| 1. |
- Ahmad, Ijaz, et al.
(author)
-
Machine Learning Meets Communication Networks: Current Trends and Future Challenges
- 2020
-
In: IEEE Access. - : IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC. - 2169-3536. ; 8, s. 223418-223460
-
Journal article (peer-reviewed)abstract
- The growing network density and unprecedented increase in network traffic, caused by the massively expanding number of connected devices and online services, require intelligent network operations. Machine Learning (ML) has been applied in this regard in different types of networks and networking technologies to meet the requirements of future communicating devices and services. In this article, we provide a detailed account of current research on the application of ML in communication networks and shed light on future research challenges. Research on the application of ML in communication networks is described in: i) the three layers, i.e., physical, access, and network layers; and ii) novel computing and networking concepts such as Multi-access Edge Computing (MEC), Software Defined Networking (SDN), Network Functions Virtualization (NFV), and a brief overview of ML-based network security. Important future research challenges are identified and presented to help stir further research in key areas in this direction.
|
|
| 2. |
- Harjula, Erkki, et al.
(author)
-
Analysis of Peer-to-Peer SIP in a Distributed Mobile Middleware System
- 2006
-
In: 49th IEEE Global Telecommunications Conference.
-
Conference paper (peer-reviewed)abstract
- The seamless and flexible interconnection of the existing and emerging protocols and networks is essential to the success of the new generation mobile applications and services. For exploiting the functional diversity, we have developed a middleware for mobile devices called the Plug-and-Play Application Platform (PnPAP). We have previously studied the Session Initiation Protocol (SIP) as an interconnecting protocol for the PnPAP nodes. In this paper, we analyze the usage of a new variant of SIP called Peer-to-Peer SIP (P2P SIP) for this purpose. Our interconnection architecture utilizes layered (hierarchical) P2P SIP to establish a self-organizing, failure tolerant overlay signaling network between PnPAP nodes. Signaling latency and scalability of the layered P2P SIP signaling is compared in a simulation environment with both the traditional client-server SIP and fully distributed P2P SIP. Simulation results illustrate the benefits of the layered P2P SIP solution where only the supernodes participate to the DHT management, enabling light-weight peer node implementation for mobile nodes.
|
|
| 3. |
- Harjula, Erkki, et al.
(author)
-
Edge Computing for Industrial IoT : Challenges and Solutions
- 2021
-
In: Wireless Networks and Industrial IoT. - Cham : Springer. ; , s. 225-240
-
Book chapter (peer-reviewed)abstract
- The evolution from local toward virtualized data storage, computing, applications and services – in the forms of Internet of Things (IoT), Everything as a Service (EaaS), and Cloud computing – has changed the way of delivering digital services for consumers and businesses. These technologies have brought clear benefits over traditional systems, such as easy management, universal availability, and decreased hardware requirements for end-user devices. The main challenges of the first-generation IoT services are related to communication latency due to high physical and logical distance between end nodes and server resources and vulnerability for network problems along the long routes. Thanks to the unveiling of the fifth-generation wireless technology (5G) for cellular networks, the last-mile connection performance – communication latency in particular – is taking a huge leap and therefore introducing new possibilities for industrial applications. Edge computing is a key technology to unleash the full potential of the arising industrial wireless communication, since it enables deploying computational tasks to computing nodes near the end devices and therefore opens novel business opportunities around real-time cloud services. In this chapter, we introduce the current state of the art and discuss different challenges the edge computing systems are facing particularly in the Industrial IoT (IIoT) domain, as well as present potential solutions for the identified challenges.
|
|
| 4. |
- Harjula, Erkki, et al.
(author)
-
Energy-aware load monitoring for improving battery life of mobile peer-to-peer nodes
- 2016
-
In: SUSTAINABLE COMPUTING-INFORMATICS and SYSTEMS. - : ELSEVIER SCIENCE BV. - 2210-5379. ; 12, s. 43-54
-
Journal article (peer-reviewed)abstract
- In this article, we propose an energy -aware load monitoring model, called e-Mon, for enabling energy aware load balancing in Peer-to-Peer (P2P) systems. P2P is a scalable and self-organizing technology for utilizing computational resources of the end-user devices for the benefit of a computing system. In P2P systems, the need for fair balance of load is crucial since the end-users need to be incentivized to participate in the system. The short battery life, caused by additional strain on the computational resources of the end-user devices, is a significant negative incentive factor for mobile end-users of current P2P systems. The e-Mon model, proposed in this article, enables moving load from energy-critical to less energy-critical nodes in P2P systems. This is done by including the energy status of a peer node as one of the factors defining a nodes load. The model helps saving the energy of mobile P2P nodes, particularly in cases when the remaining battery capacity is low. The article provides a thorough energy efficiency evaluation demonstrating that e-Mon can significantly improve the battery life of mobile nodes by improving the quality and fairness of load balance between heterogeneous nodes. With a proper selection of a load balancing model for the application scenario, e-Mon is shown to achieve up to 470% battery life extension compared to the case with traditional load balancing with no battery monitoring. (C) 2016 Elsevier Inc. All rights reserved.
|
|
| 5. |
- Howie, Douglas, et al.
(author)
-
Harnessing SIP for Autonomous Mobile Peer-to-Peer Networking
- 2005
-
In: Proc. IEEE Global Communications Conference. - 0780394143 ; , s. 879-883
-
Conference paper (peer-reviewed)abstract
- There are several non-interoperable peer-to-peer (P2P) protocols available today with different functionalities. In order to exploit this functional diversity on mobile devices, we have developed a plug-and-play application platform (PnPAP). PnPAP provides autonomous, dynamic selection between multiple P2P protocols while ensuring the best available network connectivity. In this paper, we introduce methods for utilizing session initiation protocol (SIP) in inter-PnPAP communications. This communication may include downloads of distributed P2P resources such as polymorphic protocol libraries or dynamic state-machine control modules. These components are then used to optimize connectivity management between heterogeneous wireless access networks. In addition, context information may be exchanged between mobile nodes in order to facilitate extended service availability, operability and quality. We analyze the feasibility of merged P2P and All-IP (including SIP) architecture through the novel use of a specialized SIP server and the leveraging of the emerging instant messaging capabilities of SIP. Preliminary measurement results from the prototype implementation on a Symbian platform and test-bed, with overhead and latency analysis, illustrate the feasibility of this approach.
|
|
| 6. |
- Howie, Douglas, et al.
(author)
-
State-of-the-art SIP for mobile application supernetworking
- 2004
-
In: Proceedings of the Nordic Radio Symposium.
-
Conference paper (peer-reviewed)abstract
- This paper introduces the current state-of-the-art of SIP (Session Initiation Protocol) and the use of SIP in supporting P2P (peer-to-peer) applications on mobile phones. The use of SIP in All-IP mobile phones is a step toward achieving supernetworking, providing the user with powerful yet conceptually simple tools for sending and receiving multimedia content over a wireless network. The analysis includes an introduction of the application supernetworking concept in detail, with insight into the role of SIP in the current and future implementations.
|
|
