Pavlos Kosmides

Utility-based RAT selection optimization in heterogeneous wireless networks

Abstract Recent technological advances in wireless networks will enable the realization of an integrated heterogeneous wireless environment consisting of multiple Radio Access Technologies (RATs) within a network provider. One of the most important benefits is that this will allow providers to balance their traffic among their subsystems without compromising on QoS issues. In this paper we focus on the Network Selection problem to allocate terminals to the most appropriate RATs by jointly examining both users’ and providers’ preferences. We introduce three utility-based optimization functions based on the type of application that users request. We then formulate the terminal assignment problem as an optimization problem, which is recognized as NP-hard. We examine both offline and online selection and develop an optimal Branch and Bound (BB) algorithm, a Greedy heuristic, as well as three Strip Packing variations. BB behaves efficiently in both offline and online environments reducing the search procedure, while the proposed heuristics produce results close to the values we get from BB but with very low computational cost.

SOCIETIES: where pervasive meets social

Traditionally, pervasive systems are designed with a focus on the individual, offering services that take advantage of their physical environment and provide a context-aware, personalised user experience. On the other hand, social computing is centred around the notion of a community, leveraging the information about the users and their social relationships, connecting them together often using different criteria that can range from a users physical location and activity to personal interests and past experiences. The SOCIETIES Integrated Project attempts to bridge these different technologies in a unified platform allowing individuals to utilise pervasive services in a community sphere. SOCIETIES aims to use community driven context awareness, preference learning and privacy protection for intelligently connecting people, communities and things. Thus, the goal of SOCIETIES is to radically improve the utility of Future Internet services by combining the benefits of pervasive systems with these of social computing. This paper provides an overview of the vision, concepts, methodology, architecture and initial evaluation results towards the accomplishment of this goal.

Cross-community context management in Cooperating Smart Spaces

Recently, social networks have become the most prevalent IT paradigm, as the vast majority of Internet users maintain one or multiple social networking accounts. These accounts, irrespectively of the underlying service, contain rich information and data for the owner’s preferences, social skills, everyday activities, beliefs and interests. Along with these services, the computation, sensing and networking capabilities of the state of the art mobile and portable devices, with their always-on mode, assist users in their everyday lives. Thus, the integration of social networking services with current pervasive computing systems could provide the users with the potential to interact with other users that have similar interests, preferences and expectations; and in general, the same or similar context, for limited or not time periods, in order to ameliorate their overall experience, communicate, socialise and improve their everyday activities with minimal effort. This paper introduces a cross-community context management framework that is suitable for Cooperating Smart Spaces, which couple the advantages of pervasive computing and social networking. This framework goes beyond the state of the art, among others, in that cross-community context from a multitude of sources is collected and processed to enhance the end user experience and increase the perceived value of the services provided.

Providing recommendations on location-based social networks

During the last decade, in parallel with the rapid growth of mobile communications and devices, location-based social networks have met a tremendous growth with the acceptance of the public being constantly increasing. Users have access to a plethora of venues and points of interest, while they are able to share their visits to various locations along with comments and ratings about their experience (a process which is often referred to as “check-ins”). Location recommendations based on users’ needs have been a subject of interest for many researchers, while location prediction schemes have been developed in order to provide user’s possible future locations. In this paper, we present a novel method for predicting a user’s location based on machine learning techniques. In addition, following the incremental trend towards data accumulation in social networks, we introduce a clustering based prediction method in order to enhance the recommender system. For the prediction process we propose a probabilistic neural network and confirm its superior performance against two other types of neural networks, while for the clustering process we use a K-means clustering algorithm. The dataset we used was based on input from a well-known location-based social network. Prediction results can be used in order to make appropriate suggestions for venues or points of interests to users, based on their interests and social connections.

Enhancing Social Media with Pervasive Features

During the last decade, social media have enjoyed meteoric success in bringing people together online. On the other hand, pervasive computing assists users in their everyday tasks, in a seamless unobtrusive manner exploiting the resources available in the users environments focusing on the needs of individuals. The time is ripe for the two paradigms to converge. This paper presents research work undertaken to integrate pervasive computing with various social computing systems, including enterprise social media, aiming to contribute to the emergence of the next generation of social media systems.

