Hierarchical Storage Management for Cluster Computing

• E. Kakoulli, N. D. Karmiris, and H. Herodotou. OctopusFS in Action: Tiered Storage Management for Data Intensive Computing. Demo, Proc. of VLDB Endowment (PVLDB ’18), Vol. 11, No. 12, pp. 1914-1917, August 2018.
• E. Kakoulli and H. Herodotou. OctopusFS: A Distributed File System with Tiered Storage Management. In Proc. of the ACM Intl. Conf. on Management of Data (SIGMOD '17), May 2017.
• H. Herodotou. Towards a Distributed Multi-tier File System for Cluster Computing. Proc. of the Intl. Workshop on Big Data Management on Emerging Hardware (HardBD ’16), May 2016.
• H. Herodotou. A Distributed File System with Storage-Media Awareness. Poster in Proc. of the 2015 IEEE/ACM 8th Intl. Conf. on Utility and Cloud Computing (UCC ’15), December 2015.

Cloud Computing Systems and Networks

• S. Elnikety, M. Syamala, V. Narasayya, H. Herodotou, P. Tomita, A. Chen, J. Zhang, and J. Wang. PerfIso: Performance Isolation for Commercial Latency-Sensitive Services. In Proc. of the USENIX Annual Technical Conference (USENIX ATC '18), pp. 519-531, July 2018.
• H. Herodotou. Business Intelligence and Analytics: Big Systems for Big Data. In R.Edgeman, E. G. Carayannis, and S. Sindakis (editors), Analytics, Innovation and Excellence-Driven Enterprise Sustainability. Palgrave Macmillan, January 2017.
• H. Herodotou, B. Ding, S. Balakrishnan, G. Outhred, and P. Fitter. Scalable Near Real-time Failure Localization of Data Center Networks. In Proc. of the 20th ACM Intl. Conf. on Knowledge Discovery and Data Mining (SIGKDD ’14), pp. 1689-1698, August 2014.
• S. Babu and H. Herodotou. Massively Parallel Databases and MapReduce Systems. Foundations and Trends in Databases, Vol. 5, No. 1, pp. 1-104, November 2013.

Software Development Systems for Multi-Wearable Apps

• A. Pamboris, P. Andreou, H. Herodotou, and G. Samaras. MULTI-WEAR: A Multi-Wearable Platform For Enhancing Mobile Experiences. In Proc. of the 15th IEEE Annual Consumer Communications & Networking Conference (CCNC '18), January 2018
• S. E. Alshaal, S. Michael, A. Pamboris, H. Herodotou, G. Samaras and P. Andreou. Augmenting Virtual Reality Environments with Smart Wearable Devices. Demo in Proc. of the 17th IEEE Intl. Conf. on Mobile Data Management (MDM ’16), June 2016.

Automated Tuning for Large-scale Data Processing Systems

• H. Herodotou. Automatic Tuning of Data-Intensive Analytical Workloads. LAP LAMBERT Academic Publishing, Saarbrucken, Germany, December 2016.
• M. Ead, H. Herodotou, A. Aboulnaga, and S. Babu. PStorM: Profile Storage and Matching for Feedback-Based Tuning of MapReduce Jobs. In Proc. of the 17th Intl. Conf. on Extending Database Technology (EDBT ’14), pp. 1-12, March 2014.
• H. Herodotou and S. Babu. A What-if Engine for Cost-based MapReduce Optimization. Bulletin of the IEEE Computer Society Technical Committee on Data Engineering, Vol. 36, No. 1, pp. 5-14, March 2013.
• H. Lim, H. Herodotou, and S. Babu. Stubby: A Transformation-based Optimizer for MapReduce Workflows. Proc. of VLDB Endowment (PVLDB ’12), Vol. 5, No. 1, pp. 1196-1207, August 2012.
• H. Herodotou. Automatic Tuning of Data-Intensive Analytical Workloads. Ph.D. Dissertation, Duke University, April 2012.
• H. Herodotou, F. Dong, and S. Babu. No One (Cluster) Size Fits All: Automatic Cluster Sizing for Data-intensive Analytics. In Proc. of the 2nd ACM Symposium on Cloud Computing (SOCC ’11), pp. 18:1-14, October 2011.
• H. Herodotou and S. Babu. Profiling, What-if Analysis, and Cost-based Optimization of MapReduce Programs. Proc. of VLDB Endowment (PVLDB ’11), Vol. 4, No. 11, pp. 1111-1122, August 2011.
• H. Herodotou, F. Dong, and S. Babu. MapReduce Programming and Cost-based Optimization? Crossing this Chasm with Starfish. Demo, Proc. of VLDB Endowment (PVLDB ’11), Vol. 4, No. 12, pp. 1446-1449, August 2011.
• H. Herodotou. Hadoop Performance Models. Technical Report, CS-2011-05, Duke University, February 2011.
• H. Herodotou, H. Lim, G. Luo, N. Borisov, L. Dong, F. B. Cetin, and S. Babu. Starfish: A Self-tuning System for Big Data Analytics. In Proc. of the Fifth Biennial Conf. on Innovative Data Systems Research (CIDR ’11), January 2011.

