Henrik Petander

Measuring and Improving the Performance of Network Mobility Management in IPv6 Networks

Measuring the performance of an implementation of a set of protocols and analyzing the results is crucial to understanding the performance and limitations of the protocols in a real network environment. Based on this information, the protocols and their interactions can be improved to enhance the performance of the whole system. To this end, we have developed a network mobility testbed and implemented the network mobility (NEMO) basic support protocol and have identified problems in the architecture which affect the handoff and routing performance. To address the identified handoff performance issues, we have proposed the use of make-before-break handoffs with two network interfaces for NEMO. We have carried out a comparison study of handoffs with NEMO and have shown that the proposed scheme provides near-optimal performance. Further, we have extended a previously proposed route optimization (RO) scheme, OptiNets. We have compared the routing and header overheads using experiments and analysis and shown that the use of the extended OptiNets scheme reduces these overheads of NEMO to a level comparable with Mobile IPv6 RO. Finally, this paper shows that the proposed handoff and RO schemes enable NEMO protocol to be used in applications sensitive to delay and packet loss

Energy-aware network selection using traffic estimation

This paper proposes an energy-aware handoff algorithm based on energy consumption measurements of UMTS and 802.11 WLAN networks on an Android mobile phone. The handoff algorithm uses estimation of application traffic size to find the minimum energy cost alternative by comparing the cost of using UMTS with the cost of performing an opportunistic downward vertical handoff to a WLAN and using WLAN for the transfer and the eventual upward vertical handoff back to UMTS. Our experiments show that the energy cost of UMTS is nearly equal to WLAN as a function of transfer time, but for bulk transfers, transferring a byte of data over UMTS can be over a hundred times more expensive than over WLAN. Further, we discovered that the energy cost of the vertical handoff is quite high, comparable to downloading 0.12-0.67 MB of data over UMTS. To calculate the energy cost of data transfers before they take place, we propose and evaluate a distributed traffic estimation mechanism. The mechanism can predict how much data will be transferred due to a user action (i.e. clicking of an URL link). We provide initial results on the accuracy of the mechanism. Finally, we perform a numerical analysis on the the performance of the handoff algorithm and show that it can reduce the energy consumption significantly when compared with simple policies.

A comparison of the cost and energy efficiency of prefetching and streaming of mobile video

Mobile video streaming contributes a fast growing portion of mobile data traffic. This paper compares the cost and energy efficiency of streamed video with prefetching video using real usage data from a mobile video application that employs algorithmic prefetching. Empirical energy measurements are used to evaluate the power consumed when prefetching over Wi-Fi and streaming of content over cellular networks. The energy model and price data for communications costs are then used together with the usage data to evaluate the cost efficiency of prefetching. The results strongly indicate that algorithmic prefetching can provide sufficient performance improvements to significantly reduce both battery use and the costs of video delivery from user and operator points of view.

An experimental evaluation of a HIP based network mobility scheme

In this paper, the authors present and evaluate a network mobility scheme based on Host Identity Protocol (HIP). The cryptographic host identifiers are combined with an authorization mechanism and used for delegating the mobility management signalling rights between nodes in the architecture. While the delegation of the signalling rights scheme itself is a known concept, the trust model presented in this paper differs from the MIPv6 NEMO solution. In the presented approach, the mobile routers are authorized to send location updates directly to peer hosts on behalf of the mobile hosts without opening the solution for re-direction attacks. This is the first time the characteristics of the new scheme is measured in the HIP moving network context using a real implementation. The trust model makes it possible to support route optimization and minimize over-the-air signalling and renumbering events in the moving network. The measurements also reveal new kinds of anomalies in the protocol implementation and design when data integrity and confidentiality protection are integrated into signalling aggregation. The authors propose solutions for these anomalies.

MOBNET: the design and implementation of a network mobility testbed for NEMO protocol

The inherent difficulty in faithfully modeling wireless channel characteristics in simulators has prompted researchers to build wireless network testbeds for realistic testing of protocols. While previous testbeds are mostly designed to provide a research environment of static wireless networks, our work is aimed to assess protocols used for mobile wireless networks (such as an on-board network on public transport vehicles). In this work, we describe our on-going efforts in designing and implementing a network mobility testbed for network mobility (NEMO) protocol. This paper attempts to provide an initial reference to identify the feature set necessary for a network mobility testbed. We first describe the architecture of our testbed. Next, we present some preliminary results to demonstrate the use of our testbed in evaluating the performance of NEMO protocol under different scenarios

MobiTribe: Cost Efficient Distributed User Generated Content Sharing on Smartphones

