Delay-constrained Applications Research Articles

Handover-Enabled Dynamic Computation Offloading for Vehicular Edge Computing Networks

The computation offloading technique is a promising solution that empowers computationally limited resource devices to run delay-constrained applications efficiently. Vehicular edge computing incorporates the processing capabilities into the vehicles, and thus, provides computing services for other vehicles through computation offloading. Mobility affects the communication environment and leads to critical challenges for computation offloading. In this paper, we consider an intelligent task offloading scenario for vehicular environments including smart vehicles and roadside units, which can cooperate to perform resource sharing. Intending to minimize the average offloading cost which takes into account energy consumption together with delay in transmission and processing phases, we formulate the task offloading problem as an optimization problem and implement an algorithm based on deep reinforcement learning with Double Q-learning which allows user equipments to learn the offloading cost performance by observing the environment and make steady sequences of offloading decisions despite the uncertainties of the environment. Besides, concerning the high mobility of the environment, we propose a handover-enabled computation offloading strategy that leads to a better quality of service and experience for users in beyond 5G and 6G heterogeneous networks. Simulation results demonstrate that the proposed scheme achieves low-cost performance compared to the existing offloading decision strategies in the literature.

Slicing a FANET for heterogeneous delay-constrained applications

Today’s networks use a “one size fits all” approach that makes them unsuitable to satisfy the performance requirements of heterogeneous applications in terms of latency, scalability, availability and reliability. To this purpose, the concept of network slices has been recently introduced to meet heterogeneous requirements of vertical applications deployed on top of common network infrastructures.The objective of this paper is to define a 6G zero-touch management framework based on a Flying Aerial Network (FANET) made by a set of UAVs, which is able to provide ground devices with network slices that are able to guarantee edge computing to remote areas according to heterogeneous requirements in terms of mean delay and jitter. An inter-slice orchestrator is introduced to split the computation power of the Computing Element of each UAV between the different slices, while an intra-slice orchestrator is in charge of managing horizontal offload among UAVs to obtain load balancing, so decreasing mean delay and delay jitter. An optimization problem based on Reinforcement Learning (RL) is defined to optimize the horizontal-offload decision process of the Intra-slice Orchestrators at run-time. An extensive simulation campaign is used to evaluate the performance of the system and to demonstrate the ability of the proposed framework to achieve energy efficiency, therefore increasing the flight autonomy of the FANET.

Achieving QoS for bursty uRLLC applications over passive optical networks

Emerging real-time applications such as those classified under ultra-reliable low latency (uRLLC) generate bursty traffic and have strict quality of service (QoS) requirements. The passive optical network (PON) is a popular access network technology, which is envisioned to handle such applications at the access segment of the network. However, the existing standards cannot handle strict QoS constraints for such applications. The available solutions rely on instantaneous heuristic decisions and maintain QoS constraints (mostly bandwidth) in an average sense. Existing proposals in generic networks with optimal strategies are computationally complex and are, therefore, not suitable for uRLLC applications. This paper presents a novel computationally efficient, far-sighted bandwidth allocation policy design for facilitating bursty uRLLC traffic in a PON framework while satisfying strict QoS (age of information/delay and bandwidth) requirements. To this purpose, first we design a delay-tracking mechanism, which allows us to model the resource allocation problem from a control-theoretic viewpoint as a model predictive control (MPC) problem. MPC helps in making far-sighted decisions regarding resource allocations and captures the time-varying dynamics of the network. We provide computationally efficient polynomial time solutions and show their implementation in the PON framework. Compared to existing approaches, MPC can improve delay violations by 15% and 45% at loads of 0.8 and 0.9, respectively, for delay-constrained applications of 1 ms and 4 ms. Our approach is also robust to varying traffic arrivals.

