Deterministic Network Research Articles

Stochastic Game for Resource Management in Cellular Zero-Touch Deterministic Industrial M2M Networks

In this letter, we investigate the resource allocation problem for cellular Zero-Touch Deterministic Industrial Machine-to-Machine (ZT-DI-M2M) communications. We consider a scenario, in which multiple self-adaptive industrial M2M communications are deployed underlaying cellular networks to emulate a variety of vertical use cases in Industry 4.0 with the objective of guaranteeing the determinacy of latency. Specifically, in order to figure out the relationship between latency determinacy and the utilization of wireless resources meanwhile modeling the uncertainty of the stochastic environment, we firstly formulate the resource allocation problem as a stochastic game by jointly considering transmission power control, frequency spectrum allocation and the selection of base stations. Afterwards, a random graph-based sparse Long Short-Term Memory (LSTM) network is proposed to solve the optimization problem while reducing the computational complexity. Finally, numerical result demonstrates the effectiveness of the proposed scheme.

Decentralized Dynamic Scheduling of TCPS Flows and a Simulator for Time-sensitive Networking

Cybersickness and control-loop instabilities are two main concerns in Tactile Cyber-Physical Systems (TCPS). TCPS applications demand stringent bounds on end-to-end latencies to avoid their occurrences. Traditional best-effort networks cannot guarantee packet latencies in the presence of external traffic. However, emerging deterministic networks such as IEEE 802.1 Time-Sensitive Networking (TSN) can isolate time-critical flows from external traffic using IEEE 802.1Qbv Time-Aware Shaper (TAS) to guarantee bounded end-to-end packet latencies. In this work, we develop eDDSCH-TSN, a decentralized dynamic scheduling protocol to configure non-overlapping gate slots in TAS-enabled TSN switches to support TCPS flows. eDDSCH-TSN supports plug-and-play operation of compatible TCPS terminals with guaranteed minimal end-to-end packet latencies. Compared to the state-of-the-art, eDDSCH-TSN provides three orders lower end-to-end packet latencies for TCPS flows in mid-size networks with 10 hops between source and destination terminals. Further, we also present PYTSN, an open-source discrete-event TSN simulator that we use for evaluating eDDSCH-TSN. In particular, we use PYTSN to show the isolation of TCPS flows from external traffic and plug-and-play operation of TCPS terminals.

Prediction of Lung Nodule Progression with an Uncertainty-Aware Hierarchical Probabilistic Network.

Predicting whether a lung nodule will grow, remain stable or regress over time, especially early in its follow-up, would help doctors prescribe personalized treatments and better surgical planning. However, the multifactorial nature of lung tumour progression hampers the identification of growth patterns. In this work, we propose a deep hierarchical generative and probabilistic network that, given an initial image of the nodule, predicts whether it will grow, quantifies its future size and provides its expected semantic appearance at a future time. Unlike previous solutions, our approach also estimates the uncertainty in the predictions from the intrinsic noise in medical images and the inter-observer variability in the annotations. The evaluation of this method on an independent test set reported a future tumour growth size mean absolute error of 1.74 mm, a nodule segmentation Dice's coefficient of 78% and a tumour growth accuracy of 84% on predictions made up to 24 months ahead. Due to the lack of similar methods for providing future lung tumour growth predictions, along with their associated uncertainty, we adapted equivalent deterministic and alternative generative networks (i.e., probabilistic U-Net, Bayesian test dropout and Pix2Pix). Our method outperformed all these methods, corroborating the adequacy of our approach.