Socially Aware Heterogeneous Wireless Networks

The development of smart cities has been the epicentre of many researchers’ efforts during the past decade. One of the key requirements for smart city networks is mobility and this is the reason stable, reliable and high-quality wireless communications are needed in order to connect people and devices. Most research efforts so far, have used different kinds of wireless and sensor networks, making interoperability rather difficult to accomplish in smart cities. One common solution proposed in the recent literature is the use of software defined networks (SDNs), in order to enhance interoperability among the various heterogeneous wireless networks. In addition, SDNs can take advantage of the data retrieved from available sensors and use them as part of the intelligent decision making process contacted during the resource allocation procedure. In this paper, we propose an architecture combining heterogeneous wireless networks with social networks using SDNs. Specifically, we exploit the information retrieved from location based social networks regarding users’ locations and we attempt to predict areas that will be crowded by using specially-designed machine learning techniques. By recognizing possible crowded areas, we can provide mobile operators with recommendations about areas requiring datacell activation or deactivation.

Context and Community Awareness in Support of User Intent Prediction

Proactive behaviour of pervasive computing systems cannot be realised without the establishment of suitable and reliable user intent prediction facilities. Most of the existing approaches focus on an individual end-user’s history of interactions and context in order to estimate future user behaviour. Recent trends in pervasive systems allow users to form communities with other individuals that share similar profiles, habits, and behaviours. Pervasive Communities set new challenges and opportunities regarding proactivity and context management. This chapter presents a context aware user intent learning and prediction framework that is able to exploit the knowledge available at the community level. Community knowledge, if appropriately managed, can significantly improve proactivity behaviour of individual users’ systems.

Addressing the Context-Awareness Requirements in Personal Smart Spaces

The provision of pervasive computing services is a challenging research area. This paper elaborates on the notion of Personal Smart Spaces (PSSs) that allows the delivery of pervasive services to mobile users. PSSs aim to couple the facilities offered by next generation mobile communications with the features provided by the static smart spaces to support a more ubiquitous, context-aware and personalised smart space that is able to follow the user wherever he/she goes. Moreover, PSSs provide interfaces between the user and the various services and sensors that are available via the Internet. One of the core PSS features is the management of static and dynamic context information of users. This paper elaborates on the context management approach that has been designed and implemented in order to address the advanced requirements of PSSs regarding context awareness.

Road to Next Generation Mobile Networks: An Evolutionary Dynamics Approach

One of the major challenges that mobile operators (MOs) are faced with nowadays is the transition to 4th Generation (4G) mobile communication technologies. The main reason for this lies on the reluctance of MOs to invest in a new technology without being sure about its success. The current paper investigates the decision-making procedures of a MO that wishes to migrate from its current technology type to 4G. Traditionally, the decision of deploying a new technology has been based on the analysis of similar implementations in other countries. However, such approaches can be inefficient and time consuming, as there are discrepancies concerning the technological progress among different countries. To this end, the authors employ evolutionary game theory to model the interactions of the MO’s decisions and the subscribers’ needs, and propose a practical and efficient qualitative model that identifies the circumstances under which the transition towards 4G networking can be facilitated. Specifically, the mathematical foundation of the decision making process is provided and the key role of the charging price and the quality of experience by the subscribers for using 4G connectivity is proven. With the process of 4G deployment still ongoing, this paper aims to present an analysis that can be used supplementary to the decision process of a MO that aims to evolve his network.

Artificial Neural Networks for Traffic Prediction in 4G Networks

The increasing proliferation of 4G mobile technologies is expected to satisfy the constantly growing demand for wireless broadband services. However, the high data rates provided by 4G networks at the air interface raise the need for more efficient management of the backhaul resources especially if the backhaul network has been leased by the mobile operator. In the present work, the authors investigate on the backhaul resource allocation problem at the side of the base station (BS) and a novel distributed scheme is proposed that can efficiently forecast the aggregated traffic demand at the BS using artificial neural networks. It is shown that the proposed scheme provides a mean absolute percentage error of about 10 % for the downlink traffic and about 19 % for the uplink traffic.