Multi-Agent Deep Reinforcement Learning in Flying Ad-Hoc Networks for Delay-Constrained Applications

As a benefit of their compelling features, unmanned aerial vehicles (UAVs) are expected to play a vital role in 6G networks. UAVs are capable of providing wireless connectivity where network infrastructure is not available, or complement the conventional base stations. UAVs organized as a Flying Ad-hoc Network (FANET) can process jobs received by ground devices through vertical offload. Moreover, horizontal offload inside the FANET can applied to balance the load among UAVs to reduce the processing delay to offloaded jobs. However, offloading decisions inside a FANET have to be dynamically adapted to the current processing load distribution based on the state of the FANET and the number of job requests coming from the served geographical area. As the number of UAVs in the FANET increases, single agent reinforcement learning approaches fall short to achieve reasonable performance due to the exponential increase in the action space. For this reason, in this paper we propose a Multi-AgeNt Intra-FANET (MANIA-F) Framework based on Multi Agent PPO (MAPPO), in which each agent chooses the best offloading probabilities to forward incoming jobs to neighboring UAVs. The horizontal offload decision problem is defined as a Markov Decision Process (MDP) that is solved via Multi-Agent Deep Reinforcement Learning (MARL).

Temporal Task Scheduling of Multiple Delay-Constrained Applications in Green Hybrid Cloud

A growing number of global companies select Green Data Centers (GDCs) to manage their delay-constrained applications. The fast growth of users’ tasks dramatically increases the energy consumed by GDCs owned by a company, e.g., Google and Amazon. The random nature of tasks brings a big challenge of scheduling tasks of each application with limited infrastructure resources of GDCs. Therefore, hybrid cloud is widely employed to smartly outsource some tasks to public clouds. However, the temporal variation in many factors including revenue, price of power grid, solar irradiance, wind speed, price of public clouds makes it challenging to schedule all tasks of each application in a cost-effective way while strictly meeting their expected delay constraints. This work proposes a temporal task scheduling algorithm investigating the temporal variation in green hybrid cloud to schedule all tasks within their delay constraints. Besides, it explicitly presents a mathematical equation of service rates and task refusal. The maximization problem is formulated and tackled by the proposed hybrid optimization algorithm called Genetic Simulated-annealing-based particle swarm optimization. Trace-driven experiments demonstrate that larger profit are achieved than several existing scheduling algorithms.

Design of a 5G Network Slice Extension With MEC UAVs Managed With Reinforcement Learning

Network slices for delay-constrained applications in 5G systems require computing facilities at the edge of the network to guarantee ultra-low latency in processing data flows generated by connected devices, which is challenging with larger volumes of data, and larger distances to the edge of the network. To address this challenge, we propose to extend 5G network slices with Unmanned Aerial Vehicles (UAV) equipped with multi-access edge computing (MEC) facilities. However, onboard computing elements (CE) consume UAV's battery power thus impacting its flight duration. We propose a framework where a System Controller (SC) can turn on and off UAV's CEs, with the possibility of offloading jobs to other UAVs, to maximize an objective function defined in terms of power consumption, job loss, and incurred delay. Management of this framework is achieved by reinforcement learning. A Markov model of the system is introduced to enable reinforcement learning and provide guidelines for the selection of system parameters. A use case is considered to demonstrate the gain achieved by the proposed framework and discuss numerical results.

Adaptive Forwarding With Probabilistic Delay Guarantee in Low-Duty-Cycle WSNs

Despite many existing research on data forwarding in low-duty-cycle wireless sensor networks (WSNs), relatively little work has been done on energy-efficient data forwarding with probabilistic delay bounds. Probabilistic delay guarantees ( i.e. , delay bounded data delivery with reliability constraints) are of increasing importance for many delay-constrained applications, since deterministic delay bounds are prohibitively expensive to guarantee in WSNs. However, radio duty-cycling and unreliable wireless links pose challenges for achieving the probabilistic delay guarantee in WSNs. In this paper, we propose EEAF, a novel energy-efficient adaptive forwarding technique tailored for low-duty-cycle WSNs with unreliable wireless links. We show the existence of path diversity in low-duty-cycle WSNs, where delay-optimal routing and energy-optimal routing are likely following different paths. The key idea of EEAF is to exploit the intrinsic path diversity to provide probabilistic delay guarantees while minimizing transmission cost. In EEAF, an early arriving packet will be adaptively switched to the energy-optimal path for energy conservation. Delay quantiles are derived at each node in a distributed manner and are used as the guidelines in the adaptive forwarding decision making. Extensive testbed experiment and large-scale simulation show that EEAF effectively reduces the transmission cost by 12%~25% with probabilistic delay guarantees under various network settings. In addition, we extend the EEAF technique with data aggregation for event-based traffic scenarios. Evaluation using publicly available WSN event traffic traces yields very encouraging results with up to 40% energy saving in probabilistic delay bounded data delivery.

