The Target Wake Time (TWT) feature introduced in 802.11ax can be employed to achieve higher power efficiency, reduced channel access contention, and lower network congestion by scheduling clients' transmissions. Despite these potential benefits, because TWT allows communication during service periods only, it can negatively impact the Transmission Control Protocol (TCP) performance. In this paper, we identify and discuss the impact of TWT on TCP performance for RTOS and Linux-based wireless devices and show that TWT leads to unnecessary retransmissions, which wastes channel bandwidth and increases communication delay and energy consumption. To address this problem, we propose and implement a method to share TWT operational parameters with the TCP layer to adjust its packet loss detection method. Empirical evaluations across different hardware platforms confirm the effectiveness of the proposed approach in preventing premature packet loss detection and reducing unnecessary retransmissions.

WiFi Access Points (APs) process and switch packets between the WiFi and Ethernet interfaces. These operations are managed by the Linux kernel's data plane; however, the kernelbased packet switching is inherently complex and challenging to monitor and modify. To address the growing demands for WiFi applications and services, and in particular to foster innovation in advancements of the data plane for WiFi APs, this work introduces AirXDP, a user-space packet switching architecture that leverages Linux's eXpress Data Path (XDP) framework. In this paper, we first present the AirXDP system architecture and the details of packet processing engine in the user-space. Next, we identify and address key limitations, such as the overhead caused by excessive polling of ingress queues as well as the increased RTTs resulting from standing queues. Through empirical and analytical evaluations, we demonstrate that techniques such as optimizing polling intervals, configuring core affinities, efficiently managing queues, and using XDP's native attach mode even on one interface enable AirXDP to achieve higher processing efficiency compared to packet switching performed by the Linux kernel. Overall, AirXDP provides an efficient packet switching framework for facilitating the enhancement of WiFi AP's data plane.

As the number of WiFi devices and their traffic demands continue to rise, the need for a scalable and high-performance wireless infrastructure becomes increasingly essential. Central to this infrastructure are WiFi Access Points (APs), which facilitate packet switching between Ethernet and WiFi interfaces. Despite APs’ reliance on the Linux kernel’s data plane for packet switching, the detailed operations and complexities of switching packets between Ethernet and WiFi interfaces have not been investigated in existing works. This paper makes the following contributions towards filling this research gap. Through macro and micro-analysis of empirical experiments, our study reveals insights in two distinct categories. Firstly, while the kernel’s statistics offer valuable insights into system operations, we identify and discuss potential pitfalls that can severely affect system analysis. For instance, we reveal how packet switching rate and the implementation of drivers influence the meaning and accuracy of statistics related to packet-switching tasks and processor utilization. Secondly, we analyze the impact of the packet switching path and core configuration on performance and power consumption. Specifically, we identify the differences in Ethernet-to-WiFi and WiFi-to-Ethernet data paths regarding processing components, multi-core utilization, and energy efficiency.

Identifying IoT devices is crucial for network monitoring, security enforcement, and inventory tracking. However, most existing identification methods rely on deep packet inspection, which raises privacy concerns and adds computational complexity. Moreover, existing works overlook the impact of wireless channel dynamics on the accuracy of layer-2 features, thereby limiting their effectiveness in real-world scenarios. In this work, we define and use the latency of specific probe-response packet exchanges, referred to as "device latency," as the main feature for device identification. Additionally, we reveal the critical impact of wireless channel dynamics on the accuracy of device identification based on device latency features. Specifically, this work introduces "accumulation score" as a novel approach to capturing fine-grained channel dynamics and their impact on device latency when training machine learning models. We implement the proposed methods and measure the accuracy and overhead of device identification in real-world scenarios. The results confirm that by incorporating the accumulation score for balanced data collection and training machine learning algorithms, we achieve an F1 score of over 97% for device identification, even amidst wireless channel dynamics, a significant improvement over the 75% F1 score achieved by disregarding the impact of channel dynamics on data collection and device latency.

