Hui Lei

Mobile crowdsensing: current state and future challenges

An emerging category of devices at the edge of the Internet are consumer-centric mobile sensing and computing devices, such as smartphones, music players, and in-vehicle sensors. These devices will fuel the evolution of the Internet of Things as they feed sensor data to the Internet at a societal scale. In this article, we examine a category of applications that we term mobile crowdsensing, where individuals with sensing and computing devices collectively share data and extract information to measure and map phenomena of common interest. We present a brief overview of existing mobile crowdsensing applications, explain their unique characteristics, illustrate various research challenges, and discuss possible solutions. Finally, we argue the need for a unified architecture and envision the requirements it must satisfy.

VDN: Virtual machine image distribution network for cloud data centers

Cloud computing centers face the key challenge of provisioning diverse virtual machine instances in an elastic and scalable manner. To address this challenge, we have performed an analysis of VM instance traces collected at six production data centers during four months. One key finding is that the number of instances created from the same VM image is relatively small at a given time and thus conventional file-based p2p sharing approaches may not be effective. Based on the understanding that different VM image files often have many common chunks of data, we propose a chunk-level Virtual machine image Distribution Network (VDN). Our distribution scheme takes advantage of the hierarchical network topology of data centers to reduce the VM instance provisioning time and also to minimize the overhead of maintaining chunk location information. Evaluation shows that VDN achieves as much as 30-80× speed up for large VM images under heavy traffic.

Dynamic composition and optimization of Web services

Process-based composition of Web services has recently gained significant momentum for the implementation of inter-organizational business collaborations. In this approach, individual Web services are choreographed into composite Web services whose integration logics are expressed as composition schema. In this paper, we present a goal-directed composition framework to support on-demand business processes. Composition schemas are generated incrementally by a rule inference mechanism based on a set of domain-specific business rules enriched with contextual information. In situations where multiple composition schemas can achieve the same goal, we must first select the best composition schema, wherein the best schema is selected based on the combination of its estimated execution quality and schema quality. By coupling the dynamic schema creation and quality-driven selection strategy in one single framework, we ensure that the generated composite service comply with business rules when being adapted and optimized.

Monitoring the QoS for Web Services

Quality of Service (QoS) information for Web services is essential to QoS-aware service management and composition. Currently, most QoS-aware solutions assume that the QoS for component services is readily available, and that the QoS for composite services can be computed from the QoS for component services. The issue of how to obtain the QoS for component services has largely been overlooked. In this paper, we tackle this fundamental issue. We argue that most of QoS metrics can be observed/computed based on service operations. We present the design and implementation of a high-performance QoS monitoring system. The system is driven by a QoS observation model that defines IT- and business-level metrics and associated evaluation formulas. Integrated into the SOA infrastructure at large, the monitoring system can detect and route service operational events systemically. Further, a model-driven, hybrid compilation/interpretation approach is used in metric computation to process service operational events and maintain metrics efficiently. Experiments suggest that our system can support high event processing throughput and scales to the number of CPUs.

Flexible Composition of Enterprise Web Services

The process-based composition of Web services is emerging as a promising approach to automate business process within and across organizational boundaries. In this approach, individual Web services are federated into composite Web services whose business logic is expressed as a process model. Business process automation technology such as workflow management systems (WFMSs) can be used to choreograph the component services. However, one of the fundamental assumptions of most WFMSs is that workflow schemas are static and predefined. Such an assumption is impractical for business processes that have an explosive number of options, or dynamic business processes that must be generated and altered on the fly to meet rapid changing business conditions. In this paper, we describe a rule inference framework called DY flow , where end users declaratively define their business objectives or goals and the system dynamically composes Web services