Database Query Optimization and Tuning

• H. Herodotou, N. Borisov, and S. Babu. Query Optimization Techniques for Partitioned Tables. In Proc. of the ACM Intl. Conf. on Management of Data (SIGMOD ’11), pp. 49-60, June 2011.
• H. Herodotou and S. Babu. Xplus: A SQL-Tuning-Aware Query Optimizer. Proc. of VLDB Endowment (PVLDB ’10), Vol. 3, No. 1-2, pp. 1149-1160, September 2010.
• H. Herodotou and S. Babu. Automated SQL Tuning through Trial and (Sometimes) Error. In Proc. of the Second Intl. Workshop on Testing Database Systems (DBTest ’09), pp. 1-6, June 2009.
• S. Babu, N. Borisov, S. Duan, H. Herodotou, and V. Thummala. Automated Experiment–Driven Management of (Database) Systems. In Proc. of the 12th Workshop on Hot Topics in Operating Systems (HotOS-XII), May 2009.
• H. Herodotou. zTuned: Automated SQL Tuning through Trial and (Sometimes) Error. Master's Thesis, Duke University, April 2009.

Applied Database Technologies

• F. Mitha, H. Herodotou, N. Borisov, C. Jiang, J. Yoder, and K. Owzar. SNPpy - Database Management for SNP Data from Genome Wide Association Studies. PLoS ONE, Vol. 6, No. 10, pp. e24982, October 2011.
• Y. Zhang, H. Herodotou, and J. Yang. RIOT: I/O-Efficient Numerical Computing without SQL. In Proc. of the Fourth Biennial Conf. on Innovative Data Systems Research (CIDR ’09), January 2009.

Google Scholar

http://scholar.google.com/citations?user=jyykiFIAAAAJ&hl=en
 

US Patent 9,367,601 B2. Cost-Based Optimization of Configuration Parameters and Cluster Sizing for Hadoop. June 2016.

US Provisional Patent DU4146PROV. Systems and Methods for Cost-Based Optimization for MapReduce Workflows. March 2013.

Ongoing Research Projects

Sea Traffic Management Validation Project

The primary goal of this research programme is the innovative optimization of processes and services within and between ports based on enhanced collaboration and regulated information sharing among port actors. The Sea Traffic Management concept is a holistic approach to distributed services related to the berth-to-berth voyage enabling the efficient, safe, and environmentally sustainable sea transport.

Funded by: European Commission, Innovation and Networks Executive Agency (INEA), Connecting Europe Facility (CEF)

Role in project: Technical Coordinator for Cyprus University of Technology

Distributed Multi-tier Storage for Cluster Computing

Improvements in memory, storage devices, and network technologies are constantly exploited by distributed systems in order to meet the increasing data storage and I/O demands of modern large-scale data analytics. We present a novel distributed file system that is aware of storage media (e.g., memory, SSDs, HDDs, NAS) with different capacities and performance characteristics. The system offers a spectrum of usage patterns ranging from fully automating data management to providing explicit control by exposing the storage media to users.

Funded by: Cyprus University of Technology Startup Grant

Scaling Transactional Databases with Strong Guarantees

Database replication is a common mechanism used for improving availability and performance of distributed transactional databases but it typically leads to lower degrees of consistency and poor scale out support. Hihooi is a data replication middleware solution that employs a novel fully replicated shared-nothing architecture and a light-weight transaction scheduling algorithm to provide good scalability while offering full ACID guarantees.

Collaborator: Dr. Michael Sirivianos, Cyprus University of Technology

Towards a Unified Platform for Multi-Wearable Apps

Wearable technology has recently become an ubiquitous part of everyday life. Smartwatches, activity trackers, and clothing embedded with sensors are used for monitoring personal fitness data, medical devices for detecting health disorders such as sleep apnea, and professional sports devices for offering real-time feedback for athletes. However, the current landscape of wearable devices suffers from two main issues: (i) each device currently offers only a portion of all the combined capabilities of all the devices, and (ii) most devices do not share data with each other and are tied to certain ecosystems. Hence, there is a strong need for a unified framework that will change the current collection of standalone devices to a fully networked technology connected not only to other external devices (such as smartphones) but also to the cloud.

Collaborators: Dr. Andreas Pamboris, University of Cyprus / Dr. Panayiotis Andreou, UCLan Cyprus

Completed Research Projects

Scalable Near Real-Time Failure Localization of Data Center Networks

Despite the built-in redundancy in data center networks, performance issues and device or link failures in the network can lead to user-perceived service interruptions. Therefore, determining and localizing user-impacting availability and performance issues in the network in near real time is crucial. Our key idea is to use statistical data mining techniques on large-scale active monitoring data to determine a ranked list of suspect causes, which we refine with passive monitoring signals.

Starfish: A Self-tuning System for Big Data Analytics

The Hadoop MapReduce platform is a popular choice for big data analytics. Unfortunately, Hadoop's performance out of the box leaves much to be desired, causing suboptimal use of resources, time, and money. Starfish is a self-tuning system for big data analytics that builds on Hadoop while adapting to system workloads and user needs to provide good performance automatically; without any need for users to understand and manipulate the many tuning knobs in the Hadoop platform.

