Service Requests Research Articles

SD-SRF: An Intelligent Service Deployment Scheme for Serverless-operated Cloud-Edge Computing in 6G Networks

With the development of serverless computing, developers can implement and deploy business applications as a combination of stateless functions. Although originally proposed for cloud computing, serverless computing is gradually applied to cloud-edge systems for service deployment to provide users with high-quality, low-latency services. However, optimized service deployment in 6G networks is a very challenging issue because of the vast number of deployable devices in the network, and its permutations are highly exponential. In this paper, we propose optimized service deployment schemes for online and offline, respectively, to minimize the overall latency at a lower cost. (1) First, a SD-SRF algorithm based on the greedy algorithm is proposed to optimize the service deployment for a multi-layer edge network, which consists of two phases: SR and SF. (a) Services are deployed in the nearest ancestor devices in the routing tree of all such service requests with the least cost of deployment. (b) When the deployment cost of moving some service replicas to devices in the lower layer is less than the benefit, the service will fall. (2) However, the offline algorithm relies on the availability of prior information heavily, such as request arrival pattern and number, which is difficult to obtain. Therefore, this paper proposes a PPO-MSD algorithm for optimal deployment online, where a Markov decision process (MDP) is modeled. Extensive simulation results show that PPO-MSD outperforms existing algorithms in terms of overall delay and utility, and its performance is close to the optimal ones obtained by SD-SRF, with the SD-SRF and PPO-MSD algorithms reducing the delay on average by 32.40% and 9.91%.

AI/ML for beyond 5G systems: Concepts, technology enablers & solutions

5G brought an evolution on the network architecture employing the service-based paradigm, enabling flexibility in realizing customized services across different technology domains. Such paradigm gives rise to the adoption of analytics and Artificial Intelligence/Machine Learning (AI/ML) in mobile communications with the ease of collecting various measurements related to end-users and the network, which can be exposed towards consumers, including 3rd party applications. AI/ML may influence network planning and optimization considering the service life-cycle and introduce new operations provision, paving the way towards 6G. This article provides a survey on AI/ML considering the business, the fundamentals and algorithms across the radio, control, and management planes. It sheds light on the key technologies that assist the adoption of AI/ML in 3rd Generation Partnership Project (3GPP) networks considering service request, reporting, data collection and distribution and it overviews the main AI/ML algorithms characterizing them into user-centric and network-centric. Finally, it explores the main standardization and open source activities on AI/ML, highlighting the lessons learned and the further challenges that still need to be addressed to reap the benefits of AI/ML in automation for beyond 5G/6G mobile systems.

A-174 More Timely Patient Care Amidst Healthcare Staffing Shortages, Reducing Blood Specimen Tube Barcode Errors for Continuous Flow in an Automated Laboratory System

