With the advent of edge computing, there is increasing interest in wireless latency-critical services. Such applications require the end-to-end delay of the network infrastructure (communication and computation) to be less than a target delay with a certain probability, e.g., 10(-2)-10(-5). To deal with this guarantee level, the first step is to predict the transient delay violation probability (DVP) of the packets traversing the network. The guarantee level puts a threshold on the tail of the end-to-end delay distribution; thus, it makes data-driven DVP prediction a challenging task. We propose to use the extreme value mixture model in the mixture density network (MDN) method for this task. We implemented it in a multi-hop queuing-theoretic system to predict the DVP of each packet from the network state variables. This work is a first step toward utilizing the DVP predictions, possibly in the resource allocation scheme or queuing discipline. Numerically, we show that our proposed approach outperforms state-of-the-art Gaussian mixture model-based predictors by orders of magnitude, in particular for scenarios with guarantee levels above 10(-2).

With the emergence of new application areas, such as cyber-physical systems and human-in-the-loop applications, there is a need to guarantee a certain level of end-to-end network latency with extremely high reliability, e.g., 99.999%. While mechanisms specified under IEEE 802.1AS time-sensitive networking (TSN) can be used to achieve these requirements for switched Ethernet networks, implementing TSN mechanisms in wireless networks is challenging due to their stochastic nature. To conform the wireless link to a reliability level of 99.999%, the behavior of extremely rare outliers in the latency probability distribution, or the tail of the distribution, must be analyzed and controlled. This work proposes predicting the tail of the latency distribution using state-of-the-art data-driven approaches, such as mixture density networks (MDN) and extreme value mixture models, to estimate the likelihood of rare latencies conditioned on the network parameters, which can be used to make more informed decisions in wireless transmission. Actual latency measurements of a commercial private and a software-defined 5G network are used to benchmark the proposed approaches and evaluate their sensitivities concerning the tail probabilities. Our benchmarks highlight how the proposed methods, aided by noise regularization, achieve an acceptable accuracy in the extreme 99.9999% latency probabilities.

The increasing demand for latency-sensitive applications has necessitated the development of sophisticated algorithms that efficiently manage packets with end-to-end delay targets traversing the networked infrastructure. Network components must consider minimizing the packets' end-to-end delay violation probabilities (DVP) as a guiding principle throughout the transmission path to ensure timely deliveries. Active queue management (AQM) schemes are commonly used to mitigate congestion by dropping packets and controlling queuing delay. Today's established AQM schemes are threshold-driven, identifying congestion and trigger packet dropping using a predefined criteria which is unaware of packets' DVPs. In this work, we propose a novel framework, Delta, that combines end-to-end delay characterization with AQM for minimizing DVP. In a queuing theoretic environment, we show that such a policy is feasible by utilizing a data-driven approach to predict the queued packets' DVPs. That enables Delta AQM to effectively handle links with arbitrary stationary service time processes. The implementation is described in detail, and its performance is evaluated and compared with state of the art AQM algorithms. Our results show the Delta outperforms current AQM schemes substantially, in particular in scenarios where high reliability, i.e. high quantiles of the tail latency distribution, are of interest.

This paper presents ExPECA, an edge computing and wireless communication research testbed designed to tackle two pressing challenges: comprehensive end-to-end experimentation and high levels of experimental reproducibility. Leveraging OpenStack-based Chameleon Infrastructure (CHI) framework for its proven flexibility and ease of operation, ExPECA is located in a unique, isolated underground facility, providing a highly controlled setting for wireless experiments. The testbed is engineered to facilitate integrated studies of both communication and computation, offering a diverse array of Software-Defined Radios (SDR) and Commercial Off-The-Shelf (COTS) wireless and wired links, as well as containerized computational environments. We exemplify the experimental possibilities of the testbed using OpenRTiST, a latency-sensitive, bandwidthintensive application, and analyze its performance. Lastly, we highlight an array of research domains and experimental setups that stand to gain from ExPECA's features, including closed-loop applications and time-sensitive networking.

Supporting applications in emerging domains like cyber-physical systems and human-in-the-loop scenarios typically requires adherence to strict end-to-end delay guarantees. Contributions of many tandem processes unfolding layer by layer within the wireless network result in violations of delay constraints, thereby severely degrading application performance. Meeting the application's stringent requirements necessitates coordinated optimization of the end-to-end delay by fine-tuning all contributing processes. To achieve this task, we designed and implemented EDAF, a framework to decompose packets' end-to-end delays and determine each component's significance for 5G network. We showcase EDAF on OpenAirInterface 5G uplink, modified to report timestamps across the data plane. By applying the obtained insights, we optimized end-to-end uplink delay by eliminating segmentation and frame-alignment delays, decreasing average delay from 12ms to 4ms.

With the emergence of new application areas such as cyber-physical systems and human-in-the-loop applications ensuring a specific level of end-to-end network latency with high reliability (e.g., 99.9%) is becoming increasingly critical. To align wireless links with these reliability requirements, it is essential to analyze and control network latency in terms of its full probability distribution. However, in a wireless link, the distribution may vary over time, making this task particularly challenging. We propose predicting the latency distribution using state-of-the-art data-driven techniques that leverage historical network information. Our approach tokenizes network state information and processes it using temporal deep-learning architectures-namely LSTM and Transformer models-to capture both short- and long-term delay dependencies. These models output parameters for a chosen parametric density via a mixture density network with Gaussian mixtures, yielding multi-step probabilistic forecasts of future delays. To validate our proposed approach, we implemented and tested these methods using a time-synchronized, SDR-based OpenAirInterface 5G testbed to collect and preprocess network-delay data. Our experiments show that the Transformer model achieves lower negative log-likelihood and mean absolute error than both LSTM and feed-forward baselines in challenging scenarios, while also providing insights into model complexity and training/inference overhead. This framework enables more informed decision-making for adaptive scheduling and resource allocation, paving the way toward enhanced QoS in evolving 5G and 6G networks.