- IoT and Edge/Fog Computing
- Energy Efficient Wireless Sensor Networks
- Context-Aware Activity Recognition Systems
- Privacy-Preserving Technologies in Data
- Caching and Content Delivery
- Internet Traffic Analysis and Secure E-voting
- Cloud Computing and Resource Management
- Mobile Ad Hoc Networks
- Network Security and Intrusion Detection
- Service-Oriented Architecture and Web Services
- Advanced Software Engineering Methodologies
- Blockchain Technology Applications and Security
- Mobile Crowdsensing and Crowdsourcing
- Traffic Prediction and Management Techniques
- Vehicular Ad Hoc Networks (VANETs)
- Human Mobility and Location-Based Analysis
- IoT Networks and Protocols
- Software-Defined Networks and 5G
- Software System Performance and Reliability
- Advanced Neural Network Applications
- Wireless Body Area Networks
- Opportunistic and Delay-Tolerant Networks
- Real-Time Systems Scheduling
- Smart Grid Energy Management
- Machine Learning and ELM
University of Oslo
2016-2025
NTNU Samfunnsforskning
2017-2023
Guilin University of Electronic Technology
2023
Argonne National Laboratory
2023
Norwegian University of Science and Technology
2018-2020
Sonitor Technologies (Norway)
2014-2015
Iran University of Science and Technology
2006
Mobile edge computing (MEC) is an emergent architecture where cloud services are extended to the of networks leveraging mobile base stations. As a promising technology, it can be applied mobile, wireless, and wireline scenarios, using software hardware platforms, located at network in vicinity end-users. MEC provides seamless integration multiple application service providers vendors toward subscribers, enterprises, other vertical segments. It important component 5G which supports variety...
Wireless Sensor Networks (WSNs) typically include thousands of resource-constrained sensors to monitor their surroundings, collect data, and transfer it remote servers for further processing. Although WSNs are considered highly flexible ad-hoc networks, network management has been a fundamental challenge in these types networks given the deployment size associated quality concerns such as resource management, scalability, reliability. Topology is viable technique address concerns. Clustering...
Predicting traffic flow plays an important role in reducing congestion and improving transportation efficiency for smart cities. Traffic Flow Prediction (TFP) the city requires efficient models, highly reliable networks, data privacy. As data, trajectory can be transformed into a graph representation, so as to mine spatio-temporal information of TFP. However, most existing work adopt central training mode where privacy problem brought by distributed is not considered. In this paper, we...
Many Internet of Things (IoT) networks are created as an overlay over traditional ad-hoc such Zigbee. Moreover, IoT can resemble that support device-to-device (D2D) communication, e.g., D2D-enabled cellular and WiFi-Direct. In these <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ad-hoc</i> types networks, efficient xmlns:xlink="http://www.w3.org/1999/xlink">topology management</i> is a crucial requirement, in particular massive scale...
In this article, we present a wireless powered mobile-edge computing system consisting of hybrid access point and multiple cooperative fogs, where the users in each fog can share communication computation resources to improve their performance. Based on classic time-division-multiple-access protocol, propose harvest-and-offload protocol jointly schedule energy transfer offloading. We minimize total consumption by considering beamforming, time-slot assignment, computation-task allocation,...
Modern networks generate a massive amount of traffic data streams. Analyzing this is essential for various purposes, such as network resources management and cyber-security analysis. There an urgent need analytic methods that can perform processing in online manner based on the arrival new data. Online machine learning (OL) techniques promise to support type analytics. In paper, we investigate compare OL facilitate stream analytics networking domain. We also importance highlight advantages...
Abstract Nowadays, due to the exponential and continuous expansion of new paradigms such as Internet Things (IoT), Vehicles (IoV) 6G, world is witnessing a tremendous sharp increase network traffic. In large‐scale, heterogeneous, complex networks, volume transferred data, big data , considered challenge causing different networking inefficiencies. To overcome these challenges, various techniques are introduced monitor performance called Network Traffic Monitoring Analysis (NTMA). Prediction...
