Sasu Tarkoma

Theory and Practice of Bloom Filters for Distributed Systems

Many network solutions and overlay networks utilize probabilistic techniques to reduce information processing and networking costs. This survey article presents a number of frequently used and useful probabilistic techniques. Bloom filters and their variants are of prime importance, and they are heavily used in various distributed systems. This has been reflected in recent research and many new algorithms have been proposed for distributed systems that are either directly or indirectly based on Bloom filters. In this survey, we give an overview of the basic and advanced techniques, reviewing over 20 variants and discussing their application in distributed systems, in particular for caching, peer-to-peer systems, routing and forwarding, and measurement data summarization.

Accelerometer-based transportation mode detection on smartphones

We present novel accelerometer-based techniques for accurate and fine-grained detection of transportation modes on smartphones. The primary contributions of our work are an improved algorithm for estimating the gravity component of accelerometer measurements, a novel set of accelerometer features that are able to capture key characteristics of vehicular movement patterns, and a hierarchical decomposition of the detection task. We evaluate our approach using over 150 hours of transportation data, which has been collected from 4 different countries and 16 individuals. Results of the evaluation demonstrate that our approach is able to improve transportation mode detection by over 20% compared to current accelerometer-based systems, while at the same time improving generalization and robustness of the detection. The main performance improvements are obtained for motorised transportation modalities, which currently represent the main challenge for smartphone-based transportation mode detection.

A gap analysis of Internet-of-Things platforms

We are experiencing an abundance of Internet-of-Things (IoT) middleware solutions that provide connectivity for sensors and actuators to the Internet. To gain a widespread adoption, these middleware solutions, referred to as platforms, have to meet the expectations of different players in the IoT ecosystem, including device providers, application developers, and end-users, among others.In this article, we evaluate a representative sample of these platforms, both proprietary and open-source, on the basis of their ability to meet the expectations of different IoT users. The evaluation is thus more focused on how ready and usable these platforms are for IoT ecosystem players, rather than on the peculiarities of the underlying technological layers. The evaluation is carried out as a gap analysis of the current IoT landscape with respect to (i) the support for heterogeneous sensing and actuating technologies, (ii) the data ownership and its implications for security and privacy, (iii) data processing and data sharing capabilities, (iv) the support offered to application developers, (v) the completeness of an IoT ecosystem, and (vi) the availability of dedicated IoT marketplaces. The gap analysis aims to highlight the deficiencies of todays solutions to improve their integration to tomorrows ecosystems. In order to strengthen the finding of our analysis, we conducted a survey among the partners of the Finnish IoT program, counting over 350 experts, to evaluate the most critical issues for the development of future IoT platforms. Based on the results of our analysis and our survey, we conclude this article with a list of recommendations for extending these IoT platforms in order to fill in the gaps.

Carat: collaborative energy diagnosis for mobile devices

We aim to detect and diagnose energy anomalies, abnormally heavy battery use. This paper describes a collaborative black-box method, and an implementation called Carat, for diagnosing anomalies on mobile devices. A client app sends intermittent, coarse-grained measurements to a server, which correlates higher expected energy use with client properties like the running apps, device model, and operating system. The analysis quantifies the error and confidence associated with a diagnosis, suggests actions the user could take to improve battery life, and projects the amount of improvement. During a deployment to a community of more than 500,000 devices, Carat diagnosed thousands of energy anomalies in the wild. Carat detected all synthetically injected anomalies, produced no known instances of false positives, projected the battery impact of anomalies with 95% accuracy, and, on average, increased a users battery life by 11% after 10 days (compared with 1.9% for the control group).

Enabling energy-aware collaborative mobile data offloading for smartphones

Searching for mobile data offloading solutions has been topical in recent years. In this paper, we present a collaborative WiFi-based mobile data offloading architecture - Metropolitan Advanced Delivery Network (MADNet), targeting at improving the energy efficiency for smartphones. According to our measurements,WiFi-based mobile data offloading for moving smartphones is challenging due to the limitation ofWiFi antennas deployed on existing smartphones and the short contact duration with WiFi APs. Moreover, our study shows that the number of open-accessible WiFi APs is very limited for smartphones in metropolitan areas, which significantly affects the offloading opportunities for previous schemes that use only open APs. To address these problems, MADNet intelligently aggregates the collaborative power of cellular operators, WiFi service providers and end-users. We design an energy-aware algorithm for energy-constrained devices to assist the offloading decision. Our design enables smartphones to select the most energy efficient WiFi AP for offloading. The experimental evaluation of our prototype on smartphone (Nokia N900) demonstrates that we are able to achieve more than 80% energy saving. Our measurement results also show that MADNet can tolerate minor errors in localization, mobility prediction, and offloading capacity estimation.

