Service Requests Research Articles

Microservice instances selection and load balancing in fog computing using deep reinforcement learning approach

Fog-native computing is an emerging paradigm that makes it possible to build flexible and scalable Internet of Things (IoT) applications using microservice architecture at the network edge. With this paradigm, IoT applications are decomposed into multiple fine-grained microservices, strategically deployed on various fog nodes to support a wide range of IoT scenarios, such as smart cities and smart farming. Nonetheless, the performance of these IoT applications is affected by their limited effectiveness in processing offloaded IoT requests originating from multiple IoT devices. Specifically, the requested IoT services are composed of multiple dependent microservice instances collectively referred to as a service plan (SP). Each SP comprises a series of tasks designed to be executed in a predefined order, with the objective of meeting heterogeneous Quality of Service (QoS) requirements (e.g., low service delays). Different from the cloud, selecting the appropriate service plan for each IoT request can be a challenging task in dynamic fog environments due to the dependency and decentralization of microservice instances, along with the instability of network conditions and service requests (i.e., change quickly over time). To deal with this challenge, we study the microservice instances selection problem for IoT applications deployed on fog platforms and propose a learning-based approach that employs Deep Reinforcement Learning (DRL) to compute the optimal service plans. The latter optimizes the delay of application requests while effectively balancing the load among microservice instances. In our selection process, we carefully address the plan-dependency to efficiently select valid service plans for every request by introducing two distinct approaches; an action masking approach and an adaptive action mapping approach. Additionally, we propose an improved experience replay to address delayed action effects and enhance our model training efficiency. A series of experiments were conducted to assess the performance of our Microservice Instances Selection Policy (MISP) approach. The results demonstrate that our model reduces the average failure rate by up to 65% and improves load balance by up to 45% on average when compared to the baseline algorithms.

Learning-Based Cloud Server Configuration for Energy Minimization Under Reliability Constraint

Cloud computing has attracted wide attention from both academia and industry, since it can provide flexible and on-demand hardware and software resources as services. Energy consumption of cloud servers is the main concern of cloud service providers since reducing energy consumption can bring them a lower operation cost (and hence a higher profit) and alleviate carbon footprints to the environment. Typically, the common power management techniques for enhancing energy efficiency would make cloud servers more vulnerable to soft errors and hence adversely impact the quality of services. Thus, reliability cannot be ignored in the design of methodologies for improving the energy efficiency of cloud servers. In this article, we aim to minimize the energy consumption of cloud servers under the soft-error reliability constraint by configuring the size and speed of servers. Specifically, we first derive the expected reliability based energy consumption of cloud servers to formulate the reliability-constrained energy minimization problem. We then leverage the reinforcement learning technique to obtain an optimal server configuration solution that maximizes system energy efficiency while maintaining the system reliability constraint. Finally, we perform extensive simulation experiments to analyze the relationship between system energy consumption and server configuration under varying arrival rates and execution requirements of service requests. Comparative experiments are also performed to validate the efficacy of the proposed learning-based server configuration scheme. Results show that compared to a benchmark method, the energy saved by the proposed scheme can reach up to 31.5%.

Reliable paths prediction with intelligent data plane monitoring enabled reinforcement learning in SD-IoT

Legacy routing with conventional distributed networking in the Internet-of-Things (IoT) networks needs to work on efficiently handling service requests, leading to compromised Quality of Service (QoS) for user demands. In this research, we introduce Reliable routing based on Reinforcement learning in SD-IoT Networks (RRSN), an intelligent routing technique leveraging Software-Defined Networking (SDN) in IoT networks. RRSN utilizes a hybrid mechanism that combines Machine Learning (ML) and Reinforcement Learning (RL) within SDN’s centralized control to optimize QoS-aware reliable routing. In addition, network telemetry is utilized for intelligent network monitoring in the data plane to get the underlying network’s status efficiently. The proposed approach consists of three main modules: a Support Vector Regression (SVR) machine learning algorithm to predict link reliability, a traffic classifier for QoS-based traffic classification, and a reliability-aware reinforcement learning algorithm to compute optimal routing paths for IoT sensors. SVR algorithm has a high prediction accuracy, is lightweight, less susceptible to noisy data, and its computational complexity is independent of the dimensions of the input space. RRSN leverages intelligent network monitoring with RL, global view, and centralized SDN control to compute and implement optimal routes in data plane switches efficiently. We conduct extensive Proof-Of-Concept (POC) experimental evaluations, comparing RRSN with state-of-the-art models, including POC experiments in real Internet topologies. The results demonstrate that RRSN outperforms existing schemes in network performance metrics such as throughput, jitter, packet loss ratio, and delay, showcasing its effectiveness in improved QoS for IoT networks.

