Mariam’s research focuses on learning and decentralized optimization of system architectures and algorithms for high performance computing, underlying networks and Cloud infrastructures. She has been exploring various platforms such as HPC grids, GPUs, Cloud and SDN-related technologies. Her work involves optimization of QoS, performance using parallelization algorithms and software engineering principles to solve complex data intensive problems such as large-scale complex simulations. Over the years, she has been working with biologists, economists, social scientists, building tools and performing optimization of architectures for multiple problems in their domain.
Mariam joins ESnet as a Research Scientist, working on intent-based networking and engineering intelligent networks for optimizing performance and user experience. Before coming to Berkeley Lab, she worked as an Associate Professor at University of Bradford (UK), focusing on Software engineering and building her Cloud Computing research group, looking at infrastructure-related issues particularly exploring Openstack, AWS and Azure, building an in-house cloud for experimentation called BradStack. Previous to this, she held Postdoctoral research positions at University of Leeds and Sheffield working on HPC and MultiCloud optimization problems. Her work has led to multiple publications in the area of optimizing agent-based simulations over HPC and Cloud, building virtual platforms, Internet of things (IoT) and been involved in multiple EU-research projects and initiatives. She finished her PhD in Computer Science and MSc (Eng) in Software Engineering from University of Sheffield (UK) in 2010 and 2007 respectively.
Please visit Google Scholar for an updated list of publications.
Machine learning and Networks
- FLAME (http://www.flame.ac.uk)
Agent-based modelling platform which allows users to create decentralized models in various fields such as biology, social networks and economics. FLAME allows programming of intelligent agents to study how complex systems evolve when decentralized learning and game theory principles apply. FLAME automates parallelization of agent code using MPI for HPC and GPU tools.
- Optimis (http://www.optimis-project.eu/)
Cloud computing software which allows building clouds that can provision on demand resources based on trust, risk, energy and cost demands. Optimis was part of an EU-funded FP7 project and released software tools via Atos (Spain) and BT (UK).
Cloud computing project to investigate building clouds from ground using minimum hardware resources and experimenting with Openstack solutions. This project was an internal research group project to allow PhD students to understand how clouds exist and test out their fault tolerance and performance modelling tools on a in-house cloud infrastructure.
M. Gribaudo, M. Iacono, M. Kiran, “A performance modeling framework for lambda architecture based applications”, Future Generation Computer Systems, August 30, 2017,
M Kiran, E Pouyoul, A Mercian, B Tierney, C Guok, I Monga, “Enabling intent to configure scientific networks for high performance demands”, Future Generation Computer Systems, August 2, 2017,
Tatyana Eftonova, Mariam Kiran, Mike Stannett, “Long-term Macroeconomic Dynamics of Competition in the Russian Economy using Agent-based Modelling”, International Journal of System Dynamics Applications (IJSDA) 6 (1), 1-20, 2017, January 1, 2017,
Mariam Kiran, Anthony Simons, “Testing Software Services in Cloud Ecosystems”, International Journal of Cloud Applications and Computing (IJCAC) 6 (1), 42-58 2016, July 1, 2016,
M Kiran, G Katsaros, J Guitart, J L Prieto, “Methodology for Information Management and Data Assessment in Cloud Environments”, International Journal of Grid and High Performance Computing (IJGHPC), 6(4), 46-71, June 1, 2015,
M Kiran, “Modelling Cities as a Collection of TeraSystems–Computational Challenges in Multi-Agent Approach”, Procedia Computer Science 52, 974-979, 2015, June 1, 2015,
