Publikationer

Relaterade till projektet

A Blockchain-based Approach for Assessing Compliance with SLA-guaranteed IoT Services

2020 IEEE International Conference on Smart Internet of Things (SmartIoT), Beijing, China, 2020, pp. 213-220, doi: 10.1109/SmartIoT49966.2020.00039.

A. Alzubaidi, K. Mitra, P. Patel and E. Solaiman

Abstract
Big data processing systems, such as Hadoop and Spark, usually work on large-scale, highly-concurrent, and multi-tenant environments that can easily cause hardware and software malfunctions or failures, thereby leading to performance degradation. Several systems and methods exist to detect big data processing systems’ performance degradation, perform root-cause analysis, and even overcome the issues causing such degradation. However, these solutions focus on specific problems such as straggler and inefficient resource utilization. There is a lack of a generic and extensible framework to support the real-time diagnosis of big data systems. In this paper, we propose, develop and validate AutoDiagn. This generic and flexible framework provides holistic monitoring of a big data system while detecting performance degradation and enabling root-cause analysis. We present the implementation and evaluation of AutoDiagn that interacts with a Hadoop cluster deployed on a public cloud and tested with real-world benchmark applications. Experimental results show that AutoDiagn has a small resource footprint, high throughput and low latency.

Experiences and Challenges of Providing IoT-Based Care for Elderly in Real-Life Smart Home Environments.

Scalable Computing and Communications. Springer, Cham. (2020)

Saguna S., Åhlund C., Larsson A

Abstract
Elderly population across the world is on the rise and municipalities along with caregivers are struggling to provide care due to limited resources. Sweden’s elderly population is set to grow significantly by 2050 where the number of people between 65–79 years and 80 years and over is expected to increase by 45% and 87% respectively [1]. The same trend continues within Europe where 25% of the population will be over 65 years of age by the year 2020, and the age group of 65–80 years is predicted to rise by 40% from the year 2010 to 2030 [2]. The rise in elderly population has increased the stress on municipalities and caregivers; and has created the need for new healthcare solutions that are feasible, affordable and easily accessible to all. Smart homes equipped with sensors have already made life easier for those living in them for many decades now by providing home automation solutions. We are also witnessing an increase in the use of Information Communication Technologies (ICT) to assist elderly population and decrease in operational costs. ICT systems in assisting elderly population have an immense potential for providing in-home care to the elderly [3]. The advent of the Internet of Things (IoT) with low-cost and prolific sensors has furthered this trend of home automation and monitoring solutions being used for elderly healthcare [4, 5]. Alongside, the field of ambient assisted homes has continuously paved the way for providing an improved quality of life for those in need such as patients with dementia or chronic conditions as well as elderly living alone at home [5–7].

Context-Aware IoT-Enabled Cyber-Physical Systems: A Vision and Future Directions.

Springer, Cham. (2020)

Mitra K., Ranjan R., Åhlund C

Abstract
The next-generation cyber-physical systems (CPSs) will not only be limited to industries but will span across multiple application-areas regarding smart cities and regions. These CPSs will leverage the recent advancements in the areas of cloud computing, Internet of Things and big data to provision citizen-centric applications and services such as smart hybrid energy grids, smart waste management, smart healthcare and smart transportation. Challenges regarding context-awareness, quality of service and quality of experience, mobility management, middleware platforms, service level agreements, trust, and privacy needs to be solved to realize such CPSs. This chapter discusses these challenges in detail and proposes ICICLE – a context-aware IoT-enabled cyber-physical system as a blueprint for next-generation CPSs.

Handbook of Integration of Cloud Computing, Cyber Physical Systems and Internet of Things.

Scalable Computing and Communications. Springer, Cham

Ranjan R., Mitra K., Prakash Jayaraman P., Wang L., Zomaya A.Y. (eds)

Abstract
This handbook covers recent advances in the integration of three areas, namely, cloud computing, cyber-physical systems, and the Internet of things which is expected to have a tremendous impact on our daily lives. It contains a total of thirteen peer-reviewed and edited chapters. This book covers topics such as context-aware cyber-physical systems, sustainable cloud computing, fog computing, and cloud monitoring; both the theoretical and practical aspects belonging to these topics are discussed. All the chapters also discuss open research challenges in the areas mentioned above. Finally, the handbook presents three use cases regarding healthcare, smart buildings and disaster management to assist the audience in understanding how to develop next-generation IoT- and cloud-enabled cyber-physical systems. This timely handbook is edited for students, researchers, as well as professionals who are interested in the rapidly growing fields of cloud computing, cyber-physical systems, and the Internet of things.

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

Abstract
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

Abstract

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

Abstract

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

Abstract

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

Abstract

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

Abstract

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.

