Upendra Rathnayake

Predicting network availability using user context

Most mobile devices nowadays can simultaneously connect to different access networks with different characteristics at different times. Most solutions proposed for such an environment are reactive in nature. For example, when networks are encountered, the device performs a vertical handover to the network that offers the highest bandwidth. But the cost of handover may not be justified if that network is only available for a short time. Knowledge of future network availability and its capabilities would help to proactively handle the handover process more intelligently. Network availability prediction is often addressed as user path predictions with network coverage maps. In contrast, we model it as a more robust context prediction problem that can use any of the available context variables like GSM cell ID, WLAN AP, whether the power cable plugged, number of people around etc. Specifically, we propose a Semi-Markovian context prediction model to predict WLAN availability. As collecting and processing context consumes power, we propose a method to rank each context variable according to their contributions to prediction accuracy. We also employ the same method for optimizing model parameters. Real user data collected in our experiments show that when WLAN status is static, prediction errors are nearly zero and even in changing environments, error is less than 26% on average and the obtained context variable ranking is realistic.

A DBN approach for network availability prediction

Modern mobile devices are increasingly capable of simultaneously connecting to multiple access networks with different characteristics. Restricted coverage combined with user mobility will vary the availability of networks for a mobile device. Most proposed solutions for such an environment are reactive in nature, such as performing a vertical handover to the network that offers the highest bandwidth. But the cost of the handover may not be justified if that network is only available for a short time. Knowledge of future network availability and their capabilities are the basis for proactive schemes which will improve network selection and utilization. We have previously proposed a prediction model that can use any available context such as GSM Location Area, WLAN presence or even whether the power cable is plugged in, to predict network availability. As it may not be possible to sense all of the context variables that influence future network availability, in this paper we introduce a generic, new model incorporating a hidden variable to account for this. Specifically, we propose a Dynamic Bayesian Network based context prediction model to predict network availability. When the predictions were performed for WLAN availability with the real user data collected in our experiments, this model shows 20% or more improvement than both of our earlier proposals of order 1 and 2 Semi-Markov models.

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.

Environmental context aware trust in mobile P2P networks

With the growing popularity and capabilities of mobile devices, peer-to-peer networking among such devices is increasingly of interest for mobile content sharing. One of the major challenges in practical use of Mobile Peer-to-Peer networks (MP2P) is the trust among peers. Traditionally, solutions in the state of the art have focused on a peers past experience in evaluating trust of other peers, based on direct interactions. Previously unknown peers (with no history of direct interactions) are assessed based on third party recommendations, yet again requiring a peer to evaluate and find trustworthy recommenders. This reveals the fundamental need to find peers with honest intentions before any interaction. It becomes challenging when no known peers are in the vicinity, which is highly likely in an MP2P scenario. For a general mobile user, the probability of encountering trustworthy peers in particular situations or environmental contexts may be higher than in other contexts, e.g. in office than on the road while traveling. Further, observed peers which are co-located over a number of environmental contexts may have more in common and thus resulting a higher mutual trust. These facts can be utilized to enrich the trust derivation process in a decentralized manner. In this paper, we propose a generalized and a novel distributed mechanism to estimate the trust for peers using their encounter history in different environmental contexts, and a way to prioritize contexts depending on the level of association with them. When evaluated against real user data of the reality mining dataset, the results of the proposed mechanism show a significantly improved accuracy of trust evaluation compared to the state of the art.

Network availability prediction with hidden context

Modern mobile devices are increasingly capable of simultaneously connecting to multiple access networks with different characteristics. Restricted coverage combined with user mobility will vary the availability of networks for a mobile device. Most proposed solutions for such an environment are reactive in nature, such as performing a vertical handover to the network that offers the highest bandwidth. But the cost of the handover may not be justified if that network is only available for a short time. Knowledge of future network availability and their capabilities are the basis for proactive schemes which will improve network selection and utilization. We have previously proposed a prediction model that can use any available context such as GSM Location Area, WLAN presence or even whether the power cable is plugged in, to predict network availability. As it may not be possible to sense all of the context variables that influence future network availability, in this paper we introduce a generic, new model incorporating a hidden variable to account for this. Specifically, we propose a Dynamic Bayesian Network based context prediction model to predict network availability. Predictions performed for WLAN availability with the real user data collected in our experiments show 20% or more improvement compared to both of our earlier proposals of order 1 and 2 semi-Markov models.

Network availability prediction: Can it be done?

With the availability of more powerful mobile devices and a variety of access networks, users are expecting more and more services whilst on the move. There have been many attempts develop methods of providing these types of services form a user as well as a service provider perspective. All of these methods are based on the ability to predict the future. In this paper, will first present an overview of the research on one aspect of this, namely network availability prediction. We first, summarise the work that has been done in network availability prediction and categorize them. Using the categorisation, we show that one of the existing mechanisms provide the necessary accuracy and robustness. Then we present a hybrid design which overcome the limitations of the current systems. We show the viability of the the proposed hybrid system by summarising a dynamic baysean network and report exchange based predication mechanisms. We conclude the paper with a brief discussion on the open issues of developing such a hybrid scheme.

Protocol support for bulk transfer architecture

Todays 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 podcasts, software updates etc are essentially non-real-time and buffers in mobile devices are effectively unlimited. We therefore proposed EMUNE, a new transfer service architecture in our previous work which leverages these aspects and supports opportunistic bulk transfers in high bandwidth networks. EMUNE uses multiple wireless network interfaces according to an optimal transfer schedule derived based on device power concerns, application requirements, user preferences of cost and quality and future network availability. In this paper, we explore the usability of network/transport protocols to achieve the use of multiple network interfaces with required functionalities including flow mobility and striping in mobile environments and propose a MONAMI [1] + R2CP [3] hybrid approach for the architecture.