Query Optimization Techniques for Partitioned Tables

Table partitioning has evolved into a powerful mechanism but is currently not utilized effectively during query optimization. We have developed new techniques to generate efficient plans for SQL queries involving multiway joins over partitioned tables. The techniques are designed for easy incorporation into bottom-up query optimizers and have been prototyped in PostgreSQL.

Automating the Process of SQL Tuning

zTuned is a new system that automates SQL tuning using an experiment–driven approach. The nontrivial challenge is to plan the best set of experiments to conduct so that a satisfactory (new) plan can be found quickly. A novel feature of zTuned is a SQL-tuning-aware query optimizer, called Xplus, capable of executing plans proactively, collecting monitoring data from the runs, and iterating. Xplus has been prototyped using PostgreSQL.
 

2017-1-CY01-KA202-026728: ENGineering and Industry Innovative Training for Engineers (ENGINITE)

• Funded By: Foundation for the Management of European Lifelong Learning Programmes
• Total Budget: 220K euro
• Budget for CUT: 42K euro
• Coordinator: Cyprus University of Technology
• Partners: 7 partners from 4 European countries
• Duration: 2017 –2019
• Webpage: https://www.enginite.eu/

2014-EU-TM-0206-S: Sea Traffic Management Validation Project

• Funded By: European Commission, Innovation and Networks Executive Agency (INEA), Connecting Europe Facility (CEF)
• Total Budget: 42,9M euro
• Budget for CUT: 860K euro
• Partners: 39 partners from 13 European countries
• Role in Project: Technical Coordinator for CUT
• Duration: 2015-2018
• Webpage: http://stmvalidation.eu/

H2020-TWINN-2015: Network for Social Computing Research (NOTRE)

• Funded By: Funded By: European Commission, Horizon 2020
• Total Budget: 1M euro
• Budget for CUT: 450K euro
• Coordinator: Cyprus University of Technology
• Partners: IMDEA, UNIGE, UDUS, FORTH
• Duration: 2016-2018
• Webpage: http://notre.socialcomputing.eu/

Distributed Multi-tier Storage for Cluster Computing

• Funded By: Cyprus University of Technology Starting Grant
• Total Budget: 40K euro
• Role in Project: Principal Investigator
• Duration: 2015-2016

Program Committee Chair

• 16th Hellenic Data Management Symposium, HDMS 2018
• 9th International Workshop on Self-Managing Database Systems, SMDB 2014

Program Committee Member

• International Conference on Very Large Data Bases, VLDB 2018, 2016, 2015, 2013
• IEEE International Conference on Data Engineering, ICDE 2018
• International Conference on Cloud Computing, GRIDs, and Virtualization, CLOUD 2018, 2017
• Hellenic Data Management Symposium, HDMS 2017, 2016
• ACM International Conference on Management of Data, SIGMOD 2016
• International Conference on Utility and Cloud Computing, UCC 2016
• Workshop on Cloud Data Management, CloudDM 2015
• ACM International Conference on Information and Knowledge Management, CIKM 2013
• Workshop on Management of Big Data Systems, MBDS 2012

Journal Reviewer

• IEEE Transactions on Knowledge and Data Engineering, TKDE 2017, 2015, 2014, 2013, 2010
• ACM Transactions on Autonomous and Adaptive Systems, TAAS 2017
• IEEE Transactions on Parallel and Distributed Systems, TPDS 2017, 2014, 2013
• International Journal on Very Large Data Bases, VLDB Journal 2015, 2014, 2013, 2011

Professional Memberships

• Member of the Association for Computing Machinery (ACM)
• Member of the Institute of Electrical and Electronics Engineers (IEEE)

CEI 325 - Database Systems

The course gives a solid background in databases with a focus on relational database management systems. Topics include data modeling, database design theory and methodology, data definition and manipulation languages, storage and indexing techniques, query processing and optimization, transactions, concurrency control, and recovery. The course also covers fundamentals of database management system architecture and techniques for database application development.

CEI 467/526 - Advanced Topics in Data Processing Systems

The need to store and process massive amounts of data has led to the evolution of existing database systems while a new breed of data processing systems has emerged. This course covers a spectrum of topics from core techniques in relational data management to highly-scalable data processing using parallel database systems and MapReduce. First, the course covers the basic principles in database query processing and optimization, including index structures, sort and join processing, query rewrites, and physical plan selection. Next, the course covers topics from parallel and distributed databases, including data partitioning and distributed join algorithms. Finally, the course covers scalable data processing systems such as MapReduce and NoSQL databases (column, document, and key-value stores). The course material will be drawn from textbooks as well as recent research literature. Prerequisite background: Basic database knowledge.

CEI 226 - Algorithms and Complexity

The course focuses on the design and analysis of efficient algorithms and their complexity. In particular, the course covers various topics including algorithm analysis, asymptotic analysis, recurrence relations, divide-and-conquer algorithms, dynamic programming, greedy algorithms, graph representation, graph search, minimum spanning trees, shortest paths, maximum flow, NP-Completeness, and approximation algorithms. Prerequisite background: Data Structures.