Thesis Presentations Group 2

Title: A Framework and a Web Application for self-assessment of Sustainable Green ICT practices in SMEs
Author: Khan, Farniba
Supervisor(s): Professor Jari Porras
Hosting Institution: Lappeenranta University of Technology
Abstract: Insert thesis abstract(200 words)
Paper: Insert link to thesis paper.

Title: A Belief Rule-Based Flood Risk Assessment Expert System using Real-Time Sensor Data Streaming
Author: Monrat, Ahmed Afif
Supervisor(s): Professor Mohammad Shahadat Hossain; Professor Karl Andersson
Hosting Institution: Luleå University of Technology, University of Chittagong
Abstract: Among the various natural calamities, flood is considered one of the most catastrophic natural hazards, which has disastrous impact on the socio-economic lifeline of a country. Assessing flood risks will allow to take proper precautions before it occurs to save human lives along with their residential and commercial properties. However, the assessment of risks involves severe uncertainty as crisis response teams need to take decisions based on the huge amount of incomplete and inaccurate information, which are mainly coming from sensor streaming in real time. Therefore, the present methods of flood risk assessment cannot assess the risk of flooding accurately. This paper rigorously investigates various types of uncertainties associated with different factors and voluminous dataset along with BRBES’s approach to develop an expert system which will be integrated with Big Data platform to assess flood risk in real time. In addition, a comprehensive study of the data-driven approach in comparison with the knowledge-driven approach regarding flood risk assessment has been conducted. The system processes all the complex mathematical computation on extremely large dataset through Spark machine learning library at the backend and through a web-based interface, the users can monitor the risk of flood in real time. In order to check the reliability of the system, a comparison has been performed among various approaches such as linear regression, decision tree, random forest, artificial neural network and experts’ opinion while the BRBES produces reliable results than from the other approaches. This research explores the challenges, opportunities and methods, required to leverage the potentiality of Big Data and BRBES to assess the risk of flooding.
Paper: Insert link to thesis paper.

Title: Performance Evaluation of IoT Platform in Green ICT Applications
Author: Qureshi, Daniyal Akhtar
Supervisor(s): Prof. Arkady Zaslavsky; Dr. Karan Mitra; Dr. Saguna Saguna
Hosting Institution: Commonwealth Scientific and Industrial Research Organisation; Lulea University of Technology
Abstract: With the advent of Internet of Things (IoT), its deployments and applications has grown in an exponential rate during the past few years. This growth has led scientists, stakeholders, and industrial companies to the prediction that about 50 billion of things (IoT) will be installed by 2020 in diverse applications such as transport, healthcare, utility, education and home automation. Large data streams generated by sensors; be it data acquisition, storage, or processing, this expansion in physical deployments and connecting things drive the development of cloud-based middleware for management. To date, hundreds of IoT platforms fluxing the market (both open-source and commercial) with various complexities, pricing and services. This paper, we will develop a methodology based on TPC benchmarking to evaluate the performance of cloud-based framework or otherwise known as IoT Platform. The main objective of this research is to provide insight into key parameters in each layer of the platform affecting the overall performance of the framework. Air quality monitoring using OpenIoT (an open source IoT Platform) as a use-case will be used for the deployment of methodology.
Paper: Insert link to thesis paper.

Title: Architecting and Designing Sustainable Smart City Services in Living Lab Environment
Author: Alam, Md Tawseef
Supervisor(s): Professor Jari Porras; Professor Ahmed Seffah
Hosting Institution: Lappeenranta University of Technology
Abstract: Insert thesis abstract(200 words)
Paper: Insert link to thesis paper.

Title: Energy - Aware Cloud Infrastructure for IoT Big Data Processing
Author: Ganesan, Madhubala
Supervisor(s): Prof. Colin Pattinson; Dr. Ah-Lian Kor
Hosting Institution: Leeds Beckett University
Abstract: Internet of Things (IoT) along with Big Data Analytics is poised to become the backbone of Smart and Sustainable Systems which bolster economic, environmental and social sustainability. Cloud-based data centers provide computing power to churn out valuable information from voluminous IoT data. Multifarious servers in the data centers turn out to be the black hole of superfluous energy burn contributing to 23% of the global Carbon dioxide (CO2) emissions in ICT industry. IoT energy concerns are addressed by researches carried out on low-power sensors and improved Machine-to-Machine communications. However, cloud-based data centers still face energy–related challenges. Virtual Machine (VM) consolidation is an approach towards energy efficient cloud infrastructure. Although several works show convincing results of the potential of VM consolidation in simulated environments, there is inadequacy in terms of investigations on real, physical cloud infrastructure for big data workloads. This work intends to evaluate dynamic VM consolidation approaches by combining algorithms from literature. An open source VM consolidation framework, Openstack NEAT is adopted and experiments are conducted on a Multi-node Openstack Cloud with Apache Spark as Big data platform. This work studies the performance based on Service Level Agreement (SLA) metrics and energy usage of compute hosts. The corresponding results are presented based on which the best combination of algorithms is recommended.
Paper: Insert link to thesis paper.