Deep transfer reinforcement learning for resource allocation in hybrid multiple access systems

This paper proposes a resource allocation scheme for hybrid multiple access involving both orthogonal multiple access and non-orthogonal multiple access (NOMA) techniques. The proposed resource allocation scheme employs multi-agent deep reinforcement learning (MA-DRL) to maximize the sum-rate for all users. More specifically, the MA-DRL-based scheme jointly allocates subcarrier and power resources for users by utilizing deep Q networks and multi-agent deep deterministic policy gradient networks. Meanwhile, an adaptive learning determiner mechanism is introduced into our allocation scheme to achieve better sum-rate performance. However, the above deep reinforcement learning adopted by our scheme cannot optimize parameters quickly in the new communication model. In order to better adapt to the new environment and make the resource allocation strategy more robust, we propose a transfer learning scheme based on deep reinforcement learning (T-DRL). The T-DRL-based scheme allows us to transfer the subcarrier allocation network and the power allocation network collectively or independently. Simulation results show that the proposed MA-DRL-based resource allocation scheme can achieve better sum-rate performance. Furthermore, the T-DRL-based scheme can effectively improve the convergence speed of the deep resource allocation network.

Risk-Averse Equilibria for Vehicle Navigation in Stochastic Congestion Games

The fast-growing market of autonomous vehicles, unmanned aerial vehicles, and fleets in general necessitates the design of smart and automatic navigation systems considering the stochastic latency along different paths in the traffic network. The longstanding shortest path problem in a deterministic network, whose counterpart in a congestion game setting is Wardrop equilibrium, has been studied extensively, but it is well known that finding the notion of an optimal path is challenging in a traffic network with stochastic arc delays. In this work, we propose three classes of risk-averse equilibria for an atomic stochastic congestion game in its general form where the arc delay distributions are load dependent and not necessarily independent of each other. The three classes are risk-averse equilibrium (RAE), mean-variance equilibrium (MVE), and conditional value at risk level <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> equilibrium ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{CVaR}_{\alpha}\text{E}$ </tex-math></inline-formula> ) whose notions of risk-averse best responses are based on maximizing the probability of taking the shortest path, minimizing a linear combination of mean and variance of path delay, and minimizing the expected delay at a specified risky quantile of the delay distributions, respectively. We prove that for any finite stochastic atomic congestion game, the risk-averse, mean-variance, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{CVaR}_{\alpha}$ </tex-math></inline-formula> equilibria exist. We show that for risk-averse travelers, the Braess paradox may not occur to the extent presented originally since players do not necessarily travel along the shortest path in expectation, but they take the uncertainty of travel time into consideration as well. We show through some examples that the price of anarchy can be improved when players are risk-averse and travel according to one of the three classes of risk-averse equilibria rather than the Wardrop equilibrium.

Holographic-type communication: A new challenge for the next decade

Holographic-Type Communication (HTC) is an important technology that will be supported by 6G and beyond wireless systems. It provides truly immersive experiences for a large number of novel applications, such as holographic telepresence, healthcare, retail, education, training, entertainment, sports, and gaming, by displaying multi-view high resolution 3D holograms of humans or objects/items and creating multi-sensory media (mulsemedia), including audio, haptic, smell, and taste. HTC faces great challenges in transmitting high volume data with guaranteed end-to-end latency which cannot be addressed by existing communication and networking technologies. The contribution of this paper is two-fold. First, it introduces the basics and generic architectures of HTC systems. The encoding and decoding of hologram and mulsemedia are discussed, and the envisioned use cases and technical requirements are introduced. Second, this paper identifies limitations of existing wireless and wired networks in realizing HTC and points out the promising 6G and beyond networking technologies. Particularly, for HTC sources, the point cloud encoding and mulsemedia creation and synchronization are introduced. For HTC networking, new directions and associated research challenges, such as semantic communications, deterministic networks, time sensitive networks, distributed encoding and decoding, and predictive networks, are discussed as they may enable high data rate communications with guaranteed end-to-end latency. For HTC destinations, the heterogeneity of HTC devices, synchronization, and user motion prediction are explored and associated research challenges are pointed out. Video communication with 2D content has profoundly changed our daily life and workin style. HTC is an advanced technology that provides 3D immersive experiences, which will become the next research frontier.