To reduce packet collisions and enhance the energy efficiency of stations, Target Wake Time (TWT), which is a feature of the 802.11ax standard (WiFi 6), allows the allocation of communication service periods to stations. While effective TWT allocation requires characterizing the traffic pattern of stations, in this paper, we empirically study and reveal that the existing methods (i.e., channel utilization estimation, packet sniffing, and buffer status report) do not provide adequate accuracy. To remedy this problem, we propose a traffic characterization method that can accurately capture inter-packet and inter-burst intervals on a per-flow basis in the presence of factors such as channel access and packet preparation delay. We empirically evaluate the proposed method and confirm its superior traffic characterization performance against the existing ones. We also present a sample TWT allocation scenario that leverages the proposed method to enhance throughput.

We are witnessing an emergence of a new era of applications delivered via a paradigm of flexible and softwarized communication networks. This has opened the market to a wider movement towards virtualized applications and services in key verticals such as automated vehicles, smart grid, virtual reality (VR), Internet of Things (IoT), industry 4.0, telecommunications, etc. With an increasing emergence of verticals driven by the vision of low latency and high reliability, there is a wide gap to efficiently bridge the Quality of Service (QoS) constraints for the end-user experience. Most latency-critical services are over-provisioned on all fronts to offer reliability, which is inefficient in the long run. In this work, we present a Residual Long Short-Term Memory (LSTM) based multi-label classification framework for proactive SLA management in a latency-critical Network Function Virtualization (NFV) application use case. We compose a multivariate time-series forecasting model with multiple time-step predictions in a multi-output scenario, and associate a multi-label classifier for a granular prediction of individual Service Level Objective (SLO) violations for each step in the forecast horizon. The Residual LSTM approach achieves an improvement of 31.1% over the baseline on the forecast classification accuracy, and a 2.65% improvement on the interpolated average precision over the standard LSTM methodology.

Wireless sensor networks (WSNs) are being used in various applications, such as structural health monitoring and industrial control. Since energy efficiency is one of the major design factors, the existing WSNs primarily rely on low-power,low-ratewireless technologies, such as 802.15.4 and Bluetooth. In this article, by proposing Sensifi, we strive to tackle the challenges of developingultrahigh-rateWSNs based on the 802.11 (WiFi) standard. As an illustrative structural health monitoring application, we consider the spacecraft vibration test and identify system design requirements and challenges. Our main contributions are as follows. First, we propose packet encoding methods to reduce the overhead of assigning accurate timestamps to samples. Second, we propose energy-efficiency methods to enhance the system’s lifetime. Third, to enhance sampling rate and mitigate sampling rate instability, we reduce the overhead of processing outgoing packets through the network stack. Fourth, we study and reduce the delay of processing time synchronization packets through the network stack. Fifth, we propose a low-power node design, particularly targeting vibration monitoring. Sixth, we use our node design to empirically evaluate energy efficiency, sampling rate, and data rate. We leave large-scale evaluations as future work.

IoT devices have become popular targets for various network attacks due to their lack of industry-wide security standards. In this work, we focus on the classification of smart home IoT devices and defending them against Distributed Denial of Service (DDoS) attacks. The proposed framework protects smart homes by using VLAN-based network isolation. This architecture includes two VLANs: one with non-verified devices and the other with verified devices, both of which are managed by a SDN controller. Lightweight, stateless flow-based features, including ICMP, TCP and UDP protocol percentage, packet count and size, and IP diversity ratio, are proposed for efficient feature collection. Further analysis is performed to minimize training data to run on resource-constrained edge devices in smart home networks. Three popular machine learning models, including K-Nearest-Neighbors, Random Forest, and Support Vector Machines, are used to classify IoT devices and detect different DDoS attacks based on TCP-SYN, UDP, and ICMP. The system’s effectiveness and efficiency are evaluated by emulating a network consisting of an Open vSwitch, Faucet SDN controller, and flow traces of several IoT devices from two different testbeds. The proposed framework achieves an average accuracy of 97%in device classification and 98% in DDoS detection with average latency of 1.18 milliseconds.

Software switching, a.k.a virtual switching, plays a vital role in network virtualization and network function virtualization, enhances configurability, and reduces deployment and operational costs. Software switching also facilitates the development of edge and fog computing networks by allowing the use of commodity hardware for both data processing and packet switching. Despite these benefits, characterizing and ensuring deterministic performance with software switches is more complicated than physical switching appliances. In particular, achieving deterministic performance is essential to adopt software switching in mission-critical applications, especially those deployed in edge and fog computing architectures. In this paper, we study the impact of switch configurations on bandwidth slicing and predictable packet latency. We demonstrate that latency and predictability are dependent on the implementation of the bandwidth slicing mechanism. We also show that the packet schedulers used in OVS Kernel-Path and OVS-DPDK focus on different switching performance aspects.