Cross-domain resources optimization for hybrid edge computing networks: federated DRL approach

Due to the dynamic nature of service requests and the uneven distribution of services in the Internet of Vehicles (IoV), Multi-access Edge Computing (MEC) networks with pre-installed servers are often susceptible to insufficient computing power at certain times or in certain areas. In addition, Vehicular Users (VUs) need to share their observations for centralized neural network training, resulting in additional communication overhead. In this paper, we present a hybrid MEC server architecture, where fixed RoadSide Units (RSUs) and Mobile Edge Servers (MESs) cooperate to provide computation offloading services to VUs. We propose a distributed federated learning and Deep Reinforcement Learning (DRL) based algorithm, namely Federated Dueling Double Deep Q-Network (FD3QN), with the objective of minimizing the weighted sum of service latency and energy consumption. Horizontal federated learning is incorporated into the Dueling Double Deep Q-Network (D3QN) to allocate cross-domain resources after the offload decision process. A client-server framework with federated aggregation is used to maintain the global model. The proposed FD3QN algorithm can jointly optimize power, sub-band, and computational resources. Simulation results show that the proposed algorithm outperforms baselines in terms of system cost and exhibits better robustness in uncertain IoV environments.

Resource-aware fog service placement using deferred acceptance in edge computing

Fog computing aims at reducing network latency, bandwidth and processing delay by bringing computation resources closer to the data sources. Modern IoT applications, such as smart surveillance systems, remote health monitoring applications, ambient-aware applications etc., are time-critical and computationally intensive. For such applications, it is ideal to consider an intermediate layer of processing i.e a fog layer in addition to cloud. However, processing the workload of such IoT applications with an intermediate layer of fog nodes has several challenges. The significant challenges include the mobility of end-user nodes, dynamic patterns of workload generation leading to highly-variant resource requirements and sensitive quality of service (QOS) requirements. Hence a dynamic approach is required to precisely map the service requests from end-user devices to a suitable fog node. The optimality of a fog node for service placement depends on several factors, including location, resource utilization rates such as CPU, Memory and Disk utilization % and energy consumption. Several meta-heuristic techniques and evolutionary algorithms have been proposed in the past for optimal service placement among fog nodes. This paper investigates the applicability of a game theory-based approach called Deferred acceptance (DA) for the same. The DA algorithm, originally designed as a stable matching mechanism for the marriage market is adapted for service placement problems in fog-based IoT systems. The effectiveness of optimized service placement through the DA approach is validated experimentally. The experiment is carried out by creating a test bed that mimics a fog computing-based intelligent traffic management application. The proposed approach's performance is evaluated through parameters such as the startup time for the DA approach to produce outcomes, total execution time and handshake latency. The numerical results of the DA approach are compared with those of a simple scheduling algorithm ( FIFO) and a basic genetic algorithm-based approach. The DA approach appears to perform on par with the genetic algorithm in terms of start-up time, but exceeds the genetic algorithm with respect to stability of the outcomes produced.

An improved resource allocation method for mapping service function chains based on A3C

AbstractNetwork function virtualization (NFV) technology deploys network functions as software functions on a generalised hardware platform and provides customised network services in the form of service function chain (SFC), which improves the flexibility and scalability of network services and reduces network service costs. However, irrational resource allocation during service function chain mapping will cause problems such as low resource utilisation, long service request processing time and low mapping rate. To address the unreasonable problem of service mapping resource allocation, an improved service function chain mapping resource allocation method (SA3C) based on the Asynchronous advantageous action evaluation algorithm (A3C) is proposed. This study proposes an SFC mapping model and a mathematical model for joint allocation, which modeled the minimization of processing time as a Markov process. The main network was trained and multiple sub‐networks were generated in parallel using the ternary and deep reinforcement learning algorithm A3C, with the goal of identifying the optimal resource allocation strategy. The experimental simulation results show that compared with the Actor‐Critic (AC) and Policy Gradient (PG) methods, SA3C algorithm can improve the resource utilisation by 9.85%, reduce the total processing time by 10.72%, and improve the mapping rate by 6.72%, by reasonably allocating node computational resources and link bandwidth communication resources.