A Stochastic and Bayesian Inference Toolchain for Uncertainty and Risk Quantification of Rare Autoignition Events in Dry Low-Emission Premixers

Abstract Quantification of aleatoric uncertainties due to the inherent variabilities in operating conditions and fuel composition is essential for designing and improving premixers in dry low-emissions (DLE) combustion systems. Advanced stochastic simulation tools require a large number of evaluations in order to perform this type of uncertainty quantification (UQ) analysis. This task is computationally prohibitive using high-fidelity computational fluid dynamic (CFD) approaches such as large eddy simulation (LES). In this paper, we describe a novel and computationally efficient toolchain for stochastic modeling using minimal input from LES, to perform uncertainty and risk quantification of a DLE system. More specially, high-fidelity LES, chemical reactor network (CRN) model, beta mixture model, Bayesian inference and sequential Monte Carlo (SMC) are integrated into the toolchain. The methodology is applied to a practical premixer of low-emission combustion system with dimethyl ether (DME)/methane–air mixtures to simulate auto-ignition events at different engine conditions. First, the benchmark premixer is simulated using a set of LESs for a methane/air mixture at elevated pressure and temperature conditions. A partitioning approach is employed to generate a set of deterministic chemical reactor network (CRN) models from LES results. These CRN models are then solved at the volume-average conditions and validated by LES results. A mixture modeling approach using the expectation-method of moment (E-MM) is carried out to generate a set of beta mixture models and characterize uncertainties for LES-predicted temperature distributions. These beta mixture models and a normal distribution for DME volume fraction are used to simulate a set of stochastic CRN models. The Bayesian inference approach through SMC method is then implemented on the results of temperature distributions from stochastic CRN models to simulate the probability of auto-ignition in the benchmark premixer. The results present a very satisfactory performance for the stochastic toolchain to compute the auto-ignition propensity for a few events with a particular combination of inlet temperature and DME volume fraction. Characterization of these rare events is computationally prohibitive in the conventional deterministic methods such as high-fidelity LES.

Bisimulations of Probabilistic Boolean Networks

A probabilistic Boolean network (PBN) is a collection of Boolean networks endowed with a probability structure describing the likelihood with which a constituent network is active at each time step. This paper proposes a definition of bisimulation for PBNs. The notion is inspired by the analogous notions for probabilistic chains and for stochastic linear systems. Necessary and sufficient conditions to check the proposed notion are derived, model reduction of PBNs via bisimulation is addressed, and a discussion on the use of probabilistic bisimulation for optimal control design is given. The present results extend the theory of bisimulation known for deterministic Boolean networks to a stochastic setting.

An optimum solution for coal permeability estimation from mesoscopic scale calibrated stochastic and deterministic discrete fracture network models

The efficiency of a coal bed as a reservoir of methane and CO2 sink primarily depends on its fracture permeability. Conventional techniques of permeability estimation from drilled-core plugs in the laboratory and analytical computations are often different from in-situ measurements by multiple orders. Hence, pre-drill estimation of coal bed permeability remains one of the major challenges for the operators. Researchers usually try to solve this issue by building DFN models based on the direct use of µCT images of millimeters scale coal chips. However, such small-scale DFN models also overestimate permeability by many folds. As a solution, we propose the deployment of calibrated Discrete Fracture Network (DFN) modeling technique based on mesoscale coal images. Deterministic and stochastic DFN models are simulated by replicating thirteen coal specimens collected from the Gondwana coal seams in the Raniganj coalfield of India. Different model outputs such as directional permeabilities, permeability anisotropy, connectivity, etc. are used to distinguish and calibrate these models. The derived average permeabilities from these models closely match with available field measurements. Thus, the proposed technique helps in minimizing the huge gap between the laboratory and well-test measurements. In the process, we derive the threshold sample/model size that would sufficiently address the average cleat permeability at the well-drainage scale. Additionally, sensitivity analysis of key fracture attributes is carried out to quantify their effect on coal permeability.