Abstract Background The Core Laboratory at Henry Ford Hospital utilizes total laboratory automation to support chemistry, hematology and coagulation analyzers, processing approximately 10 000 specimens daily. Testing and reporting delays can occur when the system encounters a specimen tube barcode error. Specimens will stop moving and causes approximately a 2-minute per error production pause while the error is resolved. This induces congestion for all other specimens in line behind the error. The seemingly trivial minutes of congestion leads to a domino effect, resulting in reduced line productivity, a temporary limit of testing capacity and prolonged TATs. The laboratory receives specimen tubes with labels generated from over 600 printers. The system encounters 200–250 errors daily associated with barcode read failures of various types. Errors account for an estimated loss of ∼320 h of staff productivity per month. Methods Automation line error files, manually recorded data from lab staff, observations of automation line errors occurring in real time, data from a printer maintenance blitz and barcode printer service requests were used in root cause analysis. Three progressive Kaizens events were organized in 2022 to induce rapid process change through focused chartering of events and actions. A probing study designed to induce controlled defects and stoppages helped recognize where congestion on the line was occurring. Simulation of barcode application errors allowed an understanding of the impact of label application. Staff and line productivity loss analysis predicted the potential opportunity of error reduction. Results Fifty-five percent of the barcode errors were caused by improper label application and 45% were poor print quality of the barcode on the label. Of the label application defects, 55% were caused by the label being placed upside-down, of which 34% were caused by the label format used by our Emergency Department. Print quality issues such as faded or pitted printing labels accounted for 45% of errors. The printer preventive maintenance blitz successfully reduced print quality errors by 30%. Converting to a more robust printer in two high-volume areas resulted in zero print quality errors over three months. Barcode label format changes were 100% effective in eliminating upside-down as a root cause. Conclusion Elimination of barcode line errors can recover 2.0 FTEs in three divisions per month, while increasing automation line productivity and a cost approximately$150 000 per year in work delays and unnecessary rework. The Kaizen approach to problem-solving allowed for rapid brainstorming amongst multiple teams. Altered label format allowed built-in engineering control by mistake-proofing the process and making label positioning irrelevant. Identification of areas where high volumes of labels were being printed and replacing those printers with more robust printers reduced service calls and eliminated printer causal factors since these printers require less hands-on maintenance. Finally, instituting preventative label printer maintenance and total quality management reduces or prevents errors associated with print quality. Sustaining mechanisms include continued real-time data documentation and communication of defects, collaboration with colleagues in Nursing for further root cause analysis of barcode application defects.

Intelligent intrusion detection framework for multi-clouds – IoT environment using swarm-based deep learning classifier

In the current era, a tremendous volume of data has been generated by using web technologies. The association between different devices and services have also been explored to wisely and widely use recent technologies. Due to the restriction in the available resources, the chance of security violation is increasing highly on the constrained devices. IoT backend with the multi-cloud infrastructure to extend the public services in terms of better scalability and reliability. Several users might access the multi-cloud resources that lead to data threats while handling user requests for IoT services. It poses a new challenge in proposing new functional elements and security schemes. This paper introduces an intelligent Intrusion Detection Framework (IDF) to detect network and application-based attacks. The proposed framework has three phases: data pre-processing, feature selection and classification. Initially, the collected datasets are pre-processed using Integer- Grading Normalization (I-GN) technique that ensures a fair-scaled data transformation process. Secondly, Opposition-based Learning- Rat Inspired Optimizer (OBL-RIO) is designed for the feature selection phase. The progressive nature of rats chooses the significant features. The fittest value ensures the stability of the features from OBL-RIO. Finally, a 2D-Array-based Convolutional Neural Network (2D-ACNN) is proposed as the binary class classifier. The input features are preserved in a 2D-array model to perform on the complex layers. It detects normal (or) abnormal traffic. The proposed framework is trained and tested on the Netflow-based datasets. The proposed framework yields 95.20% accuracy, 2.5% false positive rate and 97.24% detection rate.

REVIEW OF SOLUTIONS TO THE PROBLEM OF RESOURCE ALLOCATION IN FOG COMPUTING

Despite the high popularity of cloud computing, they are not recommended for use in applications and systems that are critical to network delays. Therefore, given the increasing volumes of data circulating over global networks, the concept of fog computing has become very relevant, as it allows to significantly offload cloud services, while minimizing latency and expanding computing capabilities of cloud technologies. As an intermediate layer between cloud and end user, fog computing improves network performance by taking on some of the load. The efficiency of fog computing as well as efficiency of any computer network, directly depends on the efficiency of resource allocation for service requests. Given this fact and taking into account the mobility, heterogeneity and dynamic nature of fog computing, there is an urgent challenge of organizing the distribution of resources in the fog to provide high quality user service. This review provides a full and comprehensive view of the available solutions to the problem of resource allocation in the fog. The article presents works classified with respect to quality of service metrics, policy types and classes of resource allocation algorithms. Approaches to resource management in fog computing for Internet of things, that is critical to delays. Analysis of results presented in the work overview with research and practical nature, made it possible to formulate the significance of solving this problem, to identify key challenges in the development of approaches to fog resource allocation and key metrics for their effeiciancy and performance evaluation. The conclusions obtained in the present study not only testify to the relevance and importance of the resource allocation problem in fog computing, but also allows to determine key factors that must be taken into account when solving it.