Hierarchical Offloading for Delay-Constrained Applications in Fog RAN

By computation offloading, fog radio access network (RAN) can support delay-constrained applications, since such a hierarchical network architecture enables parallel computing at local computing layer (LCL), edge computing layer (ECL), and cloud computing layer (CCL). Comparing to processing applications exclusively at the LCL, the assistance of processing at the ECL and the CCL can reduce computation latency, while introduce extra communication latency. These two latency are not only influenced by the hierarchical offloading decision but also by the available communication and computational resources at multiple computing layers. In this regard, this paper aims to jointly provision communication and computational resources for a powerful hierarchical offloading mechanism in fog RAN to complete delay-constrained applications with high-efficiency resource utilization. Specifically, we formulate a deadline-constrained energy minimization problem, which is followed by feasibility analysis, effective solution, and application extension. Through theoretical analyses and simulation results, we provide some insights on hierarchical offloading conditions and demonstrate advantages of our proposed algorithms in terms of the minimum affordable latency, total energy consumption, and scalability.

End-to-End Performance Analysis of Delay-Sensitive Multi-Relay Networks

We study the end-to-end (E2E) performance of multi-relay networks in delay-constrained applications. The results are presented for both decode-and-forward (DF) and AF (A: amplify) relaying schemes. We use some fundamental results on the achievable rates of finite-length codes to analyze the system performance in the cases with short packets. Taking the message decoding delays and different numbers of hops into account, we derive closed-form expressions for the E2E packet transmission delay, the E2E error probability as well as the E2E throughput. Moreover, for different message decoding delays, we determine the appropriate codeword length and the relay power such that the same E2E error probability and packet transmission delay are achieved in the AF- and DF-relay networks. As we show, for different codeword lengths and numbers of hops, the E2E performance of multi-relay networks are affected by the message decoding delay of the nodes considerably.

Parallel Offloading in Green and Sustainable Mobile Edge Computing for Delay-Constrained IoT System

Currently, the Internet of Things (IoT) solutions are playing an important role in numerous areas, especially in smart homes and buildings, health-care, vehicles, and energy. It will continue to expand in various fields in the future. However, some issues limit the further development of IoT technologies. First, the battery-powered feature increases the maintenance cost of replacing batteries for IoT devices. Second, existing Cloud-IoT frameworks are not able to cope with emerging delay-constrained applications in the IoT system due to its centralized mode of operation and the considerable communication delay. Existing studies neither satisfy the demand for the quick response in time-constraint IoT applications nor fundamentally solving the problem of energy sustainability. Therefore, this paper studies the problem of energy sustainability and timeliness in IoT system. Based on Energy Harvesting Technologies (EHT), the Green and Sustainable Mobile Edge Computing (GS-MEC) framework is proposed to make IoT devices self-powered by utilizing the green energy in the IoT environment. In this framework, we formulate the problem of minimizing response time and packet losses of tasks under the limitation of energy queue stability to improve the timeliness and reliability of task processing. Additionally, the dynamic parallel computing offloading and energy management (DPCOEM) algorithm is designed to solve the problem based on the Lyapunov optimization technology. Finally, theoretical analysis demonstrates the effectiveness of the proposed algorithm, and the numerical result of simulation shows that the average performance of the proposed algorithm is an order of magnitude better than state-of-the-art algorithms.

A node deployment algorithm for maximizing network lifetime in delay-constrained duty-cycled wireless sensor networks

Although duty-cycling is a promising approach to reduce energy consumption in wireless sensor networks, sufficiently long network lifetime may not be achieved due to the hot spot problem. Moreover, a long duty cycle interval can lead to high end-to-end delay, which is not desired in delay-constrained applications. In order to address the hot spot problem and long end-to-end delay, this article proposes a novel energy-balanced node deployment algorithm for maximizing network lifetime in duty-cycled wireless sensor networks while taking into account a delay requirement. In addition, energy-balanced node deployment considers network connectivity and sensing coverage constraints, which are also important factors when wireless sensor networks are deployed. An optimization problem is first formulated where the objective function and constraints are estimated based on node distribution in the area and the network parameters. Then, a non-deterministic algorithm is proposed to derive the optimal number of nodes in each circular layer that meets given constraints and maximizes network lifetime. Numerical analysis and simulations have been conducted to validate the proposed algorithm. The results show that the proposed algorithm can achieve higher network lifetime than other schemes.