Deterministic Latency/Jitter-Aware Service Function Chaining Over Beyond 5G Edge Fabric

Deterministic Networking (DetNet) has recently attracted much attention. It aims at studying the deterministic bounded latency and low latency variation for time-sensitive applications (e.g., industrial automation). To improve the quality of service (QoS) guarantee and make the network management efficient, it is desirable for Internet Service Provider (ISP) to obtain an optimal service function chain (SFC) provision strategy while providing deterministic service performance for the time-sensitive applications. In this paper, we will study the deterministic SFC lifetime management problem in beyond 5G edge fabric with the objective of maximizing the overall profits and ensuring the deterministic latency and jitter of SFC requests. We first formulate this problem as a mathematical model with the maximal profits for ISP. Then, the novel Deterministic SFC Deployment algorithm (Det-SFCD) and SFC Adjustment algorithm (Det-SFCA) due to traffic load variation are proposed to efficiently solve the SFC lifetime management problem. Extensive simulation results show that our proposed algorithms can achieve better performance in terms of SFC request acceptance rates, overall profits and latency variation compared with the benchmark algorithm.

Delay Analysis of Consensus Communication for Blockchain-Based Applications Using Network Calculus

Blockchain has been witnessed a growing application in mobile communication. The application field ranges from the Internet of Things (IoT), Vehicle to Everything (V2X), Mobile Edge Computing (MEC), etc. The conjunction with blockchain can significantly avoid data tempering and protect user privacy. Although blockchain guarantees the security of mobile communication, the operation cost is increasing. The consensus algorithm of blockchain drives multiple untrust parties to keep data consistency, and it generates a large number of communication overheads. In this letter, we focus on the Byzantine Fault Tolerance (BFT) type of consensus and conduct a performance model. By utilizing the deterministic network calculus method, we analyze the delay bound of the Practical Byzantine Fault Tolerance (PBFT) and HotStuff consensus algorithm. The result of the simulation provides a valuable guideline for delay-sensitive blockchain-based applications.

Metagrating-based acoustic wavelength division multiplexing enabled by deterministic and probabilistic deep learning models

Wavelength division multiplexing (WDM), the technology that utilizes different wavelengths of carrier signal as independent information channels and helps to realize enhanced information density and functional diversity, is desired in various acoustic applications for the growing demand of higher transmission efficiency and lower cost. In this paper, we marry the rising concept of acoustic metagrating with the technology of WDM and demonstrate that interesting and distinct wavelength-dependent functionalities with unitary efficiency in prespecified frequency ranges can be realized by a simple grating structure. To this end, we integrate the particle swarm optimization with the deep learning technique to resolve the uncertainty issue and multi-objective problem and develop both deterministic and probabilistic neural networks for the inverse design of a metagrating-based WDM device. As a result, the computational cost is greatly reduced, and the probabilistic model reveals the sensitivity and flexibility of the parameters of the metagrating with respect to the desired functionality. In this paper, we not only provide an intelligent inverse design paradigm of high-performance WDM devices for multiple manipulation purposes but also present a feasible solution for the development of integrated acoustic devices for wavelength-dependent applications.

Receding-Horizon Prediction of Vehicle Velocity Profile Using Deterministic and Stochastic Deep Neural Network Models

