Skip to main content
main-content

Über dieses Buch

This book provides a comprehensive set of optimization and prediction techniques for an enterprise information system. Readers with a background in operations research, system engineering, statistics, or data analytics can use this book as a reference to derive insight from data and use this knowledge as guidance for production management. The authors identify the key challenges in enterprise information management and present results that have emerged from leading-edge research in this domain. Coverage includes topics ranging from task scheduling and resource allocation, to workflow optimization, process time and status prediction, order admission policies optimization, and enterprise service-level performance analysis and prediction. With its emphasis on the above topics, this book provides an in-depth look at enterprise information management solutions that are needed for greater automation and reconfigurability-based fault tolerance, as well as to obtain data-driven recommendations for effective decision-making.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract
An enterprise information system (EIS) is an integrated data-applications platform characterized by diverse, heterogeneous, and distributed data sources. For many enterprises, a number of business processes still depend heavily on static rule-based methods and extensive human expertise. Enterprises are faced with the need for optimizing operation scheduling, improving resource utilization, discovering useful knowledge, and making data-driven decisions. This book is focused on real-time optimization and knowledge discovery that addresses workflow optimization, resource allocation, as well as data-driven predictions of process-execution times, order fulfillment, and enterprise service-level performance. In contrast to prior work on data analytics techniques for enterprise performance optimization, the emphasis here is on realizing scalable and real-time enterprise intelligence based on a combination of heterogeneous system simulation, combinatorial optimization, machine-learning algorithms, and statistical methods. In order to handle the increase in volume and diversity of demands, we first present a high-performance, scalable, and real-time production-scheduling algorithm for production automation based on an incremental genetic algorithm (IGA). The objective of this algorithm is to optimize the order dispatching sequence and balance resource utilization. Compared to prior work, this solution is scalable for a high volume of orders and it provides fast scheduling solutions for orders that require complex fulfillment procedures. Experimental results highlight its potential benefit in reducing production inefficiencies and enhancing the productivity of an enterprise. We next discuss analysis and prediction of different attributes involved in hierarchical components of an enterprise. We start from a study of the fundamental processes related to real-time prediction. Our process-execution time and process status prediction models integrate statistical methods with machine-learning algorithms. In addition to improved prediction accuracy compared to stand-alone machine-learning algorithms, it also performs a probabilistic estimation of the predicted status. An order generally consists of multiple series and parallel processes. We next introduce an order-fulfillment prediction model that combines advantages of multiple classification models by incorporating flexible decision-integration mechanisms. Experimental results show that adopting due dates recommended by the model can significantly reduce enterprise late-delivery ratio. Finally, we investigate service-level attributes that reflect the overall performance of an enterprise. We analyze and decompose time-series data into different components according to their hierarchical periodic nature, perform correlation analysis, and develop univariate prediction models for each component as well as multivariate models for correlated components. Predictions for the original time series are aggregated from the predictions of its components. In addition to a significant increase in mid-term prediction accuracy, this distributed modeling strategy also improves short-term time-series prediction accuracy. In summary, this book has led to a set of characterization, optimization, and prediction tools for an EIS to derive insightful knowledge from data and use them as guidance for production management. It is expected to provide solutions for enterprises to increase reconfigurability, accomplish more automated procedures, and obtain data-driven recommendations or effective decisions.
Qing Duan, Krishnendu Chakrabarty, Jun Zeng

Chapter 2. Production Simulation Platform

Abstract
Research on productivity improvement is gaining accelerated attention in enterprise industry in recent years. One notable example is the LDP solution by Xerox [1]. LDP is Xerox’s simulation-based service solution offered through Xerox Managed Services (XMS) that helps to enhance print shop productivity. There are distinctions between our and their simulation-based approaches. In our approach, we modeled the print production as a content-driven cyber-physical system [2]. Anticipating that the pervasive sensing and computing-based knowledge discovery will enable additional design space and flexibility, we have tested our optimization and knowledge discovery components on the simulation platform.
Qing Duan, Krishnendu Chakrabarty, Jun Zeng