Distributed social networking services show promise to solve data ownership and privacy problems associated with centralized approaches. Smartphones could be used for hosting and sharing users data in a distributed manner, if the associated high communication costs and battery usage issues of the distributed systems could be mitigated. We propose a novel mechanism for reducing these costs to a level comparable with centralized systems by using a connectivity aware replication strategy. We develop an algorithm for grouping devices into tribes for content replication among intended content consumers and serve it using low-cost network connections. We evaluate the performance of the algorithm using three real world trace data sets. The results show that a persistent low-cost network availability can be achieved with an average of two replicas per content. Additionally, cellular bandwidth consumption and energy consumption of users are evaluated analytically using user content creation and consumption modeling. The results show that the proposed mechanism lowers monetary and energy costs for users compared to non-mobile-optimized distributed systems irrespective of the content demand model.

Predictive context aware mobility handling

The handling of device multi-homing and mobility, such as deciding which network interface to use or when to perform vertical handoff between network interfaces, can be greatly enhanced by considering recent context information. We describe a system for context aware multi-homing and mobility handling which enacts network interface allocation and handoff decisions based on the predicted characteristics of transport layer sockets and network interfaces. Predictions are made using a statistical machine learning technique which can utilise simple context data such as time-of-day and GPS co-ordinates, as well as more complex contextual information such as nearby Bluetooth beacons and internal system state. We present a prototype implementation of the described system and show via experimentation that it enables more timely mobility handling without requiring changes to either applications or to the underlying operating system.

Performance of content replication in MobiTribe: A distributed architecture for mobile UGC sharing

An increasing portion of traffic in mobile networks comes from users creating content and uploading it to the Internet to share it. The capacity of mobile networks is a limited resource and uploading high resolution content consumes a large part of it. We introduce MobiTribe, a distributed storage cloud consisting of mobile devices for storing the content created on the phones. It can serve requests for content and take advantage of networks with spare capacity to deliver the content at a lower cost. We propose a content distribution and replication algorithm which achieves this goal. The performance of the algorithm is evaluated using empirical data traces of WLAN availability patterns of mobile devices, showing that it is possible to achieve 99.98% availability of a content via WLAN while minimising content distribution to an average of 2.69 replicas.

Enabling mobile distributed social networking on smartphones

Distributed social networking services show promise to solve data ownership and privacy problems associated with centralised approaches. Smartphones could be used for hosting and sharing users data in a distributed manner, if the associated high communication costs and battery usage issues of the distributed systems could be mitigated. We propose a novel mechanism for reducing these costs to a level comparable with centralised systems by using a connectivity aware replication strategy. To this end, we develop an algorithm based on a combination of bipartite b-matching and a greedy heuristics for grouping devices into tribes among intended content consumers. The tribes replicate content and serve it using low-cost network connections by exploiting time elasticity of user generated content sharing. The performance is evaluated using three real world trace data sets. The results show that a persistent low-cost network availability can be achieved with an average of two replicas per content. Additionally, a content creator can reduce 3G traffic by up to 43% and device energy use by up to 41% on average compared to content sharing in non-mobile-optimised distributed social networking approaches. Moreover, the results show that the proposed mechanism can provide the benefits of a distributed content sharing system for monetary and energy costs comparable to those of a centralised server based system.

EMUNE: Architecture for Mobile Data Transfer Scheduling with Network Availability Predictions

With the mobile communication market increasingly moving towards value-added services, the network cost will need to be included in the service offering itself. This will lead service providers to optimize network usage based on real cost rather than simplified network plans sold to consumers traditionally. Meanwhile, today’s mobile devices are increasingly containing multiple radios, enabling users on the move to take advantage of the heterogeneous wireless network environment. In addition, we observe that many bandwidth intensive services such as video on demand and software updates are essentially non real-time and buffers in mobile devices are effectively unlimited. We therefore propose EMUNE, a new transfer service which leverages these aspects. It supports opportunistic bulk transfers in high bandwidth networks while adapting to device power concerns, application requirements and user preferences of cost and quality. Our proposed architecture consists of an API, a transport service and two main functional units. The well defined API hides all internal complexities from a programmer and provides easy access to the functionalities. The prediction engine infers future network and bandwidth availability. The scheduling engine takes the output of the prediction engine as well as the power and monetary costs, application requirements and user preferences into account and determines which interface to use, when and for how long for all outstanding data transfer requests. The transport service accordingly executes the inferred data transfer schedule. The results from the implementation of EMUNE’s and of the prediction and scheduling engines evaluated against real user data show the effectiveness of the proposed architecture for better utilization of multiple network interfaces in mobile devices.