Statistical Quality Of Service Research Articles

Proportional-fair uplink resource allocation with statistical QoS provisioning for RAN slicing

This paper investigates the uplink resource allocation issue for radio access network (RAN) slicing with a focus on three primary fifth generation (5G) use cases, namely ultra-reliable low-latency communications (uRLLC), enhanced mobile broadband (eMBB) and massive machine-type communications (mMTC). Most of the existing resource allocation schemes for RAN slicing were designed to address the use cases in downlink communications. However, these schemes are not applicable to the uplink RAN slicing, even though the primary use cases also entail stringent requirements in the uplink. To this end, we aim to develop a new, fairness-aware uplink resource allocation scheme for RAN slicing, catering to the three 5G use cases. Firstly, we formulate a new uplink resource allocation optimization problem that maximizes a sum logarithmic utility for ensuring proportional-fair effective capacity distribution and resource allocation among RAN slices, subject to the distinct quality of service (QoS) requirements of the uRLLC, eMBB and mMTC slices. Then, an efficient, hierarchical resource allocation framework is then proposed to solve the problem deterministically, whereby resource block assignment is first performed at the base station via a demand-oriented greedy algorithm, followed by power allocation using a bisection method at individual user equipment. Results show that the proposed scheme outperforms the baseline schemes with fairness and QoS provisioning performance gains of up to 44.3% and 19.17% respectively.

Analysis of Optical Camera Communications for Terminal Jiggle With Quality of Service Guarantees

Although Optical Camera Communications (OCC) has carved out a space in sixth-generation(6 G) communications, building a theoretical analysis model for OCC remains an open question. Hence, we propose the analytical models for OCC systematic evaluation with unique quality of service (QoS) requirements, and build a practice communication system to validate the effectiveness of our models. A three-dimension discrete-time Markov chain is modeled to characterize the jiggle of user terminal in actual OCC scenarios. Supporting the randomly-oriented receiver, the available maximum data rate in guaranteeing statistical QoS based on effective capacity theory is derived. Moreover, a receiver imaging model is built to represent the logical relations of optical parameters, which provides guidance for image demodulation. Finally, extensive field experiments are implemented to verify the reasonability of our theoretical OCC models.

Energy‐efficient machine type communication in HetNets under statistical QoS guarantees

AbstractThere has been an unprecedented rise in the Internet‐of‐Things (IoT) in the past decade. One of the underlying reasons for this exponential growth is that IoT allows for massive machine‐type communication (mMTC), which facilities machine‐to‐machine (M2M) communication with minimal human intervention. However, mMTC devices are characterized by resource and energy limitations, and thus require powerful and efficient power allocation methods that do not jeopardize quality‐of‐service (QoS) performance. In this work, a statistical QoS analysis of M2M communication in heterogeneous wireless networks is performed. We propose a communication mode selection (CMS) scheme that selects an uplink transmission link from the available candidate links based on pathloss criteria. The closed‐form expressions for the Effective Capacity and effective energy efficiency (Effective‐EE) of the M2M communication in the heterogeneous wireless network are derived and verified via simulations. The optimal fixed transmission rate that maximizes the Effective Capacity and Effective‐EE is also analytically analyzed. Furthermore, four scenarios are adopted to study the overall Effective Capacity and Effective‐EE of a two‐hop M2M communication link where the transmitter and access point operate under independent and identical QoS constraints. This article also investigates the impact of circuit power and the efficiency of the power amplifier on the achievable Effective‐EE of the communication link.

Proportionally fair load balancing with statistical quality of service provisioning for aerial base stations

AbstractAerial base stations (ABSs) seem promising to enhance the coverage and capacity of fifth‐generation and upcoming networks. With the flexible mobility of ABSs, they can be positioned in air to maximize the number of users served with a guaranteed quality of service (QoS). However, ABSs may be overloaded or underutilized given inefficient placement, and user association has not been well addressed. Hence, we propose a three‐dimensional ABS placement scheme with a delay‐QoS‐driven user association to balance loading among ABSs. First, a load balancing utility function is designed based on proportional fairness. Then, an optimization problem for joint ABS placement and user association is formulated to maximize the utility function subject to statistical delay QoS requirements and ABS collision avoidance constraints. To solve this problem, we introduce an efficient modified gray wolf optimizer for ABS placement with a greedy user association strategy. Simulation results demonstrate that the proposed scheme outperforms baselines in terms of load balancing and delay QoS provisioning.

