Related to the project

Performance Evaluation of FIWARE: A Cloud-Based IoT Platform for Smart Cities

Journal of Parallel and Distributed Computing Systems, Elsevier, 2019

Victor Araujo, Karan Mitra,  Saguna Saguna, Christer Åhlund

As the Internet of Things (IoT) becomes a reality, millions of devices will be connected to IoT platforms in smart cities. These devices will cater to several areas within a smart city such as healthcare, logistics, and transportation. These devices are expected to generate significant amounts of data requests at high data rates, therefore, necessitating the performance benchmarking of IoT platforms to ascertain whether they can efficiently handle such devices. In this article, we present our results gathered from extensive performance evaluation of the cloud-based IoT platform, FIWARE. In particular, to study FIWARE’s performance, we developed a testbed and generated CoAP and MQTT data to emulate large-scale IoT deployments, crucial for future smart cities. We performed extensive tests and studied FIWARE’s performance regarding vertical and horizontal scalability. We present bottlenecks and limitations regarding FIWARE components and their cloud deployment. Finally, we discuss cost-efficient FIWARE deployment strategies that can be extremely beneficial to stakeholders aiming to deploy FIWARE as an IoT platform for smart cities.

Propagation Model Evaluation for LoRaWAN: Planning Tool Versus Real Case Scenario

Proceedings of  The IEEE 5th World Forum on Internet of Things (WF-IoT) 2019, Limerick Ireland

Nibia Souza Bezerra, Christer Åhlund, Saguna Saguna, Vicente A. de Sousa Jr


LoRa has emerged as a prominent technology for the Internet of Things (IoT), with LoRa Wide Area Network (LoRaWAN) emerging as a suitable connection solution for smart things. The choice of the best location for the installation of gateways, as well as a robust network server configuration, are key to the deployment of a LoRaWAN. In this paper, we present an evaluation of Received Signal Strength Indication (RSSI) values collected from the real-life LoRaWAN deployed in Skelleftea, Sweden, when compared with the values calculated by a Radio Frequency (RF) planning tool for the Irregular Terrain Model (ITM), Irregular Terrain with Obstructions Model (ITWOM) and Okumura-Hata propagation models. Five sensors are configured and deployed along a wooden bridge, with different Spreading Factors (SFs), such as SF 7, 10 and 12. Our results show that the RSSI values calculated using the RF planning tool for ITWOM are closest to the values obtained from the real-life LoRaWAN. Moreover, we also show evidence that the choice of a propagation model in an RF planning tool has to be made with care, mainly due to the terrain conditions of the area where the network and the sensors are deployed.

Performance Evaluation of Scalable and Distributed IoT Platforms for Smart Regions

Masters Thesis, Luleå University of Technology, Sweden, 2017

Victor Araujo


As the vision of the Internet of Things (IoT) becomes a reality, thousands of devices will be connected to IoT platforms in smart cities and regions. These devices will actively send data updatestocloud-basedplatforms,aspartofsmartapplicationsindomainslikehealthcare,traffic and pollution monitoring. Therefore, it is important to study the ability of modern IoT systems to handle high rates of data updates coming from devices. In this work we evaluated the performance of components of the Internet of Things Services Enablement Architecture of the European initiative FIWARE. We developed a testbed that is able to inject data updates using MQTT and the CoAP-based Lightweight M2M protocols, simulating large scale IoT deployments. Our extensive tests considered the vertical and horizontal scalability of the components oftheplatform. Ourresultsfoundthelimitsofthecomponentswhenhandlingtheload, andthe scaling strategies that should be targeted by implementers. We found that vertical scaling is not an effective strategy in comparison to the gains achieved by horizontally scaling the database layer. We reflect about the load testing methodology for IoT systems, the scalability needs of different layers and conclude with future challenges in this topic.

Analysis and Estimation of Video QoE in Wireless Cellular Networks using Machine Learning

Proceedings of the  11th International Conference on Quality of Multimedia Experience (QoMEX), Berlin, Germany, 2019

Dimitar Minovski, Christer Åhlund, Karan Mitra, Per Johansson


The use of video streaming services are increasing in the cellular networks, inferring a need to monitor video quality to meet users’ Quality of Experience (QoE). The so-called no-reference (NR) models for estimating video quality metrics mainly rely on packet-header and bitstream information. However, there are situations where the availability of such information is limited due to tighten security and encryption, which necessitates exploration of alternative parameters for conducting video QoE assessment. In this study we collect real-live in-smartphone measurements describing the radio link of the LTE connection while streaming reference videos in uplink. The radio measurements include metrics such as RSSI, RSRP, RSRQ, and CINR. We then use these radio metrics to train a Random Forrest machine learning model against calculated video quality metrics from the reference videos. The aim is to estimate the Mean Opinion Score (MOS), PSNR, Frame delay, Frame skips, and Blurriness. Our result show 94% classification accuracy, and 85% model accuracy (R 2 value) when predicting the MOS using regression. Correspondingly, we achieve 89%, 84%, 85%, and 82% classification accuracy when predicting PSNR, Frame delay, Frame Skips, and Blurriness respectively. Further, we achieve 81%, 77%, 79%, and 75% model accuracy (R 2 value) regarding the same parameters using regression

ALPINE: A Bayesian System for Cloud Performance Diagnosis and Prediction

The 14th IEEE International Conference on Services Computing (IEEE SCC 2017), Honolulu, Hawaii

Karan Mitra, Saguna Saguna, Christer Ahlund, Rajiv Ranjan


Cloud performance diagnosis and prediction is a challenging problem due to the stochastic nature of the cloud systems. Cloud performance is affected by a large set of factors including (but not limited to) virtual machine types, regions, workloads, wide area network delay and bandwidth. Therefore, necessitating the determination of complex relationships between these factors. The current research in this area does not address the challenge of building models that capture the uncertain and complex relationships between these factors. Further, the challenge of cloud performance prediction under uncertainty has not garnered sufficient attention. This paper proposes develops and validates ALPINE, a Bayesian system for cloud performance diagnosis and prediction. ALPINE incorporates Bayesian networks to model uncertain and complex relationships between several factors mentioned above. It handles missing, scarce and sparse data to diagnose and predict stochastic cloud performance efficiently. We validate our proposed system using extensive real data and trace-driven analysis and show that it predicts cloud performance with high accuracy of 91.93%.

A Bayesian System for Cloud Performance Diagnosis and Prediction

Proceedings of the 8th IEEE International Conference on Cloud Computing Technology and Science (IEEE CloudCom 2016), Luxembourg

Emanuel Palm, Karan Mitra, Saguna Saguna, Christer Åhlund


The  stochastic  nature  of  the  cloud  systems  makes
cloud  quality  of  service  (QoS)  performance  diagnosis  and  pre-
diction a challenging task. A plethora of factors including virtual
machine   types,   data   centre   regions,   CPU   types,   time-of-the-
day,  and  day-of-the-week  contribute  to  the  variability  of  the
cloud  QoS.  The  state-of-the-art  methods  for  cloud  performance
diagnosis  do  not  capture  and  model  complex  and  uncertain
inter-dependencies between these factors for efficient cloud QoS
diagnosis and prediction. This paper presents ALPINE, a proof-
of-concept  system  based  on  Bayesian  Networks.  Using  a  real-
life  dataset,  we  demonstrate  that  ALPINE  can  be  utilised  for
efficient  cloud  QoS  diagnosis  and  prediction  under  stochastic
cloud  conditions.