Anomaly Detection using Machine Learning to Discover Sensor Tampering in IoT Systems

Aditya Kumar Pathak, Saguna Saguna, Karan Mitra, Christer Åhlund

Abstract

With the rapid growth of the Internet of Things (IoT) applications in smart regions/cities, for example, smart healthcare, smart homes/offices, there is an increase in security threats and risks. The IoT devices solve real-world problems by providing real-time connections, data and information. Besides this, the attackers can tamper with sensors, add or remove them physically or remotely. In this study, we address the IoT security sensor tampering issue in an office environment. We collect data from real-life settings and apply machine learning to detect sensor tampering using two methods. First, a real-time view of the traffic patterns is considered to train our isolation forest-based unsupervised machine learning method for anomaly detection. Second, based on traffic patterns, labels are created, and the decision tree supervised method is used, within our novel Anomaly Detection using Machine Learning (AD-ML) system. The accuracy of the two proposed models is presented. We found 84% with silhouette metric accuracy of isolation forest. Moreover, the result based on 10 cross-validations for decision trees on the supervised machine learning model returned the highest classification accuracy of 91.62% with the lowest false positive rate.

Augmented Reality-Assisted Healthcare System for Caregivers in Smart Regions. (Winner: Best paper award).

2021 IEEE International Smart Cities Conference (ISC2)

J.C. Kim, S. Saguna, C. Åhlund and K. Mitra

Abstract

The rise in the aging population worldwide is already negatively impacting healthcare systems due to the lack of resources. It is envisioned that the development of novel Internet of Things (IoT)-enabled smart city healthcare systems may not only alleviate the stress on the current healthcare systems but may significantly improve the overall quality of life of the elderly. As more elderly homes are fitted with IoT, and intelligent healthcare becomes the norm, there is a need to develop innovative augmented reality (AR) based applications and services that make it easier for caregivers to interact with such systems and assist the elderly on a daily basis. This paper proposes, develops, and validates an AR and IoT-enabled healthcare system to be used by caregivers. The proposed system is based on a smart city IoT middleware platform and provides a standardized, intuitive and non-intrusive way to deliver elderly person’s information to caregivers. We present our prototype, and our experimental results show the efficiency of our system in IoT object detection and relevant information retrieval tasks. The average execution time, including object detection, communicating with a server, and rendering the results in the application, takes on average between 767ms and 1,283ms.

An Automated Real-time Diagnosis Framework for Big Data Systems

Demirbaga U, Wen Z, Noor A, Mitra K, Alwasel K, Garg S, Zomaya A, Ranjan R.

Abstract

With the rapid growth of the Internet of Things (IoT) applications in smart regions/cities, for example, smart healthcare, smart homes/offices, there is an increase in security threats and risks. The IoT devices solve real-world problems by providing real-time connections, data and information. Besides this, the attackers can tamper with sensors, add or remove them physically or remotely. In this study, we address the IoT security sensor tampering issue in an office environment. We collect data from real-life settings and apply machine learning to detect sensor tampering using two methods. First, a real-time view of the traffic patterns is considered to train our isolation forest-based unsupervised machine learning method for anomaly detection. Second, based on traffic patterns, labels are created, and the decision tree supervised method is used, within our novel Anomaly Detection using Machine Learning (AD-ML) system. The accuracy of the two proposed models is presented. We found 84% with silhouette metric accuracy of isolation forest. Moreover, the result based on 10 cross-validations for decision trees on the supervised machine learning model returned the highest classification accuracy of 91.62% with the lowest false positive rate.

Smart Contract Design Considerations for SLA Compliance Assessment in the Context of IoT. (Winner: Best paper candidate award).

2021 IEEE International Conference on Smart Internet of Things (IEEE SmartIoT2021)

A. Alzubaidi, K. Mitra, E. Solaiman

Abstract

One of the main drivers behind blockchain adoption is a lack of trust among entities serving a common goal, but with different interests. Following the success of Bitcoin, several blockchain platforms have emerged, such as Ethereum and Hyperledger Fabric, to enable conducting distrusted processes in a non-repudiable manner. However, it is not safe to assume the applicability of conventional software design strategies to Blockchain-based solutions. In this paper, we assume an untrusted SLA (service level agreement) relationship between an IoT service provider and its consumer. We adopt Hyperledger Fabric for the purpose of implementing SLA compliance assessment. We design a smart contract that takes blockchain unique features into consideration. The design particularly accounts for the MVCC (multiversion concurrency control) mechanism, which while effective for resolving the double spending problem, causes read-write conflicts when high transmission rates are experienced between the IoT application and the blockchain. Using a fire station event monitoring scenario, we describe our smart contract design and solution for conflicting transactions. We experimentally evaluate our solution and demonstrate clear performance improvements in terms of throughput and latency.

Toward Distributed, Global, Deep Learning Using IoT Devices

IEEE Internet Computing, vol. 25, no. 3, pp. 6-12, 1 May-June 2021

B. Sudharsan et al

Abstract

Deep learning (DL) using large scale, high-quality IoT datasets can be computationally expensive. Utilizing such datasets to produce a problem-solving model within a reasonable time frame requires a scalable distributed training platform/system. We present a novel approach where to train one DL model on the hardware of thousands of mid-sized IoT devices across the world, rather than the use of GPU cluster available within a data center. We analyze the scalability and model convergence of the subsequently generated model, identify three bottlenecks that are: high computational operations, time consuming dataset loading I/O, and the slow exchange of model gradients. To highlight research challenges for globally distributed DL training and classification, we consider a case study from the video data processing domain. A need for a two-step deep compression method, which increases the training speed and scalability of DL training processing, is also outlined. Our initial experimental validation shows that the proposed method is able to improve the tolerance of the distributed training process to varying internet bandwidth, latency, and Quality of Service metrics.