Evaluating MotorCycleApp: A Mobile Application Mechanic Finder for Repair and Maintenance Servicing

The remarkable surge in demand for motorcycle repair and maintenance services within the motorcycle industry can be attributed to the growing number of motorcycles in the Philippines. This paper presents the development of the MotorCyclepp mobile application, designed to facilitate the finding of motorcycle mechanics in Metro Cebu, Philippines. With this app, riders can effortlessly locate and choose from a list of available mechanics within their vicinity and send service requests accordingly. Simultaneously, mechanics can conveniently review the received requests and decide whether to accept or decline them. Once a request is accepted, the service begins, and upon completion, both parties can conclude their transactions and provide feedback messages. The Input-Process-Output (IPO) model was employed as the system’s methodology. The user interface (UI) design was created using Unified Modeling Language (UML), such as a use case diagram, sequence diagram, and class diagram. The evaluation procedures utilized the ISO 9126 model, which examines five quality characteristics: functionality, reliability, usability, efficiency, and portability, for data analysis. The results revealed that the app is unique and interesting but requires further improvements. The significance of this research to the body of literature and the industry will provide future researchers with a valuable reference for advancing mechanic finder app innovations. Keywords: finder, information technology, ISO 9126, mobile application.

Efficient Decentralized Multi-agent Learning in Asymmetric Bipartite Queueing Systems

New Algorithm Enables Efficient Decentralized Learning in Bipartite Queueing Systems Bipartite queueing systems, where agents with individual job queues request service from a pool of heterogeneous servers, are standard models for service applications like data networks and call centers. Traditionally, a central controller schedules agent requests with full knowledge of system parameters. However, emerging applications require decentralized operation without this central coordination or complete system information. This presents challenges as agents lack the global knowledge needed to efficiently route jobs. Recent research into efficient decentralized learning algorithms for such systems faces limitations in nonoptimal throughput, demanding computations, or degrading efficiency with exponential queue growth. In contrast, this paper introduces an algorithm that enables queues to efficiently learn decentralized scheduling policies while ensuring throughput optimality. The approach is computationally lightweight, achieving queue length bounds that scale polynomially rather than exponentially in system size. Experiments demonstrate faster convergence and robustness of our algorithm compared with prior decentralized algorithms.

Navigating the contradiction: balancing patient care and caregiver protection. From heroes to victims

The COVID emergency has accelerated professional and organizational transformations, prompting a re-signification of activity systems, routines, professional visions, concrete daily operations. An unforeseen scenario emerges, highlighting elements of uncertainty, fatigue, and discomfort, linked, on the one hand, to the challenge raised towards the professional identities of the various players, called to deal with the new organizational constraints, to reposition themselves in changing contexts. On the other hand, the challenge refers to the possibility to achieve a good balance between offering services aimed at the promotion and protection of health and, at the same time, to guarantee working safety and security conditions, in increasingly complex contexts in which tensions and contradictions coexist with reduction of resources and requests for more effective services.
 At risk is the possibility to cope with increasing situations of social conflicts (i.e. the no vax manifestations) and events such as those related to the aggressiveness of patients, the verbal and often physical aggression against the health professionals, exposed to the temptation to abandon work and devote oneself to something else. Tackling with patients taken in charge by the Services and with characteristics of aggressive behavior, decidedly above the sustainability thresholds (death threats; screams and insults; raids on the service; stalking; shadowing of operators, ... with situations of requesting emergency intervention by the police, which could only be limited to a light intervention in the absence of an explicit complaint against the person), generates understandable fears and dynamics of avoidance/expulsion. These are, more and more (even though not exclusively) at the basis of resignations and retirement from work. This is in evident contrast with the mission of the health service and therefore with the identification of personnel with the aim of taking care of every user with a need.
 Hence a situation of impasse (disenchantment/impotence/give up/avoidance), having to deal with balancing the threshold of the limit(boundary) and the limit(boundary) of the threshold, defining conditions of survival, of joint elaboration, of collective action agreed. The possibility of conceiving oneself as an emancipatory limit(boundary), avoiding fantasies of ‘expulsive killerage’ and ‘regulatory stiffening’, relies on a collective system alliance, capable of considering both realistic fears with respect to personal safety to be protected, and the elaboration of one's own defensive dynamics in the face of exposure to external aggression.
 At stake is the lacerating dilemma between the identification with a service that must take charge of the needs (whatever they may be) of a user/patient and, at the same time, with the need to protect one's own and others' (other patients) safety conditions to be able to fulfill the professional task to which one is called.