An algorithm for sink positioning in bus-assisted smart city sensing

Smart Cities use data obtained from different sensors to offer better services. Such data is usually sent to sinks, using the paradigm of Internet of Things. However, covering the whole city area with static sensors might be expensive. This paper addresses the utilization of the public transportation system as a mobility platform for sensor nodes and bus stops acting as sinks. This platform can improve the coverage of a sensor network and take advantage of opportunistic communication. Since this platform can be used for delay-constrained applications, we propose an algorithm to choose sensor sinks in the bus stops of a smart city that minimizes the maximum delay when delivering messages. We compare our solution with an optimal formulation and use real data, obtained in buses from Rio de Janeiro, as an input of our algorithm. Our experiments show that we can use approximately 16% of bus stops as sinks, having less than 10% of increase in the network maximum delay and no significant loss in the spatial coverage.

Delay-Constrained Energy Optimization in High-Latency Sensor Networks

Sensor networks deployed in high-latency environments, such as underwater acoustic and satellite channels, find critical applications in disaster prevention and tactical surveillance. The sensors in these networks have limited energy reserves. In order to extend the lifetime of these sensors, energy must be conserved in all layers of the protocol stack. In addition to long propagation delays, these channels are characterized by limited bandwidth and a lack of well-established closed-form analytical models. This fact makes finding cross-layer energy-optimal solutions a difficult problem to solve. Our goal is to compute near-optimal routes, schedules and transmit power levels for delay-constrained applications of high-latency sensor networks. We present a mixed-integer programming relaxation of the optimization problem. We further propose a decentralized algorithm to iteratively solve the relaxed optimization problem. Comparative simulation analysis shows that our decentralized approach is approximately 3~6 dB more energy-efficient and 2~5 dB more throughput-efficient than the heuristic, time-sensitive greedy forwarding, and least-cost routing algorithms.

Congestion-Aware MAC Layer Adaptation to Improve Video Telephony over Wi-Fi

In wireless networks such as those based on IEEE 802.11, packet losses due to fading and interference are often misinterpreted as indications of congestion by the congestion control protocol at higher layers, causing an unnecessary decrease in the data sending rate. For delay-constrained applications such as video telephony, packet losses may result in excessive artifacts or freeze in the decoded video. We propose a simple and yet effective mechanism to detect and reduce channel-caused packet losses by adjusting the retry limit parameter of the IEEE 802.11 protocol while taking into account the delay requirement of the traffic. Since the retry limit is left configurable in the IEEE 802.11 standard and does not require cross-layer coordination, our scheme can be easily implemented and incrementally deployed. Experimental results of applying the proposed scheme to a WebRTC-based real-time video communication prototype show significant performance gain compared to the case where the retry limit is configured statically.

Analytical model of large data transactions in CoAP networks.

We propose a novel analytical model to study fragmentation methods in wireless sensor networks adopting the Constrained Application Protocol (CoAP) and the IEEE 802.15.4 standard for medium access control (MAC). The blockwise transfer technique proposed in CoAP and the 6LoWPAN fragmentation are included in the analysis. The two techniques are compared in terms of reliability and delay, depending on the traffic, the number of nodes and the parameters of the IEEE 802.15.4 MAC. The results are validated trough Monte Carlo simulations. To the best of our knowledge this is the first study that evaluates and compares analytically the performance of CoAP blockwise transfer and 6LoWPAN fragmentation. A major contribution is the possibility to understand the behavior of both techniques with different network conditions. Our results show that 6LoWPAN fragmentation is preferable for delay-constrained applications. For highly congested networks, the blockwise transfer slightly outperforms 6LoWPAN fragmentation in terms of reliability.

Energy-Efficient Sleep Scheduling for Delay-Constrained Applications Over WLANs

In wireless local area networks (WLANs), switching of the nodes to low-power sleep mode to save energy is common. However, if sleep time is not properly scheduled, significant delays can occur, which is undesirable in delay-constrained applications. In this paper, we propose a novel energy-efficient sleep-scheduling protocol for maximizing the sleep time lengths of each node while satisfying the delay constraints. We first consider the single-user case and present the basic steps that the node takes to decide when and how long it can sleep. For the multiuser scenario, to mitigate channel contention in packet downloading after sleeping, the sleep schedules requested by the nodes are coordinated by the access point (AP) to avoid overlapping active epochs. Simulation results demonstrate that the proposed sleep-scheduling algorithm achieves lower loss rate while achieving higher energy efficiency than that of the existing GreenCall method.