A Scalable and Elastic Publish/Subscribe Service

The rapid growth of sense-and-respond applications and the emerging cloud computing model present a new challenge: providing publish/subscribe as a scalable and elastic cloud service. This paper presents the Blue Dove attribute based publish/subscribe service that seeks to address such a challenge. Blue Dove uses a gossip-based one-hop overlay to organize servers into a scalable cluster. It proactively exploits skew ness in data distribution to achieve high performance. By assigning each subscription to multiple servers through a multidimensional subscription space partitioning technique, it provides multiple candidate servers for each publication message. A message can be matched on any of its candidate servers with one hop forwarding. The performance-aware forwarding in Blue Dove ensures that the message is sent to the least loaded candidate server for processing, leading to low latency and high throughput. The evaluation shows that Blue Dove has a linear capacity increase as the system scales up, adapts to sudden workload changes within tens of seconds, and achieves multifold higher throughput than the techniques used in the existing enterprise and peer-to-peer pub/sub systems.

Policy-driven exception-management for composite Web services

Process-based composition of Web services has recently gained significant momentum in the implementation of business processes. A critical and time-consuming part of business process development is the detection and handling of exceptions that may occur during process execution. In this paper, we introduce a novel, policy-driven approach to exception management, which substantially simplifies business process development. We advocate that exception management should be implemented in the system infrastructure. Using our exception management framework, developers define exception policies in a declarative manner. Before a business process is executed, the service composition middleware integrates the exception policies with normal business logic to generate an exception-aware process schema. We argue that our policy-driven approach significantly reduces the development time of business processes through its separation of the development of the business logic and the exception handling policies.

The Design and Implementation of a Smart Building Control System

A significant proportion of total worldwide energy is consumed by buildings. For example, buildings in the US account for about 40 percent of total energy consumption and greenhouse gas emission. Making buildings more energy-efficient is an important step to reduce our energy consumption and carbon emission in the combat with global climate change. Broad participation by consumers, business owners, and governments is required to continuously improve on energy efficiency for new and existing buildings and to achieve the global greenhouse gas emission reduction objectives. This paper provides a software system perspective of improving energy efficiency for buildings. It proposes an architecture that allows for phased investments in technologies to capture the returns from energy savings in various use cases. In addition, it addresses the needs and objectives of different stakeholders, including owners, operators, users, and utility providers. A proof-of-concept implementation of the architecture is used to demonstrate the support for building-wide energy conservation policies using real-time energy pricing and individual occupants’ locations and preferences. It shows that the proposed architecture enables fine-grained building control and reduces energy consumption while maximizing its occupants’ comfort.

Event-Driven Quality of Service Prediction

Quality of Service Management (QoSM) is a new task in IT-enabled enterprises that supports monitoring, collecting and predicting QoS data. QoSM solutions must be able to efficiently process runtime events, compute and pre dict QoS metrics, and provide real-time visibility and prediction of key perform ance indicators (KPI). Currently, most QoSM systems focus on moni tor ing of QoS constraints, i.e., they report what has been happened. In a way, this provides the awareness of past developments and sets the basis for decisions. However, this kind of knowledge is afterwit. For example, it cannot provide early warnings to prevent the QoS degradation or the violation of commitments. In this paper, we move one step forward to provide QoS prediction. We argue that performance metrics and KPIs can be predicted based on historical data. We present the design and implementation of a novel event-driven QoS prediction system. Integrated into the SOA infrastructure at large, the prediction system can process operational service events in a real-time fashion, in order to predict or refine the prediction of metrics and KPIs.

Model driven development for business performance management

Business process integration and monitoring provides an invaluable means for an enterprise to adapt to changing conditions. However, developing such applications using traditional methods is challenging because of the intrinsic complexity of integrating large-scale business processes and existing applications. Model Driven DevelopmentTM (MDDTM) is an approach to developing applications-from domain-specific models to platform-sensitive models-that bridges the gap between business processes and information technology. We describe the MDD framework and methodology used to create the IBM Business Performance Management (BPM) solution. We describe how we apply model-driven techniques to BPM and present a scenario from a pilot project in which these techniques were applied. Technical details on models and transformation are presented. Our framework uses and extends the IBM business observation metamodel and introduces a data warehouse metamodel and other platform-specific and transformational models. We discuss our lessons learned and present the general guidelines for using MDD to develop enterprise-scale applications.