Balancing resources for dynamic vehicle routing with stochastic customer requests

We consider a service provider performing pre-planned service for initially known customers with a fleet of vehicles, e.g., parcel delivery. During execution, new dynamic service requests occur, e.g., for parcel pickup. The goal of the service provider is to serve as many dynamic requests as possible while ensuring service of all initial customers. The allocation of initial services impacts the potential of serving dynamic requests. An allocation aiming on a time-efficient initial routing leads to minimal overall workload regarding the initial solution but may congest some vehicles that are unable to serve additional requests along their routes. An even workload division is less efficient but grants all vehicles flexibility for additional services. In this paper, we investigate the balance between efficiency and flexibility. For the initial customers, we modify a routing algorithm to allow a shift between efficient initial routing and evenly balanced workloads. For effective dynamic decision making with respect to the dynamic requests, we present value function approximations with different feature sets capturing vehicle workload in different levels of detail. We show that sacrificing some initial routing efficiency in favor of a balanced vehicle workload is a key factor for a flexible integration of later customer requests that leads to an average improvement of 10.75%. Further, we show when explicitly depicting heterogeneity in the vehicle workload by features of the value function approximation provides benefits and that the best choice of features leads to an average improvement of 5.71% compared to the worst feature choice.

Be careful with the use of experts

Students with disabilities often request auxiliary aids and services and academic modifications. Colleges and universities may grant these requests, but if they do not, the institutions may respond by demanding written documentation and/or expert reports. However, this may result in unnecessary, time‐consuming, and costly litigation. Here are some suggestions to avoid lawsuits on these issues.

Congestion control method for overloaded service of smart substation under high concurrent users

Overload service in the communication network of smart substation will cause congestion, resulting in low overload service throughput, high congestion rate and long congestion control time in the average smart substation. A congestion control method for overloaded services in smart substations with high concurrent users is proposed. According to the characteristics of overload service request of smart substation, the mathematical model of the algorithm is defined by describing the overload service request of smart substation on the basis of network topology model. Combined with the wavelength rotation strategy, the congestion rate of overloaded services in smart substations is reduced, and the throughput rate of overloaded services in smart substations is improved. Considering the factors of high concurrent users, by judging and feeding back the congestion of the overloaded services of smart substations, the congestion control of overloaded services of smart substations under high concurrent users is realized. The experimental results show that the proposed method has better effect and scalability in the congestion control of the overloaded service of the smart substation, and can effectively shorten the congestion control time of the overloaded service of the smart substation.

Patient Reported Outcome Measurement (PROM) under real-life conditions of non-curable cancer outpatients with the Integrated Palliative Outcome Scale (IPOS) and NCCN-Distress Thermometer – A mixed methods study

ObjectiveProspective cohort study to test the real-life feasibility of longitudinal patient-reported outcome measurement PROM (Integrated Palliative Outcome Scale IPOS, and NCCN Distress Thermometer DT) required for outpatients with non-curable lung or prostate cancer in comprehensive cancer centers. MethodsAssessment with paper-based IPOS and DT was observed for 15 months. We analyzed response to patients' distress (requests for supportive and palliative services) following PROM. Focus groups to comprehensively explore the user experience of patients, informal caregivers and health care professionals (HCP) supplemented the analysis. ResultsNinety-seven percent (125/129) of the patients received a questionnaire once, but quarterly assessment as recommended by certification committees was achieved only in 50% and 31% of prostate and lung cancer patients. Although both instruments were well accepted, only IPOS showed a high content validity, because some patients had difficulties in understanding the DT. Patients felt comfortable with completing the PROM, and HCP found PROM helped to structure the patient encounter. Due to organizational deficiencies in the handling of the instruments and operationalization of reactions to identified distress, the referrals to supportive and palliative services were rare. ConclusionTo facilitate consequences from PROM it should be a standardized intervention rather than assessment alone. InnovationThe patient perspective improves the implementation of PROM under real-life clinical conditions.