Uplink Non-Orthogonal Multiple Access With Statistical Delay Requirement: Effective Capacity, Power Allocation, and α Fairness

The proliferation of delay-sensitive Internet-of-Things (IoT) applications has ushered in a need for the statistical delay quality-of-service (QoS) guarantee for the applications. In this paper, we first derive an upper bound for the queuing delay violation probability (UB-QDVP) in uplink non-orthogonal multiple access (NOMA) by applying stochastic network calculus (SNC) to the Mellin transforms of service processes. A closed-form asymptotic approximation of the UB-QDVP is developed by proving the asymptotic convergence of the Mellin transform and its finite-length truncations. Given the closed-form asymptotic UB-QDVP, we propose two power allocation schemes. The first scheme minimizes the transmit power of a NOMA user pair while guaranteeing the statistical delay QoS of the pair. The second maximizes the <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> -utility function of the effective capacity of the user pair, striking a balance between the energy efficiency and user fairness of uplink NOMA systems. Simulations validate the UB-QDVP and show the superiority of the proposed schemes to conventional power allocation schemes in terms of energy efficiency and fairness.

Buffer-Aided Relaying in NOMA-Based MTC Networks With Finite Blocklength and Statistical QoS Constraints

Machine-type communication (MTC) is one of the main enabling technologies to support various applications with diverse quality of service (QoS) requirements. Finite blocklength transmission has great potential in meeting the strict delay requirements of delay-sensitive MTC devices (MTCDs), while also causing loss of network capacity due to the decoding error probability. Aiming at this problem, we introduce uplink non-orthogonal multiple access (NOMA) and buffer-aided relaying to assist the finite blocklength transmission with delay requirements for improving the achievable effective capacity (EC), which is defined as the maximum short-packet constant arrival rate under specific statistical QoS constraints. To solve the EC maximization problem, we derive the closed-form expression of time allocation coefficient. Then we establish a concave lower bound of EC using successive convex approximation (SCA) for power allocation of MTCDs, and formulate a non-cooperative game based distributed power allocation algorithm for relay. Furthermore, a joint time and power allocation (JTPA) algorithm is proposed to implement joint resource allocation. Simulation results show that under finite blocklength and statistical QoS constraints, adopting buffer-aided relaying can improve EC by 41.82% compared with no-buffer relaying. Moreover, the achievable EC of JTPA algorithm is only 3.12% lower than that of exhaustive search while reducing complexity.

Dynamic Power Allocation for Uplink NOMA With Statistical Delay QoS Guarantee

Most existing optimization objectives considered in non-orthogonal multiple access (NOMA) power allocation schemes are non-delay-sensitive metrics. In order to apply NOMA to various Internet of Things scenarios, the delay must be considered. The effective capacity of users, which characterizes the capacity under specific expiration probabilities, can potentially be a performance metric of statistical delay quality of service (QoS). In this paper, we propose two novel dynamic power allocation schemes with statistical delay QoS guarantee in the uplink NOMA system with paired users. One of the schemes maximizes the sum effective capacity (SEC) of the strong and weak users, which is a non-convex nonlinear optimization problem and is solved by Lagrangian dual decomposition and successive convex approximation (SCA). The other one maximizes the effective energy efficiency (EEE) of uplink NOMA, which is a fractional optimization problem and is solved by integrating the Dinkelbach method, SCA, and Lagrangian dual decomposition. Numerical results show that the SEC and EEE can be significantly improved by the proposed schemes, compared to the existing NOMA and orthogonal multiple access power allocation schemes.