With the rise of Internet of Things (IoT) devices, home network management and security are becoming complex. There is an urgent requirement to make smart home network management more efficient. This work proposes an SDN-based architecture to secure smart home networks through K-Nearest Neighbor (KNN) based device classifications and malicious traffic detection. The efficiency is enhanced by offloading the computation-intensive KNN model to a Field Programmable Gate Arrays (FPGA). Furthermore, we propose a custom KNN solution that exhibits the best performance on an FPGA compared with four alternative KNN instances (i.e., 78% faster than a parallel Bubble Sort-based implementation and 99% faster than three other sorting algorithms). Moreover, with 36,225 training samples, the proposed KNN solution classifies a test query with 95% accuracy in approximately 4 ms on an FPGA compared to 57 seconds on a CPU platform. This highlights the promise of FPGA-based platforms for edge computing applications in the smart home.

The southbound control protocols used in Software Defined Networks (SDNs) allow for centralized control and management of the data plane. However, these protocols introduce additional traffic and delay between network controllers and switches. Despite the well understood capabilities of SDNs, current representations of control traffic overhead consist of approximations at best. In addition to high reactivity to incoming flows, the need for resource allocation and deterministic messaging delay necessitates a thorough understanding and modeling of the amount of control traffic and its effect on latency. In this work, we capture the network overhead of various switch configurations on a testbed and extract mathematical models to predict expected overhead for arbitrary switch configurations. We demonstrate that controller-switch traffic patterns are non-negligible and can be accurately modelled to compute the bandwidth utilization and latency of controller-switch communication.

The 802.11 standard, known as WiFi, is currently being used for a wide variety of applications. The increasing number of WiFi devices, their stringent communication requirements, and the need for higher energy-efficiency mandate the adoption of novel methods that rely on monitoring the WiFi communication stack to analyze, enhance communication efficiency, and secure these networks. In this paper, we propose MonFi, a publicly-available, open-source tool for high-rate, efficient, and programmable monitoring of the WiFi communication stack. With this tool, regular user-space applications can specify their required measurement parameters, monitoring rate, and measurement collection method as event-based, polling-based, or a hybrid of both. We also propose methods to ensure deterministic sampling rate regardless of the processor load caused by other processes including packet switching. In terms of sampling rate and processing efficiency, we show that MonFi outperforms the Linux tools used to monitor the communication stack.

Internet of Things (IoT) has facilitated the prosperity of smart environments such as smart homes. Meanwhile, WiFi is a broadly used technology for the wireless connectivity of IoT devices. However, smart home IoT devices are often vulnerable to various security attacks. This article quantifies the impact of distributed denial of service (DDoS) and energy-oriented DDoS attacks (E-DDoS) on WiFi smart home devices and explores the underlying reasons from the perspective of attacker, victim device, and access point (AP). Compared to the existing work, which primarily focus on DDoS attacks launched by compromised IoT devices against servers, our work focuses on the connectivity and energy consumption of IoT devices when under attack. Our key findings are threefold. First, the minimum DDoS attack rate causing service disruptions varies significantly among different IoT smart home devices, and buffer overflow within the victim device is validated as critical. Second, the group key updating process of WiFi may facilitate DDoS attacks by causing faster victim disconnections. Third, a higher E-DDoS attack rate sent by the attacker may not necessarily lead to a victim's higher energy consumption. Our study reveals the communication protocols, attack rates, payload sizes, and victim devices' ports state as the vital factors to determine the energy consumption of victim devices. These findings facilitate a thorough understanding of IoT devices' potential vulnerabilities within a smart home environment and pave solid foundations for future studies on defense solutions.

The 802.11 standard, a.k.a., WiFi, is becoming more popular for IoT connectivity. The three essential operations performed to ensure connectivity in an 802.11 network are association, maintaining association, and periodic beacon reception. Understanding and enhancing the energy efficiency of these operations is essential for building IoT systems. Unfortunately, the overheads of these operations have not been studied considering station's software and hardware configuration, access point configuration, and link unreliability. In this paper, we show that: (i) association cost depends on multiple factors including probing, key generation, operating system, and network stack, (ii) increasing listen interval to reduce beacon reception wake-up instances may negatively impact energy efficiency, (iii) maintaining association by relying on the poll messages generated by the access point is not reliable, and (iv) key renewal aggravates the chance of disassociation. We also present station- and access point-based solutions that address some of these problems.

