Network operators are interested in continuously monitoring the satisfaction of their customers to minimise the churn rate: however, collecting user feedbacks through surveys is a cumbersome task. In this work we explore the possibility of predicting the long-term user satisfaction relative to network coverage and video streaming starting from user-side network measurements only. We leverage country-wide datasets to engineer features which are then used to train several machine learning models. The obtained results suggest that, although some correlation is visible and could be exploited by the classifiers, long-term user satisfaction prediction from network measurements is a very challenging task: we therefore point out possible action points to be implemented to improve the prediction results.

No abstract

No abstract

Continuously monitoring the network activity to proactively recognise possible problems and prevent users QoE degradation is a major concern for network operators, for both mobile radio and home networks. Considering video streaming applications, which generate the majority of overall Internet traffic, monitoring the chunk requests from the video client to the video server is of particular interest, as they not only indicate that a download burst is imminent, but their type (e.g., request of an audio or video chunk) and frequency also allow to estimate which and how much data will be downloaded to the client. In this work, we propose a machine-learning based video streaming traffic monitoring architecture able to i) predict when next uplink request will be issued by the video client and ii) classify the type of next uplink request. We evaluate the system performance on a dataset of more than 900 HTTP adaptive streaming sessions and 15,000 request-response exchanges, where both the predictor of the next request arrival and the request type classifier are fed with lightweight features extracted from encrypted traffic in an online fashion, both in the uplink and downlink directions of the traffic. Results show that i) the system is able to classify the type of a HAS uplink requests with an accuracy greater than 95 % and ii) pipe-lining request type classification and prediction of next request arrival time improves the final prediction performance.

Smart meters networks are rapidly becoming a reality in many developed countries. In this paper, we focus on the optimization of a network of smart meters operated by the wM-Bus protocol, which is the de-facto metering standard in Europe. In such a scenario, data concentrators receive data from smart meters using the wM-Bus protocol and relay it to a central server using a legacy mobile cellular backhauling technology such as GSM/GPRS. Due to the massive amount of data produced by meters installed in urban scenarios and the association-less nature of the wM-Bus protocol, data concentrators may be overloaded with many duplicate measurement packets, causing capacity problems on the backhauling links and computational overload at the central server. To solve these issues, we propose a datadriven optimization framework to populate forwarding whitelists at each data concentrator so that (i) load is balanced among the different concentrators and (ii) the overall performance of the network in terms of packet reception rate and received signal strength are maximized. We also propose a heuristic algorithm to generate near optimal forwarding whitelists in acceptable computing time. Extensive experiments are performed on a real scenario consisting of a city wide gas meter network deployed in northern Italy. Results show that the proposed heuristic is able to produce whitelists that reduce the average backhauling traffic as much as 80%, with a corresponding network quality within 4% of the one computed by the optimal solution.