Securing Service Instantiation on Next-generation Networks

The Next Generation of Software Defined Networks (NG-SDN) enables a whole new set of possibilities for innovation in the data plane (e.g., computing, monitoring, load-balancing). In parallel, we have been witnessing the increasing adoption of virtualized services running in light but efficient containers, which brings forth the capability to flexibly deploy services at the network edge, while providing dynamic scaling and management. As a result, operators have tap in a lot of computational real-estate as part of the adoption of telco cloud concepts, as well as to support the foreseen edge and fog computing scenarios. However, exposing the infrastructure to third parties and realizing complex services over a multi-stakeholder environment raises challenges at different levels (e.g., security, reliability, SLA guarantees). Reconfiguring the data plane for flow monitoring and handling service requests directly on the data plane could address these challenges to support the joint communication and computation vision. This is where this paper contributes by proposing a secure and reliable system for dynamic instantiation of third-party services. A proof-of-concept prototype was developed using P4 and Kubernetes showcasing the feasibility of the proposed approach.

An ADO‐OFDM with integrated precoding, companding and optimized power allocation methods for high‐speed data transmission in visible light communication

AbstractVisible light communications (VLC) has received a lot of attention in recent studies because of its benefits over radio‐frequency (RF) communications. It is a short‐range optical wireless communication system that uses light‐emitting diodes (LEDs) as transmitters. Optical orthogonal frequency division multiplexing (OFDM) is an auspicious technology for VLC high‐speed data transfer. The use of OFDM in a VLC system raises the system's peak‐to‐average power ratio (PAPR). The intrinsic non‐linearity of LED is a key concern in an asymmetrically clipped DC‐biased optical OFDM (ADO‐OFDM) system due to its high PAPR. Also, conventional ADO‐OFDM modulation scheme cannot be used for accommodating different demands of services in downlink multiple access due to the restriction of direct current biased optical OFDM (DCO‐OFDM) and asymmetrically clipped optical (ACO‐OFDM) transmission on odd and even subcarriers. To tackle this issue, a modified ADO‐OFDM (MADO‐OFDM) is proposed that adjusts the numbers of subcarriers required for the transmission of ACO‐OFDM and DCO‐OFDM adaptively based on the requests of services in downlink multiple access. Also, the proposed MADO‐OFDM is integrated with a discrete Hartley Matrix transform (DisHMT) precoder and Generalized Piecewise Linear Compander (GPLD) to provide high‐speed data transmission with less PAPR. In addition, the power is allocated to the proposed MADO‐OFDM system optimally by maximizing the channel capacity based on the Aquila optimizer algorithm. The simulation results reveal that the suggested system's PAPR is reduced by 2.4 dB and 0.8 dB, respectively, compared to conventional ADO and hybrid ADO‐OFDM. It also confirms that the suggested generalized PLC can greatly increase BER without affecting the PAPR performance.

Cross-Modal Stream Transmission: Architecture, Strategy, and Technology

Since the multi-modal services, which elaborately integrate audio, video, and haptic streams, are able to substantially improve the users' immersive experience, they are gradually becoming the mainstream applications. However, the existing solutions fail to simultaneously satisfy the diverse transmission requests of multi-modal services in terms of lower latency, higher reliability, and higher throughput, especially in the resource-constrained and dynamic environment. To circumvent this dilemma, this work constructs a cross-modal stream transmission architecture by exploring the intra-modal redundancy and the inter-modal correlation. Specifically, we propose an adaptive stream scheduling strategy, which can not only substantially decrease the stream traffics, but also dramatically reduce the impact of the channel uncertainty and the haptic signals' stochastic arrival on the delay jitter and reliability. Moreover, through prioritizing the resource provision of haptic signals, we design a joint uplink and downlink resource allocation scheme based on the prediction model. In particular, the transmitter sends the predicted haptic signals via the allocated resource blocks in advance according to the optimal window size, so as to offset the latency and remain the symmetry during the bilateral haptic transmission. Meanwhile, we develop an audio and video stream transmission scheme in a hierarchical and reusing structure by integrating the power-domain NOMA with LMDC-FEC, which fully utilizes the remaining limited resources to maximize the robustness of audio-video transmission.