In smart grids, the large-scale integration of distributed renewable energy resources has enabled provisioning alternative sources supply. Peer-to-peer (P2P) trading among local households is becoming an emerging technique that benefits both prosumers and operators. Since conventional supply still needed to help fill gap between demand when solar generation not sufficient, demand–response management will keep playing important role in future P2P market. Blockchain contract technology gained...
With the development of technologies deployed on vehicles, there is a significant increase in amount data, which comes from various applications, such as battery management, VR, autopilot, etc. However, privacy critical obstacle to utilizing information since many vehicle-based applications involve locations, conversations, driving behaviors, Federated Learning (FL) promising technology perfect for filling gap, it keeps users' data their devices, gives rise Vehicular Networks (FVN). As...
Network Traffic Classification (NTC) has become an important feature in various network management operations, e.g., Quality of Service (QoS) provisioning and security services. Machine Learning (ML) algorithms as a popular approach for NTC can promise reasonable accuracy classification deal with encrypted traffic. However, ML-based techniques suffer from the shortage labeled traffic data which is case many real-world applications. This study investigates applicability active form ML, called...
Internet of Vehicles (IoV) has attracted global research interests across extensive applications. Due to the significant increase in number vehicles accessing Internet, there are several challenges designing efficient task offloading and data caching strategies improve utilization network resource provide users with high-quality services. To this end, study proposes allocation schemes, including selection execution mode, transmission path, assignment sub-channels, updating a Multi-Access...
Telematics technology development offers vehicles a range of intelligent and convenient functions, including navigation mapping services, driving assistance, traffic management. However, since these functions deal with sensitive information like vehicle location habits, it is crucial to address concerns regarding security privacy protection. Federated learning (FL) highly suitable for addressing such problems due its characteristics, in which client does not need share private data upload...
Wireless reprogramming of sensor nodes is a critical requirement in long-lived wireless networks (WSNs) addressing several concerns, such as fixing bugs, upgrading the operating system and applications, adapting applications behavior according to physical environment. In resource-poor platforms, ability efficiently delimit reconfigure necessary portion software—instead updating full binary image—is vital importance. However, most existing approaches this field have not been adopted widely...
Cloud computing has been recognized as the de facto utility standard for hosting and delivering services over Internet. platforms are being rapidly adopted by business owners end-users thanks to its many benefits traditional models such cost saving, scalability, unlimited storage, anytime anywhere access, better security, high fault-tolerance capability. However, despite fact that clouds offer huge opportunities industry, landscape of cloud research is evolving several reasons, emerging...
Wireless Body Area Network (WBAN) as one of the primary Internet Things (IoT) provides real time and continuous healthcare monitoring has been widely deployed to improve quality peoples' life. In edge-enabled WBANs, intensive computing tasks could be offloaded Mobile Edge Computing (MEC) servers, guaranteeing that massive amount health data with different user priorities processed in lower delay energy consumption. Efficient computation offloading schemes are more critical satisfy access...
With the explosive growth of various connected devices and supported services, satellite-aerial-terrestrial network (SATN) can fulfill requirements increasing data traffic with enlarged coverage enhanced capacity. In particular, utilizing multiple unmanned aerial vehicles (UAVs) as relays in SATN holds great promise for bringing lots benefits terms high flexibility reliability. However, due to limited power UAVs long distance aerial-satellite links, how improve system energy efficiency (EE)...
With the rapid development of Mobile Edge Computing (MEC) technology, computationally intensive requests end devices can be offloaded to MEC servers directly, which equipped at edge wireless networks. Through offloading, performances such as execution delay well energy consumption effectively improved, significantly enhance quality user experience. Given dynamics and randomness computation arrival, in battery, radio network environment, resource server, it is a challenge perform efficient...
Abstract The rapid development of the Internet Vehicles (IoV) along with emergence intelligent applications have put forward higher requirements for massive task offloading. Even though Mobile Edge Computing (MEC) can diminish network transmission delay and ease congestion, constrained heterogeneous resources a single edge server highly dynamic topology vehicular networks may compromise efficiency offloading, including latency energy consumption. Vehicular are also vulnerable to malicious...