The paper firstly proposes a deterministic deep feedforward neural network model aimed at predicting the city bus velocity profile over receding time horizon based on the following inputs: actual vehicle position, actual velocity or short-term history of vehicle velocities, time of day and day of week. A systematic analysis of the influence of different input subsets, history interval length and prediction horizon length is carried out to find an optimal configuration of NN model inputs and hyperparameters. Secondly, a stochastic version of neural network prediction model is proposed, which predicts expectations and standard deviations of velocity patterns over the receding time horizon. The stochastic model prediction accuracy is verified against the recorded test dataset features, as well as by comparing the predicted velocity expectation with the deterministic model prediction and correlating the predicted velocity standard deviation with deterministic model prediction uncertainty metrics. The verification results indicate that: (i) the deterministic model velocity prediction accuracy is characterized by the R2 score greater than 0.8 for the prediction horizon length of 10 s and remains to be solid (greater than 0.6) for the horizon lengths up to 25 s; (ii) the actual vehicle position and the velocity history are the most significant input features, where the optimal value of history interval length lies in the range from 30 to 50 s; (iii) the stochastic model have only slightly lower accuracy of predicting the velocity expectation along the receding horizon when compared to the deterministic model (the root mean square error is higher by 2.2%), and it outputs consistent standard deviation prediction.

Increasing land-use durations enhance soil microbial deterministic processes and network complexity and stability in an ecotone

Studies of community assembly and species interactions are updating our view of the mechanisms underpinning microbial diversity in single-type ecosystems, yet they are rarely conducted in ecotones, such as the agro-pastoral ecotone of northern China (APEN) undergoing frequent land-use conversions. In this study, soil microbial assembly processes and co-occurrence patterns were examined in different land-use types and durations across the APEN. The interpretation of remote sensing images revealed that current land-use types lasted 1 to 9 years for all samples. None of measured soil properties changed significantly between cropland and grassland, while silt and sand differed between the long (5 to 9 years) and short (1 to 4 years) duration. Soil microbial communities were assembled under consistent processes in both land-use types, but determinism clearly exhibited greater influences in the long duration than in the short one. The β-nearest taxon index (βNTI) decreased significantly with the durations in all samples and was also affected by total nitrogen (TN), soil organic matter (SOM), total phosphorus (TP), and clay. For the co-occurrence networks, nodes, edges, modularity, and the proportion of negative edges were similar between cropland and grassland, but obviously higher in the long duration than in the short one. Simultaneously, these metrics of the sub-networks had strong positive correlations with the durations, and weaker but significant correlations with TN, SOM, silt, and sand. Altogether, this study demonstrated that frequent land-use conversions might alleviate the impact of current land-use types, but highlight the importance of land-use durations on soil microbial community assembly and co-occurrence patterns in the APEN, and the deterministic processes and network complexity and stability increased with the durations, which advance the understanding of the mechanisms maintaining soil microbial diversity in ecotones.

Deep deterministic policy gradient and graph convolutional network for bracing direction optimization of grid shells

In this paper, we propose a method for bracing direction optimization of grid shells using a Deep Deterministic Policy Gradient (DDPG) and Graph Convolutional Network (GCN). DDPG allows simultaneous adjustment of variables during the optimization process, and GCN allows the DDPG agent to receive data representing the whole structure to determine its actions. The structure is interpreted as a graph where nodes, element properties, and internal forces are represented by the node feature matrix, adjacency matrices, and weighted adjacency matrices. DDPG agent is trained to optimize the bracing directions. The trained agent can find sub-optimal solutions with moderately small computational cost compared to the genetic algorithm. The trained agent can also be applied to structures with different sizes and boundary conditions without retraining. Therefore, when various types of braced grid shells have to be considered in the design process, the proposed method can significantly reduce computational cost for structural analysis.

