(Downloads - 0)
For more info about our services contact : help@bestpfe.com
Table of contents
1 Introduction
1.1 Problem Statement
1.2 Objective
1.3 Contribution
1.4 Methodology
1.4.1 Observation and Requirements Gathering
1.4.2 Design and Development
1.4.3 Testing and Evaluation
1.5 Structure of Thesis
2 Graph Partitioning
2.1 Partitioning Techniques
2.1.1 Vertex Partitioning
2.1.2 Edge Partitioning
2.2 Power-Law Graphs
2.2.1 Partitioning Power-Law Graphs
2.3 Partitioning Algorithms
2.3.1 Algorithms for Vertex Stream
2.3.1.1 Linear Greedy
2.3.1.2 Fennel
2.3.2 Algorithms for Edge Stream
2.3.2.1 Least Cost Incremental
2.3.2.2 Least Cost Incremental Advanced
2.3.2.3 Degree Based Partitioner
2.4 Feature Comparison
3 Background
3.1 Data Stream Processing
3.1.1 Data Stream Processing Models
3.1.2 Data Stream Approximation Strategies
3.2 Graph Stream Processing
3.2.1 Graph Stream Models
3.2.2 Graph Stream Representations
3.3 Apache Flink
3.3.1 Flink as Data Processing Engine
3.3.2 Flink Streaming API
3.3.3 Flink Graph Processing API
3.3.4 The Graph Streaming API for Flink
3.3.4.1 Implemented Algorithms
4 Implementation
4.1 Stream Order
4.2 Vertex Stream
4.3 Edge Stream
4.4 Partitioners
4.4.1 Vertex Stream Partitioning Algorithms
4.4.2 Edge Stream Partitioning Algorithms
4.5 Post-Partitioning
5 Evaluation
5.1 Input Data Streams
5.2 Experimental Setup
5.3 Partitioning Algorithms
5.3.1 Execution Time
5.3.2 Edge-Cut
5.3.3 Replication Factor
5.3.4 Load Balancing
5.4 Post-Partitioning
5.4.1 Size of Aggregate States
5.4.2 Convergence
5.5 Evaluation Summary
6 Conclusion
6.1 Future Work
