NES &amp;#x2014; Network Expert System for heterogeneous networks

Horsmanheimo, Seppo; Eskelinen, Jari J.; Kokkoniemi‐Tarkkanen, Heli

doi:10.1109/ictel.2010.5478789

Cited by 10 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The NES and its prototype were originally presented by Horsmanheimo et al [99]. The operation principle of the NES is similar to the simpler NIS implementation presented earlier, that is, it collects network context information for its decision-making from the network resource probes, deployed in the ANs, and generates triggers based on the information that may initiate various network management actions.…”

Section: Overview Of the Proposed Solutionmentioning

confidence: 99%

“…The probe data used included current available bandwidth, radio interface quality, and packet loss measurements. The accuracy of the training was evaluated experimentally by running the training multiple times and selecting the trained SOM with the smallest quantization error and topology preservation error for use as suggested by Horsmanheimo et al [99]. The remainder of this section provides a brief overview of the experimental evaluation on the prototype and the results obtained.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…With SOM, human experts have a role in guiding the decisions of the NIS, but only in terms of selecting suitable training data to be used and defining the rules for the trigger generation. The training is done off-line, and the process is described by Horsmanheimo et al [99].…”

Section: Overview Of the Proposed Solutionmentioning

confidence: 99%

“…-Network information server (NIS) runs various services, such as Network Expert Systems (NES) [99], to process network-side context information prior to its transmission to MNs or network management tools. Located in the wired network, the NIS shares the same analogy with the standard information services, such as the IEEE 802.21 remote MIHF communication and MIIS as well as the 3GPP ANDSF without the restriction to handover management-related information.…”

Section: Cross-layer Architecture For Video Streamingmentioning

confidence: 99%

See 3 more Smart Citations

Cross-layer optimized video streaming in heterogeneous wireless networks

Ojanperä¹

2013

SIGMultimedia Rec.

View full text Add to dashboard Cite

This dissertation studies the impact of heterogeneous wireless networks on the design and implementation of mobile video streaming services. The aim is to enable Quality of Service (QoS) sensitive video streaming services to take full advantage of the access diversity of heterogeneous networks in order to optimize their operation in terms of quality and efficiency of network resource usage. This nevertheless requires support beyond the layered communication architecture of today's Internet.The thesis proposes an architecture for end-to-end cross-layer signaling and control for video streaming systems. The architecture supports extensive context information transfer in heterogeneous networks; thus, enabling the efficient management of video stream adaptation and user terminal mobility in a diverse and dynamic network environment. This thesis also studies and proposes cross-layer enhancements for adaptive video streaming and mobility management functions enabled by the cross-layer architecture. These include cross-layer video adaptation, congestion-triggered handovers, and concurrent utilization of multiple access networks in the video stream transport. For the video adaptation and multipath transmission, the flexible adaptation and transmission capabilities of the novel scalable video coding technology are used. Regarding the mobility management, the proposed solutions essentially enhance the handover decision-making of the Mobile IP protocol to better support QoS-sensitive video streaming. Finally, the thesis takes a holistic view on the application adaptation and mobility management, and proposes a solution for coordinated control of these two operations in order to achieve end-toend optimization.The resulting mobile video streaming system architecture and the cross-layer control algorithms are evaluated using network simulations and real prototypes. Based on the results, the proposed mechanisms can be seen to be viable solutions for improving video streaming performance in heterogeneous wireless networks. They require changes in the communication end-points and the access network but support gradual deployment. This allows service providers and operators to select only a subset of the proposed mechanisms for implementation. The results also support the need for cross-layer signaling and control in facilitating efficient management and utilization of heterogeneous wireless networks.

show abstract

Section: Overview Of the Proposed Solutionmentioning

confidence: 99%

Section: Experimental Evaluationmentioning

confidence: 99%

Section: Overview Of the Proposed Solutionmentioning

confidence: 99%

Section: Cross-layer Architecture For Video Streamingmentioning

confidence: 99%

See 2 more Smart Citations

Cross-layer optimized video streaming in heterogeneous wireless networks

Ojanperä¹

2013

SIGMultimedia Rec.

View full text Add to dashboard Cite

show abstract

“…QoSMeT [7]) and network probes (e.g. [8]), are able to collect a vast amount of performance data from coexisting networks for the decision makers.…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Management Architecture for Multi-Access Networks

Kliazovich

Sutinen

Kokkoniemi‐Tarkkanen

et al. 2011

2011 IEEE Global Telecommunications Conference - GLOBECOM 2011

View full text Add to dashboard Cite

Abstract-Future Internet will be highly heterogeneous supporting a multitude of access technologies with overlapping coverages. The automation and optimization of network operations like resource, mobility or QoS management in such a multi-access and multi-operator environment becomes a very challenging but vital task in order to ensure smooth network operation and user satisfaction. Cognitive network management is seen as the solution for this. However, any self* mechanism designed for small-scale networks and requiring an accurate view of the whole network status for decision-making will not be able to meet the future needs. In this paper, we propose a novel multi-access network management architecture targeted for large heterogeneous multi-access and multi-operator networks. The architecture introduces hierarchy to network management to ensure scalability. We also present results obtained from a case example of the proposed decision-making solution implemented to our cognitive network testbed.

show abstract