Lightweight Imitation Learning for Real-Time Cooperative Service Migration

Due to the revolution of communication technology, the rapidly increasing number of mobile devices in edge networks generates various real-time service requests, requiring a considerable volume of heterogeneous resources all the time. However, edge devices with limited resources cannot afford substantial learning cost, while migrating services requires heterogeneous resources, especially for dynamic networks. To address these issues, we first establish a cooperative service migration framework and formulate a bi-objective optimization problem to optimize service performance and cost. By analyzing the optimal migration ratio of service cooperative migration, we propose an offline expert policy based on global states to provide optimal expert demonstrations. To realize real-time service migration based on observable states, we design a lightweight online agent policy to imitate expert demonstrations and leverage meta update to accelerate the model transfer. Experimental results show that our algorithm is exceptional in training cost and accuracy, and has significant superiors in multiple metrics such as the service latency and payment under different workloads, compared to other representative algorithms.

Efficient service reconfiguration with partial virtual network function migration

Network Function Virtualization (NFV) decouples network functions from dedicated hardware devices into Virtual Network Functions (VNFs). These VNFs are chained in order as a Service Function Chain (SFC) to provision flexible and efficient services. When service requests dynamically increase, the intensive workloads often lead to node overloads and further impact the Quality of Service (QoS). Existing works address this problem by migrating VNFs from overload nodes to other low-load nodes, known as VNF migration. However, when a VNF is shared by multiple SFCs, migrating the VNF will change the mapping relationships between these SFCs and the physical network (nodes and links). That may make some SFCs traverse more links and increase their propagation latency. That violates the demand of users for low-latency services. In this paper, to minimize the impact of VNF migration on SFC latency, we propose partial VNF migration. It migrates only partial VNFs within these SFCs to minimize the overall SFC latency while reducing migration costs. As such, we leverage partial VNF migration for efficient latency minimization with the formulation of an integer linear programming (ILP) model. Given the NP-hard nature of the problem, we propose a dynamic latency-aware partial VNF migration algorithm to reduce node overloads and minimize SFC latency. Evaluation indicates that the proposed approach has 12.7%–21.8% lower average SFC latency and 12.5%–48.5% less migration cost than state-of-the-art VNF migration algorithms. And it demonstrates about 90% shorter execution time with similar minimization performance, compared to other SFC reconfiguration algorithms.

The stochastic share-a-ride problem with electric vehicles and customer priorities

We introduce a stochastic share-a-ride problem in which a fleet of electric vehicles (EV) in a ride-hailing system are dynamically dispatched to serve passenger and parcel orders in a shared manner. We assume uncertain demands of both passenger and parcel orders and consider that passenger orders have priority over parcel orders. Passengers must be transported directly from their origins to destinations, while parcels can share a vehicle with other orders. The operator of the ride-hailing platform needs to decide whether to accept a newly arrived service request, how to assign orders to vehicles, and how to route and charge the EVs. To develop dynamic policies for the problem, we formulate the problem as a Markov decision process (MDP) and propose a reinforcement learning (RL) approach to solve the problem. We develop action-space restriction and state-space aggregation schemes to facilitate the implementation of the RL algorithm. We also present two rolling horizon heuristic methods to develop dynamic policies for our problem. We conduct computational experiments based on real-world taxi data from New York City. The computational results show that our RL policies perform better than the three benchmark policies in terms of serving more orders and collecting more rewards. Our RL policies are able to make high-quality decisions more efficiently when compared with the rolling horizon policies.

