Atjaunināt sīkdatņu piekrišanu

Stream Data Processing: A Quality of Service Perspective: Modeling, Scheduling, Load Shedding, and Complex Event Processing 2009 ed. [Hardback]

3.50/5 (4 ratings by Goodreads)
,
  • Formāts: Hardback, 324 pages, height x width: 235x155 mm, weight: 648 g, 50 Illustrations, black and white; XXVI, 324 p. 50 illus., 1 Hardback
  • Sērija : Advances in Database Systems 36
  • Izdošanas datums: 08-May-2009
  • Izdevniecība: Springer-Verlag New York Inc.
  • ISBN-10: 0387710027
  • ISBN-13: 9780387710020
Citas grāmatas par šo tēmu:
  • Hardback
  • Cena: 136,16 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Standarta cena: 160,19 €
  • Ietaupiet 15%
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
Stream Data Processing: A Quality of Service Perspective: Modeling, Scheduling, Load Shedding, and Complex Event Processing 2009 ed.Palielināt
  • Formāts: Hardback, 324 pages, height x width: 235x155 mm, weight: 648 g, 50 Illustrations, black and white; XXVI, 324 p. 50 illus., 1 Hardback
  • Sērija : Advances in Database Systems 36
  • Izdošanas datums: 08-May-2009
  • Izdevniecība: Springer-Verlag New York Inc.
  • ISBN-10: 0387710027
  • ISBN-13: 9780387710020
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9780387710020.html
Keywords:
Data Stream Management Systems (DSMSs) are the systems used to process data streams and provide for the needs of stream-based applications. This book presents a new paradigm to meet the needs of these applications, including a detailed discussion of the techniques proposed. It includes important aspects of a QoS-driven DSMS (Data Stream Management System) and introduces applications where a DSMS can be used and discusses needs beyond the stream processing model. It also discusses in detail the design and implementation of MavStream. This volume is primarily intended as a reference book for researchers and advanced-level students in computer science. It is also appropriate for practitioners in industry who are interested in developing applications.

Traditional database management systems, widely used today, are not well-suited for a class of emerging applications, such as computer network management, homeland security, sensor computing, and environmental monitoring. These applications need to continuously process large amounts of data coming in the form of a stream, and meet stringent response time requirements. Support for handling QoS metrics, such as response time, memory usage, and throughput, is central to any system proposed for the above applications.Stream Data Processing: A Quality of Service Perspective (Modeling, Scheduling, Load Shedding, and Complex Event Processing), presents a new paradigm suitable for stream and complex event processing. This book covers a broad range of topics in stream data processing and includes detailed technical discussions of a number of proposed techniques.This volume is intended as a textbook for graduate courses and as a reference book for researchers, advanced-level students in CS, and IT practitioners.

Recenzijas

From the reviews:

The motivation for this book comes from the need for applications that can process data continuously from one or more sources, with good performance in terms of satisfying the requirements of Quality of Service . The material of this book can be used for a graduate course, as a reference book for the researcher familiar with this domain, or as a very good introductory text for people interested in the areas of stream and complex event processing. (Mirel Cosulschi, Zentralblatt MATH, Vol. 1170, 2009)