Secure Rate Control and Statistical QoS Provisioning for Cloud-Based IoT Networks

The Internet of Things (IoT) facilitates physical things to detect, interact, and execute activities on-demand, enabling a variety of applications such as smart homes and smart cities. However, it also creates many potential risks related to data security and privacy vulnerabilities on the physical layer of cloud-based Internet of Things (IoT) networks. These can include different types of physical attacks such as interference, eavesdropping, and jamming. As a result, quality-of-service (QoS) provisioning gets difficult for cloud-based IoT. This paper investigates the statistical QoS provisioning of a four-node cloud-based IoT network under security, reliability, and latency constraints by relying on the effective capacity model to offer enhanced QoS for IoT networks. Alice and Bob are legitimate nodes trying to communicate with secrecy in the considered scenario, while an eavesdropper Eve overhears their communication. Meanwhile, a friendly jammer, which emits artificial noise, is used to degrade the wiretap channel. By taking advantage of their multiple antennas, Alice implements transmit antenna selection, while Bob and Eve perform maximum-ratio combining. We further assume that Bob decodes the artificial noise perfectly and thus removes its contribution by implementing perfect successive interference cancellation. A closed-form expression for an alternative formulation of the outage probability, conditioned upon the successful transmission of a message, is obtained by considering adaptive rate allocation in an ON-OFF transmission. The data arriving at Alice’s buffer are modeled by considering four different Markov sources to describe different IoT traffic patterns. Then, the problem of secure throughput maximization is addressed through particle swarm optimization by considering the security, latency, and reliability constraints. Our results evidence the considerable improvements on the delay violation probability by increasing the number of antennas at Bob under strict buffer constraints.

Energy Efficiency Maximization for UAV-Assisted Emergency Communication Networks

Using unmanned aerial vehicles (UAVs) in emergency communications is a promising technology because of their flexible deployment, low cost, and high mobility. However, due to the limited energy of the onboard battery, the service duration of the UAV is greatly limited. In this paper, we study an emerging energy-efficient UAV emergency network, where a UAV works as an aerial base station to serve a group of users with different statistical quality-of-service (QoS) constraints in the downlink. In particular, the energy efficiency of the UAV is defined as the sum effective capacity of the downlink users divided by the energy consumption of the UAV, which includes the energy consumed by communication and the energy consumed by hovering. Then, we formulate an optimization problem to maximize the energy efficiency of the UAV by jointly optimizing the UAV’s altitude, downlink transmit power, and bandwidth allocation while meeting a statistical delay QoS requirement for each user. The formulated optimization problem is a nonlinear nonconvex optimization problem of fractional programming, which is difficult to solve. In order to deal with the nonconvex optimization problem, the following two steps are used. First, we transform the fractional objective function into a tractable subtractive function. Second, we decompose the original optimization problem into three subproblems, and then, we propose an efficient iterative algorithm to obtain the energy efficiency maximization value by using the Dinkelbach method, the block coordinate descent, and the successive convex optimization technique. Extensive simulation results show that our proposed algorithm has significant energy savings compared with a benchmark scheme.

Statistical QoS guarantees of a device‐to‐device link assisted by a full‐duplex relay

AbstractDevice‐to‐device (D2D) communication is a promising technique to enhance the spectral efficiency for 5G and beyond cellular networks. Traditionally, D2D communication was considered solely as communication directly between two closely‐located devices, without any support from the available network infrastructure; however, this understanding limits the advantages of D2D communication. Relay‐assisted D2D communication was later proposed to allow devices to exchange data and extend coverage via relay strategy for transmission distance extension and capacity improvements. This work aims to determine the statistical quality‐of‐service (QoS) guarantees of a D2D link assisted by a full‐duplex relay by employing a commonly used analytical tool, the effective capacity (EC). We provide a closed‐form expression for the EC of relay‐assisted D2D communication, in which both the transmitter and the relay devices operate under individual QoS constraints. We also provide an analysis of the impact of mode selection on the EC of relay‐assisted D2D. Additionally, for the mode selection, we propose a novel multiple features‐based mechanism by utilizing all the features of a wireless link. We further provide a closed‐form solution for the non‐convex calibration problem of the optimal weights for these underlying features. Finally, simulation results demonstrate how the quality of self‐interference cancellation techniques impacts the EC of the relay‐assisted D2D. The results also show that the performance of our proposed mode selection mechanism with optimal weights outperforms the traditional mode selection mechanism.