Wi-Fi and Bluetooth are two wireless technologies, available in every smart-phone, tablet, and laptop. Wi-Fi Access Points (APs) and Bluetooth beacons are deployed in most indoor environments to provide service for the Internet of Things (IoT) applications. Although, Bluetooth and Wi-Fi target different applications, they both share the 2.4 GHz frequency band. The re-transmissions caused by interference with Wi-Fi packets is costly for BLE in terms of energy consumption. Techniques such as Adaptive Frequency Hopping (AFH) in BLE addresses this problem. However, the static nature of AFH is not performing well for highly dynamic environments. Therefore, there is a need for a predictive model to optimize the spectrum usage. In this paper, we propose a machine learning model based on Long Short-Term Memory (LSTM) to predict the wireless activities in the 2.4 GHz frequency band and its impact on BLE channels. We apply the proposed model to analyze the Wi-Fi interference trend on these channels. The Root Mean Squared Error (RMSE) results for several experiments on both channels indicate the high performance of the proposed LSTM model over Auto Regressive Integrated Moving Average (ARIMA) model. This improvement is significant up to approximately 50% reduction in error.

With the rise of the Internet of Things (IoT), fog computing has emerged to help traditional cloud computing in meeting scalability demands. Fog computing makes it possible to fulfill real-time requirements of applications by bringing more processing, storage, and control power geographically closer to end devices. However, since fog computing is a relatively new field, there is no standard platform for research and development in a realistic environment, and this dramatically inhibits innovation and development of fog-based applications. In response to these challenges, we propose the Fog Development Kit (FDK). By providing high-level interfaces for allocating computing and networking resources, the FDK abstracts the complexities of fog computing from developers and enables the rapid development of fog systems. In addition to supporting application development on a physical deployment, the FDK supports the use of emulation tools (e.g., GNS3 and Mininet) to create realistic environments, allowing fog application prototypes to be built with zero additional costs and enabling seamless portability to a physical infrastructure. Using a physical testbed and various kinds of applications running on it, we verify the operation and study the performance of the FDK. Specifically, we demonstrate that resource allocations are appropriately enforced and guaranteed, even amidst extreme network congestion. We also present simulation-based scalability analysis of the FDK versus the number of switches, the number of end devices, and the number of fog devices.

With the proliferation of IoT, securing the abundance of devices is critical. The current IoT and security landscapes lack empirical evidence on algorithms optimized for constrained devices. In this paper, we study the performance of various symmetric encryption algorithms on a Contiki-based IoT device. This paper provides encryption and decryption durations and energy consumption results on three symmetric encryption algorithm implementations of AES (tinyAES, B-Con's AES, and Contiki's own built-in AES), where we found algorithms specifically built for constrained devices fared much better than those not, optimized algorithms using about 0.16 the energy and the time to perform encryption and decryption.

The Transport Layer Security (TLS) protocol has been considered as a promising approach to secure Internet of Things (IoT) applications. The different cipher suites offered by the TLS protocol play an essential role in determining communication security level. Each cipher suite encompasses a set of cryptographic algorithms, which can vary in terms of their resource consumption and significantly influence the lifetime of IoT devices. Based on these considerations, in this paper, we present a comprehensive study of the widely used cryptographic algorithms by annotating their source codes and running empirical measurements on two state-of-the-art, low-power wireless IoT platforms. Specifically, we present fine-grained resource consumption of the building blocks of the handshake and record layer algorithms and formulate tree structures that present various possible combinations of ciphers as well as individual functions. Depending on the parameters, a path is selected and traversed to calculate the corresponding resource impact. Our studies enable IoT developers to change cipher suite parameters and immediately observe the resource costs. Besides, these findings offer guidelines for choosing the most appropriate cipher suites for different application scenarios.

