EE‐SE relation sub‐optimal from the point view of Pareto efficiency. Through the numerical results, the most energy efficient modulation order is obtained and it is not the commonly assumed low‐order modulation scheme.

The article proposes a scalable protocol for replication management in large-scale replicated systems. The protocol organizes sites and data replicas into a tree-structured, hierarchical cluster architecture. The basic idea of the protocol is to accomplish the complex task of updating replicated data with a very large number of replicas by a set of related but independently committed transactions. Each transaction is responsible for updating replicas in exactly one cluster and invoking additional transactions for member clusters. Primary copies (one from each cluster) are updated by a cross-cluster transaction. Then each cluster is independently updated by a separate transaction. This decoupled update propagation process results in possible multiple views of replicated data in a cluster. Compared to other replicated data management protocols, the proposed protocol has several unique advantages. First, thanks to a smaller number of replicas each transaction needs to atomically update in a cluster, the protocol significantly reduces the transaction abort rate, which tends to soar in large transactional systems. Second, the protocol improves user-level transaction response time as top-level update transactions are allowed to commit before all replicas have been updated. Third, read-only queries have the flexibility to see database views of different degrees of consistency and data currency. This ranges from global, most up to date, and consistent views, to local, consistent, but potentially old views, to local, nearest to users but potentially inconsistent views. Fourth, the protocol maintains its scalability by allowing dynamic system reconfiguration as it grows by splitting a cluster into two or more smaller ones. Fifth, autonomy of the clusters is preserved as no specific protocol is required to update replicas within the same cluster. Clusters are, therefore, free to use any valid replication or concurrency control protocols.

Article Free Access Share on Flexible specification of workflow compensation scopes Authors: Weimin Du Hewlett-Packard Laboratories, 1501 Page Mill Road, Palo Alto, CA Hewlett-Packard Laboratories, 1501 Page Mill Road, Palo Alto, CAView Profile , Jim Davis Hewlett-Packard Laboratories, 1501 Page Mill Road, Palo Alto, CA Hewlett-Packard Laboratories, 1501 Page Mill Road, Palo Alto, CAView Profile , Ming-Chien Shan Hewlett-Packard Laboratories, 1501 Page Mill Road, Palo Alto, CA Hewlett-Packard Laboratories, 1501 Page Mill Road, Palo Alto, CAView Profile Authors Info & Claims GROUP '97: Proceedings of the 1997 ACM International Conference on Supporting Group WorkNovember 1997 Pages 309–316https://doi.org/10.1145/266838.267342Published:16 November 1997Publication History 24citation445DownloadsMetricsTotal Citations24Total Downloads445Last 12 Months4Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

SONET (Synchronous Optical NETwork) has been proposed as the backbone of future information superhighway infrastructure. SONET network management, however, is a complex process that involves many heterogeneous systems and applications, as well as human interactions. In this paper, we describe a prototype system developed at Hewlett-Packard (HP) that provides a service for configuring large SONET networks. The prototype differs from the existing systems in that it employs the HP OpenPM (Open Process Management) workflow system to define, execute and monitor network management processes. Using OpenPM (a middleware service that enables the automation of activities supporting complex enterprise business processes in a distributed heterogeneous computing environment) as a reliable and efficient workflow execution engine, this prototype supports efficient distributed network management and easy integration of legacy applications. The paper describes how an example network configuration management process is modeled, executed and monitored using OpenPM.

Workflow builders are designed to facilitate development of automated processes and support flexible applications that can be updated, enhanced or completely revamped. The Hewlett-Packard WorkManager is an open product data management solution with workflow management capabilities. WorkManager supports the entire product lifecycle by providing a single, logical repository for all data, and it manages and tracks enterprise-wide processes. With a strong information management platform at its core, WorkManager provides central administration capabilities, including supervision and intervention, where necessary. Because enterprise data is usually fragmented and stored in a variety of legacy systems, and different organizations have different amount of control over their data, an enterprise workflow system needs to support processes accessing data from different sites and applications. This paper describes the architecture of distributed workflow, Hewlett-Packard's solution to the enterprise workflow problem. The architecture is an extension of the existing WorkManager architecture. Its development is based on user requirements and four high-level user models. The user models and the architecture are described.>

Execution of multidatabase queries differs from that of traditional queries in that sort merge and hash joins are more often favored, as nested loop join requires repeated accesses to external data sources. As a consequence, left deep join trees obtained by traditional (e.g., System-R style) optimizers for multidatabase queries are often suboptimal, with respect to response time, due to the long delay for a sort merge (or hash) join node to produce its last result after the subordinate join node did. In this paper, we present an optimization strategy that first produces an optimal left deep join tree and then reduces the response time using simple tree transformations. This strategy has the advantages of guaranteed minimum total resource usage, improved response time, and low optimization overhead. We describe a class of basic transformations that is the cornerstone of our approach. Then we present algorithms that effectively apply basic transformations to balance a left deep join tree, and discuss how the technique can be incorporated into existing query optimizers.

The paper presents two protocols for maintaining consistency of replicated data in multidatabase systems. The protocols meet both autonomy and consistency requirements by employing different replica control and commitment approaches: unilateral local commitment and deferred propagation for local applications, and two-phase commitment and immediate propagation for global applications. The first protocol ensures replication consistency (with regard to one copy serializability) through the use of a global certification protocol. The second protocol, which is an extension of the first by using propagation locks on primary copies, allows consistency certification to be performed locally for global queries that only read data copies from a single site. We identify and examine the major issues relevant to the proposed protocols.>

A scheduler producing quasi-serializable executions for concurrency control in multidatabase systems (MDBSs) is presented. An algorithm is proposed which ensures quasi-serializability by controlling submissions of global transactions. The algorithm groups global transactions in such a way that transactions in a group affect each other in a partial order. Transaction groups are executed separately and in a consistent order at all local sites. The algorithm differs from the others in that it does not violate local autonomy, provides a high degree of concurrency, and is globally deadlock-free.>

A heterogeneous distributed databases system (HDDBS) is a system which integrates preexisting databases to support global applications accessing more than one database. An outline of approaches to concurrency control in HDDBSs is presented. The top-down approach emerges as a viable paradigm for ensuring the proper concurrent execution of global transactions in an HDDBS. The primary contributions of this work are the general schemes for local concurrency control with prespecified global serialization orders. Two approaches are outlined. One is intended for performance enhancement but violates design autonomy, while the other does not violate local autonomy at the cost of generality (it does not apply to all local concurrency control protocols). This study is intended as a guide to concurrency control in this new environment.>