Statistical Delay and Error-Rate Bounded QoS Provisioning for SWIPT Over CF M-MIMO 6G Mobile Wireless Networks Using FBC

As a new and dominating type of time-sensitive traffic over 6G wireless networks, massive ultra-reliable and low latency communications (mURLLC) has attracted considerable research attention, while raising several new challenges, including massive connectivity, ultra-low latency, super-reliability, and high energy efficiency. Several promising 6G enablers, including statistical delay and error-rate bounded quality-of-service (QoS) provisioning, cell-free (CF) massive multi-input multi-output (m-MIMO), simultaneous wireless information and power transfer (SWIPT), etc., have been developed to support mURLLC. Specifically, CF m-MIMO can significantly enhance QoS performance of SWIPT by boosting data rate and energy efficiency. On the other hand, finite blocklength coding (FBC) has been proposed to support various massive access techniques while reducing access latency and guaranteeing stringent QoS. However, how to efficiently integrate SWIPT with CF m-MIMO using FBC for statistical delay and error-rate bounded QoS to support mURLLC has posed many new challenges not encountered before. To overcome these difficulties, in this paper we develop FBC based statistical delay and error-rate bounded QoS provisioning schemes over SWIPT-enabled CF m-MIMO 6G wireless networks. First, we establish SWIPT-enabled CF m-MIMO system models using FBC. Then, we optimize the tradeoffs between <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\epsilon$</tex-math></inline-formula> -effective capacity and harvested energy for our proposed statistical QoS provisioning. Finally, our simulated results validate and evaluate our developed schemes.

Optimal Resource Allocations for Statistical QoS Provisioning to Support mURLLC Over FBC-EH-Based 6G THz Wireless Nano-Networks

One of most important techniques for enabling the sixth-generation (6G) mobile wireless network lies in how to efficiently guarantee various stringent quality-of-service (QoS) performance-metrics to support the emerging massive Ultra-Reliable Low-Latency Communications (mURLLC) in 6G. Correspondingly, finite blocklength coding (FBC) has been developed as an effective technique to significantly improve various QoS indices for mURLLC through implementing short-packet communications. On the other hand, Terahertz (THz) band wireless nano-communications have been widely envisioned as a promising 6G technique to efficiently support utra-high data-rate (up to 1 Tbps). One of the major constraints over THz-band nano-networks is the severely limited energy that can be accessed by nano devices. Towards this end, various novel energy harvesting (EH) mechanisms have been proposed to remedy the energy scarcity problem. However, how to accurately characterize the relationships among THz wireless channels, energy consumption, and EH models for FBC based nano communications remains a challenging problem to support statistical delay and error-rate bounded QoS provisioning over FBC based 6G THz wireless nano-networks. To overcome these challenges, in this paper we propose optimal resource allocation policies to achieve the maximum ε-effective capacity in the THz band over FBC-EH-based nano-networks. Particularly, we establish nano-scale system models and characterize wireless channel models in the THz band using FBC. In order to support statistical delay and error-rate bounded QoS provisioning, we formulate and solve the ε-effective capacity maximization problem under several different EH constraints for our proposed schemes. Simulation results are included, which validate and evaluate our proposed schemes in the finite blocklength regime.

3D Location and Resource Allocation Optimization for UAV-Enabled Emergency Networks Under Statistical QoS Constraint

Unmanned aerial vehicles (UAVs) as aerial base stations have attracted great attention in emergency communication networks due to flexible deployment. With the popularization of smart devices, the demand for multimedia services is increasing in disaster relief. Therefore, it is very important to significantly improve throughput of unmanned aerial vehicle base station (UAV-BS) while ensuring quality-of-service (QoS) of multimedia traffic. In this paper, we consider a UAV-BS to serve a group of users in the downlink who have different statistical delay-bound QoS requirements in an emergency situation. We formulate a problem to maximize the sum statistical-QoS-guaranteed throughput (effective capacity) of all users by jointly optimizing the UAV's 3D location, power and bandwidth allocation under each user's statistical QoS requirement constraint. The formulated problem is a non-linear non-convex optimization problem, which is very difficult to solve. To this end, we propose an efficient iteration algorithm based on the block coordinate descent and successive convex optimization techniques to solve it. Specifically, we decouple the primary problem into three sub-problems, which can be approximated as easy-to-solve convex optimization problems. In each iteration, three sub-problems are alternately optimized. Finally, numerical simulation results prove the effectiveness of our proposed algorithm compared with benchmarks.