Chapter 3. Production Workflow Optimization

Abstract
Operation optimization is a major function of an EIS. We present a high-performance and real-time production scheduler for an enterprise based on a dynamic incremental evolutionary algorithm. The optimization objective is to prioritize the dispatching sequence of orders and balance resource utilization. The scheduler is scalable for realistic problem instances and it provides solutions quickly for diverse products that require complex fulfillment procedures. Furthermore, it dynamically ingests the transient state of the enterprise, such as process information and resource failure probability in the production; therefore, it minimizes the management-production mismatch. Discrete-event simulation results show that the production scheduler leads to a higher and more stable order on-time delivery ratio compared to a rule-based heuristic. Its beneficial attributes collectively contribute to the reduction or elimination of the shortcomings that are inherent in today’s enterprise production environment and help to enhance an enterprise’s productivity and profitability.
Qing Duan, Krishnendu Chakrabarty, Jun Zeng

Chapter 4. Predictions of Process-Execution Time and Process-Execution Status

Abstract
As shown in Chap. 3, process-execution time is a fundamental measure in an EIS. Our risk-aware execution-time estimation method (Sect. 3.​2.​2) has demonstrated improved performance over static rule-based methods. However, in addition to performing real-time production scheduling, an EIS should also be able to carry out planning for the future. Therefore, accurate predictions of both process-execution time and process status are crucial for the development of an intelligent EIS. We propose new process-execution time-prediction and process status-prediction methods for an EIS.
Qing Duan, Krishnendu Chakrabarty, Jun Zeng

Chapter 5. Optimization of Order-Admission Policies

Abstract
A mass-customization enterprise offers personalized manufacturing services. Once an order is submitted to the enterprise by a client, the EIS needs to make a real-time decision on whether to accept or refuse this order. Based on the enterprise current capacity, and the order’s properties and requirements, an order is refused if its acceptance is not profitable for the enterprise. The order is accepted with the most appropriate due date in order to maximize the profit that can result from this order. We have developed an intelligent order-admission framework that provides admission decisions in real-time for new orders using machine-learning and decision-integration techniques. The framework consists of three classifiers: Support Vector Machine (SVM), Decision Tree (DT), and Bayesian Probabilistic Model (BPM). The classifiers are trained by history orders and used to predict completion status for new orders. A decision integration technique is implemented to combine the results of the classifiers and predict due dates. Experimental results derived using real factory data from a leading print-service provider and Weka open source software show that the order completion-status prediction accuracy is significantly improved by the decision-integration strategy. The proposed multi-classifier model also outperforms a stand-alone regression model.
Qing Duan, Krishnendu Chakrabarty, Jun Zeng

Chapter 6. Analysis and Prediction of Enterprise Service-Level Performance

Abstract
Research on productivity improvement is gaining accelerated attention in enterprise industry in recent years. One notable example is the LDP solution by Xerox [1]. LDP is Xerox’s simulation-based service solution offered through Xerox Managed Services (XMS) that helps to enhance print shop productivity. There are distinctions between our and their simulation-based approaches. In our approach, we modeled the print production as a content-driven cyber-physical system [2]. Anticipating that the pervasive sensing and computing-based knowledge discovery will enable additional design space and flexibility, we have tested our optimization and knowledge discovery components on the simulation platform.
Qing Duan, Krishnendu Chakrabarty, Jun Zeng

Chapter 7. Conclusion

Abstract
This thesis has presented operation optimization and knowledge discovery solutions for an EIS. Topics covered include production workflow optimization, operation scheduling, resource allocation, process-execution time and process status prediction, order/service fulfillment prediction, and enterprise service-level performance analysis and prediction. In contrast to state-of-the-art methods, which are based on stand-alone statistical methods, analytical methods, or machine-learning algorithms, this thesis has focused on designing unified real-time and data-driven applications that integrate statistical methods and machine-learning algorithms. Therefore, correlated objectives of an EIS can be optimized in a comprehensive data-driven framework.
Qing Duan, Krishnendu Chakrabarty, Jun Zeng

Backmatter

Weitere Informationen