Implementation Of Public Service Digitization Policy In Gubeng Urban Village, Gubeng Sub-District Surabaya City (Study Of Surabaya Single Window (Ssw) Alfa Imlementation In Providing Public Services)

Surabaya Single Windows (SSW) Alfa is an innovation program for licensing and non-licensing services from the Surabaya City Government. Surabaya Single Windows Alfa is a development application from a previous application called Surabaya Single Windows which was launched in 2013. With the SSW Alfa application, residents of the city of Surabaya can process service requests online. Gubeng Village consistently serves residents by using the digitalization system provided by the Surabaya City Government. The aim of this research is to describe the implementation of the Surabaya Single Windows Alfa digitalization service program in Gubeng Village, Gubeng District, Surabaya City based on the theory of Successful Program Implementation according to George Edward III which consists of Communication, Disposition, Resources and Bureaucratic Structure. The method used in this research is descriptive qualitative by collecting observation and interview data. The research results show that the Surabaya Single Windows Alfa program has been running well. However, in its implementation there are still several obstacles that hinder the implementation of the program. The inhibiting factors found in this research are the need for equal understanding of the application of Surabaya Single Windows Alfa for human resources in Gubeng Village and the lack of socialization to the community regarding the Surabaya Single Windows Alfa program. This results in many people still not understanding the terms or documents required for the application.

Service Function Chain Deployment Algorithm Based on Deep Reinforcement Learning in Space–Air–Ground Integrated Network

SAGIN is formed by the fusion of ground networks and aircraft networks. It breaks through the limitation of communication, which cannot cover the whole world, bringing new opportunities for network communication in remote areas. However, many heterogeneous devices in SAGIN pose significant challenges in terms of end-to-end resource management, and the limited regional heterogeneous resources also threaten the QoS for users. In this regard, this paper proposes a hierarchical resource management structure for SAGIN, named SAGIN-MEC, based on a SDN, NFV, and MEC, aiming to facilitate the systematic management of heterogeneous network resources. Furthermore, to minimize the operator deployment costs while ensuring the QoS, this paper formulates a resource scheduling optimization model tailored to SAGIN scenarios to minimize energy consumption. Additionally, we propose a deployment algorithm, named DRL-G, which is based on heuristics and DRL, aiming to allocate heterogeneous network resources within SAGIN effectively. Experimental results showed that SAGIN-MEC can reduce the end-to-end delay by 6–15 ms compared to the terrestrial edge network, and compared to other algorithms, the DRL-G algorithm can improve the service request reception rate by up to 20%. In terms of energy consumption, it reduces the average energy consumption by 4.4% compared to the PG algorithm.

SLA-ORECS: an SLA-oriented framework for reallocating resources in edge-cloud systems

The emergence of the Fifth Generation (5G) era has ushered in a new era of diverse business scenarios, primarily characterized by data-intensive and latency-sensitive applications. Edge computing technology integrates the information services environment with cloud computing capabilities at the edge of the network. However, the evolving landscape of business models necessitates a unified edge architecture capable of accommodating diverse requirements, posing substantial challenges for service providers in meeting Service-Level Agreements (SLAs).In response to these challenges, we introduce SLA-ORECS. This innovative framework dynamically allocates dedicated and shared resources within the edge-cloud system to cater to service requests with varying SLAs, thereby facilitating performance isolation. Furthermore, we have developed an optimization algorithm to enhance the efficiency of SLA assurance during request dispatch.The evaluation of SLA-ORECS highlights its noteworthy performance improvements, particularly in terms of system throughput and average time consumption.

Analisis Kualitas Layanan Teknologi Informasi pada Domain Service Operation dengan Pendekatan Framework ITIL V.3 (Studi Kasus: Website Kampus Merdeka)

The Independent Campus programme, which allows students to take courses outside their programme of study and participate in activities outside the university, has experienced rapid growth. However, this growth brings a number of challenges, such as increased data volume, high service demands, and IT infrastructure complexity. The performance and responsiveness of IT services is also a concern, given users' expectations for fast performance. Effective customer support is also required to ensure a satisfactory user experience. To address these issues, an analysis of information technology (IT) management using the ITIL V3 framework in the Service Operation domain was conducted. The results of the analysis show that incident management, service requests, problems, access, and service operations can be improved through the implementation of ITIL. It helps improve operational efficiency, reduce the impact of incidents and problems, accelerate request fulfilment, maintain access security, and improve the quality and availability of IT services. The implementation of ITIL V3 is an important step in supporting the success of the Kampus Merdeka Programme in providing better access to education for students in Indonesia. Thus, the implementation of ITIL V3 is an important step in supporting the success of the Merdeka Campus Programme in providing better access to education for students in Indonesia.