Joint RAN Slicing and Computation Offloading for Autonomous Vehicular Networks: A Learning-Assisted Hierarchical Approach

In this paper, a two-timescale radio access network (RAN) slicing and computing task offloading problem is investigated for a cloud-enabled autonomous vehicular network (C-AVN). We aim at jointly maximizing the communication and computing resource utilization with diverse quality-of-service (QoS) guarantee for autonomous driving tasks. Specifically, to capture the small-timescale network dynamics, a computing task scheduling problem is formulated as a stochastic optimization program, for maximizing the long-term network-wide computation load balancing with minimum task offloading variations. Due to the large problem size and unavailable network state transition probabilities, we employ cooperative multi-agent deep <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Q</i> -learning (MA-DQL) with fingerprint to solve the problem by learning the set of stationary task offloading policies with stabilized convergence. Given the task offloading decisions, we further study a RAN slicing problem in a large timescale, which is formulated as a convex optimization program. We focus on optimizing the radio resource slicing ratios among base stations, to maximize the aggregate network utility with statistical QoS provisioning for autonomous driving tasks. Based on the impact of radio resource slicing on computation load balancing, we propose a two-timescale hierarchical optimization framework to maximize both communication and computing resource utilization. Extensive simulation results are provided to demonstrate the effectiveness of the proposed framework in comparison with state-of-the-art schemes.

Caching and D2D assisted wireless emergency communications networks with statistical QoS provisioning

Along with natural disasters, the destruction of communication infrastructures leads to the congestion or failure of communication networks. Unmanned aerial vehicles (UAVs), which are with a high flexibility, can be employed as temporary base stations to establish emergency networks. To relieve the backhaul burden of UAVs, some imperative contents can be cached by terrestrial cache-enabled rescuers (CERs) and provide for victims with device-to-device (D2D) transmissions. To support the effectiveness and timeliness of emergency communication, the delay-bounded quality-of-service (QoS) requirement and network throughput are desired to be comprehensively considered, which imposes a new challenge for caching placement and CER deployment. In this paper, we focus on joint caching placement and CER deployment to maximize the effective capacity subject to delay-bounded QoS requirement. The overall non-convex problem is transformed into the caching placement and the CER deployment sub-problems. Then, we develop the QoS-aware caching placement scheme with fixed CER deployment density and obtain the QoS-aware CER deployment density with fixed caching placement. Based on the block-coordinate descent method, we also propose the joint caching placement and CER deployment scheme, which can not only effectively enhance average effective capacity but also guarantee the delay-bounded QoS requirement. Also, numerical simulations are conducted to show the performances of the proposed schemes.

On Delay-Aware Resource Control With Statistical QoS Provisioning By Dual Connectivity in Heterogeneous Aeronautical Network

In this paper, we explore the effect of dual connectivity (DC) on delay-aware resource control with statistical Quality of Service (QoS) provisioning in heterogeneous aeronautical networks. Firstly, the Software Defined Networking (SDN) controller is introduced to support the DC for aircraft by centralized management of different base stations. In light of the delay analysis of user traffic, the delay-aware resource control of SDN controller is established as a multi-objective stochastic optimization problem to guarantee the statistical QoS provisioning. Secondly, the multi-objective stochastic optimization problem is transformed into a weighted single-objective optimization and relaxed by the Lagrangian relaxation. Then, the Lyapunov optimization theory is utilized to solve the relaxed stochastic optimization for optimal resource control. Finally, the performance of resource control under DC mode is verified in two aeronautical scenarios.