Increasing the number of Internet of Things (IoT) stations or regular stations escalates downlink channel access contention and queuing delay, which in turn result in higher energy consumption and longer communication delays with IoT stations. To remedy this problem, this paper presents WiFi IoT access point (Wiotap), an enhanced WiFi access point (AP) that implements a downlink packet scheduling mechanism. In addition to assigning higher priority to IoT traffic compared to regular traffic, the scheduling algorithm computes per-packet priorities to arbitrate the contention between the transmission of IoT packets. This algorithm employs a least-laxity first (LLF) scheme that assigns priorities based on the remaining wake-up time of the destination stations. We used simulation to show the scalability of the proposed system. Our results show that Wiotap achieves 37% improvement regarding the duty cycle of IoT stations compared to a regular AP. In addition, we developed a testbed to confirm the implementation correctness and the performance benefits of Wiotap in a network with four IoT stations and regular traffic. For the edge and cloud scenarios, our empirical evaluations show up to 44% and 38% improvement in energy and 52% and 41% improvement in delay, respectively.

Industrial applications and cyber-physical systems rely on real-time wireless networks to deliver data in a timely and reliable manner. However, existing solutions provide these guarantees only for stationary nodes. In this article, we present REWIMO, a solution for real-time and reliable communications in mobile networks. REWIMO has a two-tier architecture composed of (i) infrastructure nodes and (ii) mobile nodes that associate with infrastructure nodes as they move. REWIMO employs an on-join bandwidth reservation approach and benefits from a set of techniques to efficiently reserve bandwidth for each mobile node at the time of its admission and over its potential data forwarding paths. To ensure association of mobile nodes with infrastructure nodes over high-quality links, REWIMO uses the two-phase scheduling technique to coordinate neighbor discovery with data transmission. To mitigate the overhead of handling network dynamics, REWIMO employs an additive scheduling algorithm, which is capable of additive bandwidth reservation without modifying existing schedules. Compared to the algorithms used by static real-time wireless networks, the techniques and the algorithms employed by REWIMO result in a significant increase in real-time capacity, enhanced reliability, and considerably faster handling of network dynamics.

Real-time wireless communication infrastructure is increasingly deployed to support industrial and cyber-physical applications. A limitation of existing real-time protocols is that they do not support mobility. This paper presents the development of a real-time network composed of a multi-hop infrastructure, and mobile nodes that associate with infrastructure nodes as they move. Once a mobile node joined the network, its real-time communication is guaranteed irrespective to the number and mobility pattern of mobile nodes. To develop this network, we propose Mobility-Aware Scheduling Algorithm (MASA), which benefits from new transmission scheduling approaches that cleverly combine potential packet transmissions to increase real-time capacity. We have developed a realistic trace-based simulator to evaluate the performance of MASA against two baseline algorithms. Experimental results indicate that MASA increases the number of admitted mobile nodes by 7× and 1.6×, and extends the network lifetime by 110% and 30%, compared to the baselines.

In this paper we consider the problem of supporting real-time communication in mobile networks. To address this challenge, we propose novel transmission scheduling techniques that handle the routing uncertainty introduced by mobility. The core of the scheduling techniques involves controlling the order in which transmissions are scheduled and intelligently scheduling multiple transmissions in a single entry of the scheduling matrix without conflict. Flow-Ordered Mobility-Aware Real-time Scheduling (FO-MARS) integrates these techniques to provide a 14x increase in real-time capacity compared to the baseline algorithms designed for static real-time networks. Additionally, we propose Additive Mobility-Aware Real-time Scheduling (A-MARS), which can handle network dynamics such as the addition or removal of flows without having to reschedule previously admitted flows. As a result, A-MARS achieves significantly lower admission latency than that of the baselines.

The increasing growth of low-power wireless networks in real-world implementations has intensified the need to develop well-organized key network building blocks. Neighbor discovery, link quality measurement and data collection are among the fundamental building blocks of network initialization process. Over the past decade, network initialization has attracted significant attention from the research community of low-power wireless networks. Accordingly, the general concern of this paper is to survey neighbor discovery, link evaluation and collection tree construction protocols, as well as, research challenges in these research areas. Furthermore, we explore the impacts of these protocols on the functionality of different layers in the network protocol stack. In order to provide a clear view of the state-of-the-art neighbor discovery approaches, this paper also presents a classification of the existing neighbor discovery protocols. Finally, some of the important open issues in developing network initialization protocols are discussed to present new directions for further research.