List of Figures XIX
List of Tables XXIII
List of Algorithms XXV
1 INTRODUCTION 1
1.1 Paradigm Shift
3
1.2 Data Stream Applications
5
1.3 Book Organization
6
2 OVERVIEW OF DATA STREAM PROCESSING 9
2.1 Data Stream Characteristics
9
2.2 Data Stream Application Characteristics
10
2.3 Continuous Queries
12
2.3.1 Window Specification
14
2.3.2 Examples of Continuous Queries
16
2.3.3 QoS Metrics
18
2.4 Data Stream Management System Architecture
19
2.5 Summary of
Chapter 2
20
3 DSMS CHALLENGES 23
3.1 QoS-Related Challenges
23
3.1.1 Capacity Planning and QoS Verification
23
3.1.2 Scheduling Strategies for CQs
24
3.1.3 Load Shedding and Run-Time Optimization
25
3.1.4 Complex Event and Rule Processing
26
3.1.5 Design and Implementation of a DSMS with CEP
27
3.2 Concise Overview of Book
Chapters
27
3.2.1 Literature Review
27
3.2.2 Continuous Query Modeling
28
3.2.3 Scheduling Strategies for CQs
28
3.2.4 Load Shedding in a DSMS
29
3.2.5 NFMi: A Motivating Application
30
3.2.6 DSMS and Complex Event Processing
30
3.2.7 Design and Implementation of Prototypes
31
4 LITERATURE REVIEW 33
4.1 Data Stream Management Systems
33
4.1.1 Aurora and Borealis
33
4.1.2 STREAM
34
4.1.3 TelegraphCQ
35
4.1.4 MavStream
36
4.1.5 Others
37
4.2 QoS-Related Issues
38
4.2.1 Continuous Query Modeling for Capacity Planning
38
4.2.2 Scheduling Strategies for CQs
39
4.2.3 Load Shedding in a DSMS
40
4.2.4 Design and Implementation of Prototypes
41
4.3 Complex Event Processing
41
4.3.1 Mid- to Late-Eighties: Active Databases
41
4.3.2 Nineties: Active Object-Oriented Databases
42
4.3.3 Beyond 2000: (Distributed) Complex Event Processing
45
4.4 Commercial and Open Source Stream and CEP Systems
47
5 MODELING CONTINUOUS QUERIES OVER DATA STREAMS 49
5.1 Continuous Query Processing
50
5.1.1 Operator Path
50
5.1.2 Operator Modeling
52
5.1.3 Scheduling and Service Discipline
53
5.2 Problem Definition
54
5.2.1 Notations and Assumptions
56
5.2.2 Stability and Performance Metrics
57
5.3 Modeling Relational Operators
57
5.3.1 Modeling Select and Project Operators
58
5.3.2 Modeling Window-Based Symmetric Hash join
60
5.3.3 Steady State Processing Cost
60
5.3.4 Handling Bursty Inputs and Disk-Resident Data
68
5.4 Modeling Continuous Queries
69
5.4.1 Modeling Operators with External Input(s)
71
5.4.2 Modeling Operators with Internal Input(s)
75
5.4.3 Modeling Operators with External and Internal Inputs
79
5.4.4 Scheduling Strategy and Vacation Period
79
5.4.5 Computing Memory Usage and Tuple Latency
82
5.5 Intuitive Observations
82
5.5.1 Tuple Latency
82
5.5.2 Service Discipline
82
5.5.3 Scheduling Algorithms
83
5.5.4 Choice of Query Plans
84
5.5.5 Input Rate
84
5.6 Experimental Validation
85
5.6.1 Validation of Operator Models
86
5.6.2 Validation of Continuous Query Plan Models
89
5.7 Summary of
Chapter 5
93
6 SCHEDULING STRATEGIES FOR CQs 95
6.1 Scheduling Model and Terminology
96
6.1.1 Scheduling Model
97
6.1.2 Notations
99
6.2 Impact of Scheduling Strategies on QoS
103
6.3 Novel Scheduling Strategies for CQs
105
6.3.1 Path Capacity Strategy
106
6.3.2 Analysis of CQ Scheduling Strategies
108
6.3.3 Segment Strategy and Its Variants
111
6.3.4 Hybrid Threshold Scheduling Strategy
122
6.3.5 CQ Plan Characteristics
124
6.3.6 Starvation-Free Scheduling
125
6.4 Experimental Validation
126
6.4.1 Setup
126
6.4.2 Evaluation of Scheduling Strategies
127
6.5 Summary of
Chapter 6
136
7 LOAD SHEDDING IN DATA STREAM MANAGEMENT SYSTEMS 137
7.1 The Load Shedding Problem
138
7.2 Integrating Load Shedders
140
7.2.1 Load Shedder as Part of a Buffer
142
7.2.2 Types of Load Shedders
143
7.3 Load Shedding Framework
143
7.3.1 Prediction of Query Processing Congestion
144
7.3.2 Placement of Load Shedders
151
7.3.3 Allocation of Load for Shedding
156
7.3.4 Load Shedding Overhead
157
7.4 Experimental Validation
158
7.4.1 Prototype Implementation
158
7.4.2 Experiment Setup
158
7.4.3 Load Shedding with Path capacity strategy
160
7.4.4 Load Shedding with EDF scheduling strategy
163