K. Djemame, B Barnitzke, M Corrales, M Kiran, M Jiang, D Armstrong, N Forgo, I Nwankwo, “Legal issues in clouds: towards a risk inventory”, Philosophical Transactions of the Royal Society of London A: Mathematical, Physical and Engineering Sciences, 371, 1983, The Royal Society, June 1, 2014,
M Holcombe, S Chin, S Cincotti, M Raberto, A Teglio, S Coakley, C Deissenberg, S vander Hoog, C Greenough, H Dawid, M Neugart, S Gemkow, P Harting, M Kiran, D Worth, “Large-scale modelling of economic systems”, Complex Systems 22 (2) 8 2013, June 1, 2013,
M.Holcombe, S.Adra, M.Bicak, S.Chin, S.Coakley, A.I.Graham, J.Green, C.Greenough, D.Jackson, M.Kiran, S.MacNeil, A.Maleki-Dizaji, P.McMinn, M.Pogson, R.Poole, E.Qwarnstrom, F.Ratnieks, M.D.Rolfe, R.Smallwood, T.Sun and D.Worth, “Modelling complex biological systems using an agent-based approach,”, Integrative Biology, 2012, June 1, 2012,
M.Kiran, M.Bicak, S.Maleki-Dizaji, M.Holcombe, “FLAME: A Platform for High Performance Computing of Complex Systems, Applied for Three Case Studies”, Acta Physica Polonica B, Proceedings Supplement, DOI:10.5506/APhysPolBSupp.4.201, PACS numbers: 07.05.Tp, vol 4, no 2, 2011 (Polish Journal), January 1, 2012,
Mariam Kiran, Simon Coakley, Neil Walkinshaw, Phil McMinn, Mike Holcombe, “Validation and discovery from computational biology models”, Biosystems, September 1, 2009,
S Khan, T Yairi, M Kiran, “Towards a Cloud-based Machine Learning for Health Monitoring and Fault Diagnosis”, Asia Pacific Conference of the Prognostics and Health Management Society 2017, August 1, 2017,
A Mercian, M Kiran, E Pouyoul, B Tierney, I Monga, “INDIRA:‘Application Intent’ network assistant to configure SDN-based high performance scientific networks”, Optical Fiber Communication Conference, July 1, 2017,
M Usman, A Iqbal, M Kiran, “A Bandwidth Friendly Architecture for Cloud Gaming”, 31st International Conference on Information Networking (ICOIN 2017), December 1, 2016,
M Kiran, E Pouyoul, A Mercian, B Tierney, C Guok, I Monga, “Enabling Intent to Configure Scientific Networks for High Performance Demands”, 3nd International Workshop on Innovating the Network for Data Intensive Science (INDIS) 2016, SC16., November 10, 2016,
- Download File: indis-final-2016.pdf (pdf: 745 KB)
B Mohammed, M Kiran, IU Awan, KM Maiyama, “Optimising Fault Tolerance in Real-Time Cloud Computing IaaS Environment”, Future Internet of Things and Cloud (FiCloud), 2016 IEEE 4th International, 2016, September 15, 2016,
M Kiran, “Women in HPC: Changing the Face of HPC”, SC15: HPC transforms, 2015, Austin Texas, November 15, 2015,
M Kiran, “Multiple platforms: Issues of porting Agent-Based Simulation from Grids to Graphics cards”, Workshop on Portability Among HPC Architectures for Scientific Applications, SC15: HPC transforms, 2015, Austin Texas., November 15, 2015,
P Yadav, M Kiran, A Bennaceur, L Georgieva, M Salama and A E Cano, “Jack of all Trades versus Master of one”, Grace Hopper 2015 Conference, November, 2015, November 1, 2015,
Mariam Kiran, Peter Murphy, Inder Monga, Jon Dugan, Sartaj Baveja, “Lambda Architecture for Cost-effective Batch and Speed Big Data processing”, First Workshop on Data-Centric Infrastructure for Big Data Science (DIBS), October 29, 2015,
- Download File: DIBS-Final-Paper-2015.pdf (pdf: 532 KB)
This paper presents an implementation of the lambda architecture design pattern to construct a data-handling backend on Amazon EC2, providing high throughput, dense and intense data demand delivered as services, minimizing the cost of the network maintenance. This paper combines ideas from database management, cost models, query management and cloud computing to present a general architecture that could be applied in any given scenario where affordable online data processing of Big Datasets is needed. The results are presented with a case study of processing router sensor data on the current ESnet network data as a working example of the approach. The results showcase a reduction in cost and argue benefits for performing online analysis and anomaly detection for sensor data