Asymptotic Performance Analysis of NOMA Uplink Networks Under Statistical QoS Delay Constraints

In this article, we study the performance of an uplink non-orthogonal multiple access (NOMA) network under statistical quality of service (QoS) delay constraints, captured through each user's effective capacity (EC). We first propose novel closed-form expressions for the EC in a two-user NOMA network and show that in the high signal-to-noise ratio (SNR) region, the “strong” NOMA user, referred to as U <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> , has a limited EC, assuming the same delay constraint as the “weak” user, referred to as U1. We demonstrate that for the weak user U1, OMA and NOMA have comparable performance at low transmit SNRs, while NOMA outperforms OMA in terms of EC at high SNRs. On the other hand, for the strong user U <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> , NOMA achieves higher EC than OMA at small SNRs, while OMA becomes more beneficial at high SNRs. Furthermore, we show that at high transmit SNRs, irrespective of whether the application is delay tolerant, or not, the performance gains of NOMA over OMA for U <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> , and OMA over NOMA for U <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> remain unchanged. When the delay QoS of one user is fixed, the performance gap between NOMA and OMA in terms of total EC increases with decreasing statistical delay QoS constraints for the other user. Next, by introducing pairing, we show that NOMA with user-pairing outperforms OMA, in terms of total uplink EC. The best pairing strategies are given in the cases of four and six users NOMA, raising once again the importance of power allocation in the optimization of NOMA's performance.

Statistical QoS Aware for Wireless Powered Cooperative Communications in Internet of Things

This article unveils the importance of statistical quality of service (QoS) for resource allocation in a two-hop network. Particularly, an access point (AP) serves multiple IoT devices for information transfer with the assistance of the energy harvesting (EH) relaying. To explore the maximum constant data arrival metric, we aim to maximize the effective capacity (EC) under specified QoS requirements. Also, the statistical QoS inspired resource allocation policies are investigated for half/full duplex (HD/FD) modes, respectively, to jointly optimize power allocation and power splitting (PS) ratio. To solve the formulated problem, we first derive the closed-form solution of the optimal power allocation at the AP and the PS ratio. To gain more insights, we further derive the boundary conditions of optimal power allocation and PS ratio. Finally, numerical results are demonstrated to validate the theoretical derivations, which highlights the proposed scheme in terms of EC performance in comparison to the benchmark scheme.

A Random Compensation Scheme for 5G Slicing Under Statistical Delay-QoS Constraints

For the communication scenarios of heterogeneous arrivals in the fifth generation cellular networks, slicing is believed to be an effective way to provide quality-of-service (QoS) provisioning. However, the reports on an effective segmentation of resources for random and bursty arrival are rare. Relying on the bandwidth estimation and service design, we give a simple but effective scheme for the slicing of bandwidths named two-hole leaky bucket random service mechanism. The service in our scheme comprises two parts, the specific basic service and shared random compensation service. Accordingly, the mechanism of resource allocation is just like leaky bucket with two holes, one of which has a random leak rate. To guarantee the statistical QoS of heterogeneous traffic flows, effective bandwidth/capacity theory is introduced into the slicing scheme. By establishing function equations, we deduce the compensation probability of each slice, which is taken as the slicing adjustment factor. Simulation results prove that the random compensation scheme can satisfy the statistical QoS requirements of heterogeneous traffic flows. Although the scheme is proved to be effective against two slices, the proposed model is applicable to general multiple heterogeneous arrivals.

QoS Driven Task Offloading with Statistical Guarantee in Mobile Edge Computing

In mobile edge computing, popular mobile applications, such as augmented reality, usually offload their tasks to resource-rich edge servers. The user experience can be considerably affected when many mobile users compete for the limited communication and computation resources. The key technical challenge in task offloading is to guarantee the Quality of Service (QoS) for such applications. Existing work on task offloading focus on deterministic QoS guarantee, which means that tasks have to complete before the given deadline with 100%. However, it is impractical to impose a deterministic QoS guarantee for tasks due to the high dynamics of the wireless environment when offloading to edge servers. In this paper, we focus on task offloading with statistical QoS guarantee, which can further save more energy by loosing the QoS requirement. Specially, we first propose a statistical computation model and a statistical transmission model to quantify the correlation between the statistical QoS guarantee and task offloading strategy. Then, we formulate the task offloading problem as an mixed integer non-Linear programming problem. We propose an algorithm to provide the statistical QoS guarantee for tasks using convex optimization theory and Gibbs sampling method. Experiment results show that the proposed algorithm outperforms the three baselines.