In this paper we focus on knowledge extraction from large-scale wireless networks through stream processing. We present the primary methods for sampling, data collection, and monitoring of wireless networks and we characterize knowledge extraction as a machine learning problem on big data stream processing. We show the main trends in big data stream processing frameworks. Additionally, we explore the data preprocessing, feature engineering, and the machine learning algorithms applied to the scenario of wireless network analytics. We address challenges and present research projects in wireless network monitoring and stream processing. Finally, future perspectives, such as deep learning and reinforcement learning in stream processing, are anticipated.

/pdf/a-survey-on-data-analysis-on-large-scale-wireless-networks-1u7mqx9u9t.pdf

A survey on data analysis on large-Scale wireless networks: online stream processing, trends, and challenges

Today’s communication is mainly done over wireless networks, with IEEE 802.11 (Wi-Fi) at the forefront. There are billions of devices and millions of access points (APs), but only very few non-overlapping channels. As a result, the performance of Wi-Fi devices is severely degraded, because perfect channel allocation - with every AP alone in its channel - is close to impossible. Even in situations where all networks are under centralised control, existing approaches quickly tend to be either unscalable or suboptimal. By focusing on a subset of problems, identifying Wireless Local Area Networks (WLANs) that severely interfere with each other, performance can be improved even in such a complex situation. We tackle this problem through machine learning and coin it Bad Neighbour Detection (BND). Based on this output alongside monitoring data about the networks’ activity, we then propose a channel allocation that optimises performance and as a side effect, stabilises networks that we do not control. We evaluate our approach in a field trial and show that we significantly improve the experience for users, eliminating virtually all interference-related issues.

A Machine Learning Approach for IEEE 802.11 Channel Allocation

Two evolutionary algorithms are proposed in this paper to handle with access point channel assignment in Wireless Local Area Network. The objective considered is to minimize the maximum level of interference experienced by the users. Two deterministic heuristics, commonly employed in the considered problem, are used as benchmark. The paper is focused on the IEEE 802.11ac standard, which operates exclusively in the 5 GHz band. This standard provides a bigger number of non-overlapped channels and higher throughput. Tests in three different scenarios and configurations, using channel width of 20, 40 and 80 MHz, are performed.

Using evolutionary algorithms for channel assignment in 802.11 networks

SCIFI is an open source software wireless controller. Large scale wireless networks that use low cost (SOHO) Access Points are hard to install and run due to the complexity of configuring and monitoring many APs with a distributed interface, coupled with the difficulty of creating a good network configuration with no help from the system. On the other hand, hardware controllers and their compatible APs are too expensive, proprietary and ultimately tie the buyer to a single vendor. SCIFI allows the use of inexpensive hardware to create large scale wireless installations. This paper describes the SCIFI algorithms, its interface, the current deployment at UFF and the future work planned for SCIFI.

SCIFI – A Software-Based Controller for Efficient Wireless Networks

IEEE 802.11 protocol uses random frequency channel assignment which can severely degrade the network throughput. This paper presents a novel efficient throughput oriented frequency channel assignment mechanism with low complexity for the infra-structured IEEE 802.11 based WiFi networks. The core idea of this assignment mechanism is to choose the frequency channel that is just good enough to maximize the number of served users per access point (AP) and leave the over-qualified frequency channels to other APs that may be in need for using them. Unlike other proposed works which aim to solve this IEEE 802.11 problem while ignoring some important network factors (e.g. out- of-system interference, the random AP deployment in reality, the APs not owned by one administrator, etc.), the proposed assignment mechanism takes these factors in consideration. The proposed mechanism performance is compared with the Random, the Greedy and the CACAO channel assignment mechanisms. The results show a remarkable throughput and fairness improvement of the proposed scheme while reserving the simplicity and realism.

Generous Throughput Oriented Channel Assignment for Infra-Structured WiFi Networks

The sharing of the wireless spectrum is a major concern of network administrators. Access points in the same network interfere with each other, degrading the aggregate performance of stations. Moreover, wireless networks usually coexist with others applications that share the same spectrum and negatively impact the packet transmission. To overcome these issues, we propose the channel allocation algorithm designed for central controllers of infra-structured IEEE 802.11 networks. Our algorithm reduces the interference in controlled access points through the dynamic choice of their operating channels and, unlike other proposals, was designed to operate in a network composed of low cost devices from different brands, and open source software. Furthermore, we also consider the interference caused by unmanaged networks, adjusting the settings of the managed access points according to the wireless environment. The proposal was implemented and evaluated in an open testbed, and the results show that our controller efficiently manages the spectrum with low cost equipment and a low complexity algorithm.

F. Souza

Papers

Centralized channel allocation algorithm for IEEE 802.11 networks