Data-Driven Design of Intelligent Wireless Networks: An Overview and Tutorial

Abstract

Data science or “data-driven research” is a research approach that uses real-life data to gain insight about the behavior of systems. It enables the analysis of small, simple as well as large and more complex systems in order to assess whether they function according to the intended design and as seen in simulation. Data science approaches have been successfully applied to analyze networked interactions in several research areas such as large-scale social networks, advanced business and healthcare processes. Wireless networks can exhibit unpredictable interactions between algorithms from multiple protocol layers, interactions between multiple devices, and hardware specific influences. These interactions can lead to a difference between real-world functioning and design time functioning. Data science methods can help to detect the actual behavior and possibly help to correct it. Data science is increasingly used in wireless research. To support data-driven research in wireless networks, this paper illustrates the step-by-step methodology that has to be applied to extract knowledge from raw data traces. To this end, the paper (i) clarifies when, why and how to use data science in wireless network research; (ii) provides a generic framework for applying data science in wireless networks; (iii) gives an overview of existing research papers that utilized data science approaches in wireless networks; (iv) illustrates the overall knowledge discovery process through an extensive example in which device types are identified based on their traffic patterns; (v) provides the reader the necessary datasets and scripts to go through the tutorial steps themselves.

A decision tree‐based NLOS detection method for the UWB indoor location tracking accuracy improvement

“…We then evaluated the performance of the pruned model using the testing data from the seven different indoor environments. Using several standard metrics in the confusion matrix, with the actual class is NLOS = 1, the result assignments fall into four categories are as follow. True positive ( TP ): instances that are classified as the actual class True negative ( TN ): instances that are correctly classified as not being the actual class False positive ( FP ): instances that are misclassified as the actual class (type 1 error) False negative ( FN ): instances from the actual class that are misclassified as another class (type 2 error) …”

“…We then evaluated the performance of the pruned model using the testing data from the seven different indoor environments. Using several standard metrics in the confusion matrix, 31 with the actual class is NLOS = 1, the result assignments fall into four categories are as follow. The detail of the performance metrics is as follow.…”

Self-Organized Low-Power IoT Networks: A Distributed Learning Approach

“…The IoT devices aim at data transfer to the gateway on average each T rep seconds. Recalling the operation control problem in (1) the LoRa operation control consists in solving the following problem: 1) Distributed Learning for Operation Control: One can directly apply the presented Algorithms 1 and 2 in section III, in order to solve the optimization problem in (3). In this case, the set of actions, i.e.…”

“…User devices, mostly smart-phones with a daily charging routine, listen frequently (in the order of sub-seconds) to their serving base stations (BSs), which are responsible for managing the connections, sending connection instructions, and scheduling radio resources. As complexity, scale and heterogeneity of wireless networks, especially due to the IoT traffic, availability of statistical models for arriving traffic in the network-side and ability of energy-limited devices in frequent listening to the access network become infeasible [3]. The latter is mainly due to the fact that in IoT networks, the design objectives, quality of service (QoS) requirements, and communications' characteristics are fundamentally different than the ones of legacy communication networks [4].…”

“…For example, one may consider coexistence of LoRa and SigFox in an environment, where LoRa receiver treats SigFox signal as interference 2. The transmit code also determines the data rate[17] 3. In the NB-IoT and SigFox, several replicas are transmitted per data packet for range extension and resilience against interference, respectively[6] 4.…”