7.5 Summary of
Chapter 7
165
8 NFMi: AN INTER-DOMAIN NETWORK FAULT MANAGEMENT SYSTEM 167
8.1 Network Fault Management Problem
168
8.2 Data Processing Challenges for Fault Management
170
8.2.1 Semi-structured Text Messages
171
8.2.2 Large Number of Messages
172
8.2.3 Complex Data Processing
172
8.2.4 Online Processing and Response Time
172
8.3 Stream- and Event-Based NFMi Architecture
173
8.3.1 Message Splitter
175
8.3.2 Message Filter and Information Extractor
175
8.3.3 Alarm Processing
178
8.4 Three-Phase Processing Model for NFMZ
178
8.4.1 Continuous Query (CQ) Processing Phase
178
8.4.2 Complex Event Processing Phase
181
8.4.3 Rule Processing Phase
182
8.4.4 Summary
183
8.5 Transactional Needs of Network Management Applications
184
8.5.1 Updates and Views
185
8.6 Summary of
Chapter 8
186
9 INTEGRATING STREAM AND COMPLEX EVENT PROCESSING 187
9.1 Motivation
188
9.2 Event Processing Model
191
9.2.1 Event Detection Graphs
192
9.2.2 Event Consumption Modes
192
9.2.3 Event Detection and Rule Execution
194
9.3 Complex Event Vs. Stream Processing
195
9.3.1 Inputs and Outputs
195
9.3.2 Consumption Modes Vs. Window Types
196
9.3.3 Event Operators Vs. CQ Operators
197
9.3.4 Best-Effort Vs. QoS
197
9.3.5 Optimization and Scheduling
198
9.3.6 Buffer Management and Load Shedding
198
9.3.7 Rule Execution Semantics
199
9.3.8 Summary
199
9.4 MavEStream: An Integrated Architecture
200
9.4.1 Strengths of the Architecture
201
9.5 Stream-Side Extensions
203
9.5.1 Named Continuous Queries
203
9.5.2 Stream Modifiers
205
9.6 Event-Side Extensions
207
9.6.1 Generalization of Event Specification
207
9.6.2 Event Specification using Extended SQL
208
9.6.3 Mask Optimization
210
9.6.4 Enhanced Event Consumption Modes
210
9.6.5 Rule Processing
211
9.7 Summary of
Chapter 9
213
10 MavStream: DEVELOPMENT OF A DSMS PROTOTYPE 215
10.1 MavStream Architecture
216
10.1.1 Functionality
216
10.1.2 MavStream Server Design
217
10.1.3 Mal/Stream Server Implementation
219
10.2 Window Types
220
10.2.1 Functionality
220
10.2.2 Design
220
10.2.3 Implementation
222
10.3 Stream Operators and CQs
222
10.3.1 Functionality
222
10.3.2 Design of Operators
223
10.3.3 Implementation
225
10.4 Buffers and Archiving
229
10.4.1 Functionality
229
10.4.2 Buffer Manager Design
230
10.4.3 Buffer Manager Implementation
231
10.5 Run-time Optimizer
231
10.5.1 Functionality
231
10.5.2 Run-time Optimizer Design
232
10.5.3 Run-time Optimizer Implementation
234
10.6 QoS-Delivery Mechanisms
243
10.6.1 Functionality
243
10.6.2 Scheduler Design
243
10.6.3 Scheduler Implementation
245
10.6.4 Load Shedder Design
246
10.6.5 Load Shedder Implementation
246
10.7 System Evaluation
248
10.7.1 Single QoS Measure Violation
248
10.7.2 Multiple QoS Measures Violation
249
10.7.3 Effect of Load Shedding on QoS Measures
253
10.7.4 Effect of Load Shedding on Error in Results
257
11 INTEGRATING CEP WITH A DSMS 261
11.1 MavEStream: Integration Issues
262
11.1.1 Event Generation
263
11.1.2 Continuous Event Query (CEQ) Specification
264
11.1.3 Events and Masks
264
11.1.4 Address Space Issues
265
11.1.5 Summary
265
11.2 Design of the Integrated System
266
11.2.1 Address Space
266
11.2.2 Continuous Event Queries
266
11.2.3 Events and Masks
268
11.2.4 Event Generator Interface
271
11.2.5 Need for a Common Buffer for All Events
272
11.2.6 Complex Events and Rule Management
274
11.3 Implementation Details of Integration
275
11.3.1 Input Processor
276
11.3.2 Event and Rule Instantiator
278
11.3.3 Event Generator Interface
278
11.4 Stream Modifiers
281
11.4.1 Tuple-Based Stream Modifiers
281
11.4.2 Window-Based Stream Modifiers
282
11.4.3 Implementation
282
11.5 Additional Benefits of CEP Integration
284
11.6 Summary of
Chapter 11
285
12 CONCLUSIONS AND FUTURE DIRECTIONS 287
12.1 Looking Ahead
287
12.2 Stream Processing
288
12.2.1 Continuous Query Modeling
289
12.2.2 Scheduling
289
12.2.3 Load Shedding
290
12.3 Integration of Stream and Event Processing
291
12.4 Epilogue
293
References 295
Index 315