High Capacity and Resilient Large-Scale Deterministic IP Networks

High Capacity and Resilient Large-Scale Deterministic IP Networks

Enabling Deterministic Tasks with Multi-Access Edge Computing in 5G Networks

Deterministic executions of computation-intensive and delay-sensitive tasks are vital for realizing Industry 4.0. Multi-access edge computing (MEC) enables critical tasks to be offloaded to the network edge for quickly responding and processing tasks locally. However, during workload peaks at the resource-limited edge, the best effort IP forwarding in the typical network architecture incurs long-tail latency at both the access and interconnection networks of MEC systems. The long-tail latency results in strict service level agreements (SLAs) unable to be guaranteed in end-to-end communication. In this article, we propose a task deterministic network (TDN) architecture that provides communication with bounded low latency and zero jitter for critical tasks among MEC systems. In TDN, the cross-domain collaboration mechanisms of the layer 2/layer 3 deterministic networking and 5G are jointly designed to eliminate the long-tail latency in typical MEC system networks. In addition, we design a seamless working scheme for the time-sensitive networking controller, the MEC orchestrator, and other coordinators to enable edge collaboration and global deterministic forwarding. Moreover, the main functions of TDN are detailed, including clock synchronization, network slicing, cycle mapping, and multi-layer collaboration. Finally, we present simulation results to substantiate the performance of TDN for accommodating critical service flows among MEC systems.

Autonomous Reinforcement Control of Visual Underwater Vehicles: Real-Time Experiments Using Computer Vision

Swift decision-making based on visual environment perception is crucial for autonomous control of visual underwater vehicles (VUVs) during underwater missions. However, learning perception and decision models individually might result in weak robustness of overall control system as the mismatched state extraction and control decision making are asynchronous. As a remedy, we will introduce in this paper an end-to-end monocular autonomous reinforcement control (MARC) framework for autonomous control of VUVs, which is performed in two cascaded procedures, i.e., 1) perception, where a geometric network (GeoNet) is designed based on a convolutional encoder-decoder network to generate depth maps from input environmental videos; 2) decision, where with depth maps as input, a reinforcement control network (CtrlNet) integrates a convolutional neural network into a deep deterministic policy gradient network and outputs action decisions, which are refined by reinforcement learning algorithm for obstacle-avoiding based autonomous control. Numerical and experimental results demonstrate that the proposed MARC exhibits high-quality depth prediction and is capable of conducting obstacle-avoiding navigation and autonomous control of VUVs with high accuracy and strong robustness.

Resource Allocation for Cellular Zero-Touch Deterministic Industrial M2M Networks: A Reinforcement Learning-Based Scheme

In this letter, we investigate the resource allocation problem for cellular zero-touch deterministic industrial machine-to-machine networks. We consider a scenario in which multiple self-adaptive industrial machine-to-machine (M2M) networks are deployed underlaying cellular networks to emulate a variety of vertical use cases in future Industry 4.0 with the objective of guaranteeing the determinacy of latency by learning-inspired resource allocation policy. Specifically, in order to figure out the relationship between latency determinacy and the utilization of wireless resources meanwhile modeling the uncertainty of the stochastic environment, we first formulate the resource allocation problem as a Markov game by jointly considering transmission power control, frequency spectrum allocation, and the selection of base stations. Afterward, a random graph-based sparse long short-term memory network is proposed to solve the optimization problem while reducing the computational complexity. Finally, numerical result demonstrates the effectiveness of the proposed scheme.

Analysis of Dampers in Time-Sensitive Networks With Non-Ideal Clocks

Dampers are devices that reduce delay jitter in the context of time-sensitive networks, by delaying packets for the amount written in packet headers. Jitter reduction is required by some real-time applications; beyond this, dampers have the potential to solve the burstiness cascade problem of deterministic networks in a scalable way, as they can be stateless. Dampers exist in several variants: some apply only to earliest-deadline-first schedulers, whereas others can be associated with any packet schedulers; some enforce FIFO ordering whereas some others do not. Existing analyses of dampers are specific to some implementations and some network configurations; also, they assume ideal, non-realistic clocks. In this paper, we provide a taxonomy of all existing dampers in general network settings and analyze their timing properties in presence of non-ideal clocks. In particular, we give formulas for computing residual jitter bounds of networks with dampers of any kind. We show that non-FIFO dampers may cause reordering due to clock non-idealities and that the combination of FIFO dampers with non-FIFO network elements may very negatively affect the performance bounds. Our results can be used to analyze timing properties and burstiness increase in any time-sensitive network, as we illustrate on an industrial case-study.