A5100426920- Distributed and Parallel Computing Systems
- Advanced Data Storage Technologies
- Scientific Computing and Data Management
- Efficiency Analysis Using DEA
- Parallel Computing and Optimization Techniques
- Advanced Database Systems and Queries
- Multi-Criteria Decision Making
- Simulation Techniques and Applications
- Business Process Modeling and Analysis
- Reservoir Engineering and Simulation Methods
- Quality and Supply Management
- Data Management and Algorithms
- Software System Performance and Reliability
- Engineering and Test Systems
- Cloud Computing and Resource Management
- Peer-to-Peer Network Technologies
- Caching and Content Delivery
- Optimization and Mathematical Programming
- Time Series Analysis and Forecasting
- Interconnection Networks and Systems
Imperial College London
2021-2024
Sichuan Normal University
2021
University of Edinburgh
2020
Hefei University of Technology
2015-2017
Huawei Technologies (China)
2009
Fudan University
2008
Data stream processing systems enable querying over sliding windows of streams data. Efficient index structures for the streaming window are a crucial building block to operations such as aggregation and joins. This paper proposes SWIX, novel memory-efficient learned windows. Unlike conventional indexes that rely on tree achieve logarithmic query cost, SWIX has flat structure uses substantially less memory enables efficient execution while having low cost maintenance when inserting (and...
This work presents three new adaptive optimization techniques to maximize the performance of dispel4py workflows. is a parallel Python-based stream-orientated dataflow framework that acts as bridge existing programming frameworks like MPI or Python multiprocessing. When user runs workflow, original performs fixed workload distribution among processes available for run. allocation does not take into account workflows' features, which can cause scalability issues, specially data-intensive...
Scientific workflows bridge scientific challenges with computational resources. While dispel4py, a stream-based workflow system, offers mappings to parallel enactment engines like MPI or Multiprocessing, its optimization primarily focuses on dynamic process-to-task allocation for improved performance. An efficiency gap persists, particularly the growing emphasis conserving computing Moreover, existing lacks support stateful applications and grouping operations. To address these issues, our...
Scientific workflows bridge scientific challenges with computational resources. While dispel4py, a stream-based workflow system, offers mappings to parallel enactment engines like MPI or Multiprocessing, its optimization primarily focuses on dynamic process-to-task allocation for improved performance. An efficiency gap persists, particularly the growing emphasis conserving computing Moreover, existing lacks support stateful applications and grouping operations.
The increasing complexity of automated test systems demands high performance communication libraries that can be distributed. Protocal Buffer is a widely used mechanism for providing object serialization Remote Processing Calls (RPC). However, it lacks support an efficient and high-level programming language such as Vala, which suitable instrumentation control. This paper presents details methodology creating library Vala. And the developed has been applied to system was designed testing...