Mobile code offloading: from concept to practice and beyond

The emerging mobile cloud has expanded the horizon of application development and deployment with techniques such as code offloading. While offloading has been widely considered for saving energy and increasing responsiveness of mobile devices, the technique still faces many challenges pertaining to practical usage. In this article, we adopt a systemic approach for analyzing the components of a generic code offloading architecture. Based on theoretical and experimental analysis, we identify the key limitations for code offloading in practice and then propose solutions to mitigate these limitations. We develop a generic architecture to evaluate the proposed solutions. The results provide insights regarding the evolution and deployment of code offloading.

Mobile search and the cloud: The benefits of offloading

This paper presents the benefits and drawbacks of mobile desktop search coupled with cloud-assisted operations, such as operation offloading, cloud storage, and cloud-assisted search. The energy trade-off when offloading a task is analyzed and measured in several different scenarios. An example case of offloading indexing is presented. The problem of cloud-assisted mobile desktop search is introduced and a possible solution outlined. This paper argues that the synergy between mobile platforms and cloud computing is under-utilized and should be explored further, particularly in the search and synchronization use case. Our measurements support offloading (parts of) search related tasks to a cloud service.

Overlay Networks: Toward Information Networking.

A recent Cisco traffic forecast indicates that annual global IP traffic will reach two-thirds of a zettabyte by 2013. With their ability to solve problems in massive information distribution and processing, while keeping scaling costs low, overlay systems represent a rapidly growing area of R&D with important implications for the evolution of Internet architecture. Inspired by the authors articles on content based routing, Overlay Networks: Toward Information Networking provides a complete introduction to overlay networks. Examining what they are and what kind of structures they require, the text covers the key structures, protocols, and algorithms used in overlay networks. It reviews the current state of the art in applications, decentralized overlays, security, information routing, and information forwarding. The book provides readers with an overview of networking technologies, the TCP/IP protocol suite, and networking basics. It also examines: The foundations of structured overlays Unstructured P2P overlay networks Graph-based algorithms for information dissemination and probabilistic algorithms Content-centric routing and a number of protocols and algorithms Security challenges of P2P and overlay technologiesproviding solutions for these mitigating risks Written by a scientist who is a university professor and a senior member of the Nokia research staff, this forward-looking reference covers advanced issues concerning performance and scalability. It highlights recent developments and discusses specific algorithms, including BitTorrent, Coolstream, BitOs, Chord, Content Addressable Network, Content Delivery Networks, Overlay multicast, and Peer-to-Peer SIP. Complete with a number of frequently-used probabilistic techniques and projections for future trends, this authoritative resource provides the tools and understanding needed to create deployable solutions for processing and distributing the vast amounts of data that modern networksdemand.

Incentive-compatible caching and peering in data-oriented networks

Several new, data-oriented internetworking architectures have been proposed recently. However, the practical deployability of such designs is an open question. In this paper, we consider data-oriented network designs in the light of the policy and incentive structures of the present internetworking economy. A main observation of our work is that none of the present proposals is both policy-compliant and incentive-compatible with the current internetworking market, which makes their deployment very challenging if not impossible. This difficulty stems from the unfounded implicit assumption that data-oriented routing policies directly reflect the underlying packet-level inter-domain policies. We find that to enable the more effective network utilization promised by data-oriented networking, essential caching incentives need to exist, and that data-oriented peering needs be considered separately from peering for packet forwarding.

Supporting software agents on small devices

Current small devices, such as Personal Digital Assistants (PDAs), are powerful enough to enable the use of Java applications and middleware. In this paper, we present the Java based MicroFIPA-OS, which is an agent platform for enabling software agents on small devices. We give an overview of the system, the target environment and examine the performance on two current PDAs.