Reducing Power Consumption with QoS Constraints in IEEE 802.16e Wireless Networks

Mobile Broadband Wireless Access (BWA) networks will offer in the forthcoming years multiple and differentiated services to users with high mobility requirements, connecting via portable or wearable devices which rely on the use of batteries by necessity. Since a relatively large fraction of energy is consumed by such devices for transmitting/receiving data over-the-air, mechanisms are needed to reduce power consumption, in order to increase the lifetime of devices, and hence, improve user's satisfaction. The IEEE 802.16, which supports mobile BWA since its e amendment in 2005, defined power saving functions at the Medium Access Control (MAC) layer, which are designed to be operated during open traffic sessions for the greatest energy consumption reduction. However, enabling power saving usually increases the transmission latency, which can negatively affect the Quality of Service (QoS) experienced by users. On the other hand, imposing stringent QoS requirements may limit the amount of energy that can be saved. In this paper, an extensive study of the mutual interaction between power saving mechanisms and QoS support is carried out in the context of the IEEE 802.16e. In particular, two types of delay-constrained applications with different requirements are considered, i.e., Web and Voice over IP (VoIP) for which the IEEE 802.16e standard specifies two different power saving classes. The performance is assessed via detailed packet-level simulation, with respect to several system parameters. To capture the relative contribution of all the factors on the energy- and QoS-related metrics, part of the evaluation is carried out by means of 2k · ?! analysis.

Cross-layer distributed joint power control and scheduling for delay-constrained applications over CDMA-based wireless ad-hoc networks

In this paper, we propose a cross-layer distributed power control and scheduling protocol for delay-constrained applications over mobile CDMA-based ad hoc wireless networks. Herein, we propose a novel scheme where power control is employed to combat delay occurring on multi-hop wireless ad hoc networks via cross-layer information exchange. Based on that, a distributed power control and scheduling protocol is proposed to control the incurred delay as well as the multiple access interference (MAI). Unlike other previous work on power control and scheduling, we also investigate the impact of Doppler spread upon the system performance, and provide a robust system which employs a combination of power control, and coding/interleaving to combat the effects of Doppler spread by exploiting the time diversity when the Doppler spread gets large. Hence, our proposed approach can function appropriately over a wide range of channel conditions.

Robust VB 2D-CELP image transmission over CDMA Rayleigh fading channels

Abstract This paper describes a new error resilient analysis-by-synthesis coding scheme and its application for robust still image transmission over CDMA Rayleigh fading channels. For the purpose of providing reliable transmission, a type-I hybrid ARQ protocol is used in a concatenated Reed–Solomon/convolutional coding scheme. However, for delay-constrained applications, the protocol is used with a limited number of retransmissions in addition to limited RS interleaving. Results of coded images are provided for the uplink of a communication system, where a slowly Rayleigh fading channel is considered.

Statistical multiplexing and QoS provisioning for real-time traffic on wireless downlinks

Quality of service (QoS) provisioning in wireless networks involves accounting for the statistical fluctuations in the wireless channel quality, in addition to the traffic variability of interest in a purely wireline setting. We consider providing QoS to packetized, delay-constrained (real-time) applications over a Rayleigh-faded wireless downlink. Since the wireless medium is prone to high error rates with typically correlated errors, it is essential to use some kind of link-layer error-recovery mechanism to provide the desired level of reliability. We call this procedure of converting a link with frequent and correlated errors into a near-lossless packet pipe "link shaping." The link-shaping scheme considered in this paper exploits the natural interleaving provided by packet-by-packet transmissions to different mobiles to break up the error correlations due to Rayleigh fading and employs forward error correction (FEC) coding on the interleaved data. In addition to considering static (peak-rate) bandwidth sharing as in conventional wireless downlinks, we propose mechanisms for statistical multiplexing of traffic, which lead to substantial capacity gains. For example, for 13 kb/s voice sources over a 1-Mb/s link, we obtain a two-fold capacity gain over static (peak-rate) bandwidth allocation.