Operating performance of a Joule-Brayton pumped thermal energy storage system integrated with a concentrated solar power plant

The expected performance of an innovative Pumped Thermal Energy Storage (PTES) system based on a closed-loop Brayton-Joule cycle and integrated with a Concentrated Solar Power (CSP) plant are analysed in this study. The integrated PTES–CSP plant includes five machines (two compressors and three turbines), a central receiver tower system, three water coolers and three Thermal Energy Storage (TES) tanks, while argon and granite pebbles are chosen as working fluid and storage media, respectively. A sizing of the main components of the integrated plant has been firstly carried out for the design of an integrated PTES-CSP plant with a nominal net power of 5 MW and a nominal storage capacity of 6 equivalent hours of operation. Specific mathematical models have been developed in MATLAB-Simulink to simulate the PTES and CSP subsystem in different operating conditions, and to evaluate the thermocline profile evolution within the three storage tanks during/charging and discharging processes. A control strategy has finally been developed to determine the operating modes of the plant based on the grid service request, the solar availability, and the TES levels. The performance of the system during a summer and a winter day have been analysed considering the integration of the PTES subsystem in the Italian energy market for arbitrage. Results have demonstrated the technical feasibility of the hybridization of a PTES system with a CSP plant and the ability of the integrated system to participate to energy arbitrage, although a lower exergy roundtrip efficiency (about 54 %) has been observed with respect to the sole PTES system (about 60 %).

A novel hierarchical edge-based architecture for service oriented IoT

IoT (Internet of Things) is becoming increasingly prevalent in everyday life, with many commercialized IoT platforms available for use. In this paper, we propose a novel hierarchical IoT platform under a single administrating entity to provide scalability to an edge-based service-oriented IoT platform. To enable communication and resource sharing between edges while preserving the privacy benefit of the edge-based platform, a new type of service, called super service is introduced. And the scheduling problem of service requests to devices and a proposed solution are presented. To evaluate the proposed platform, a simulation framework is developed. Through a smart campus test-bed and extensive experiments with the simulation framework, the viability of the proposed platform is demonstrated.

Security Measures Applied on Digital Banking Towards Service Improvement Proposal

The main objective of this study is to assess the security measures on digital banking as a basis for improving services. The researcher used a descriptive method of research, employed with the used of a standard questionnaire. Descriptive research design involves gathering data that seeks to describe events and then organizing, tabulates, depicts, and describes the data collection in a systematic manner. (Glass, G. V., & Hopkins, K. D. 1984) The survey questionnaire is divided into two parts: the demographic profile of respondents and the list of questions that the researcher aims to know in order to collect valid and reliable data needed for the study. The second part was subdivided into 3 parts, which are Security Measures on Digital Banking, Common Digital Banking Issues and Problems Encountered by Respondents, and an open-ended question about Suggestions & other problems encountered. The security measures on digital banking in terms of trust and security trust and security, knowledge and awareness, ease of use, and usefulness are strongly agreed upon. However, it is necessary to improve the security measures with regard to accessing the apps using multiple devices, securing one time passwords, an easy withdrawal system, and clearing service requests.

VNF-Enabled 5G Network Orchestration Framework for Slice Creation, Isolation and Management

Network slicing is widely regarded as the most critical technique for allocating network resources to varied user needs in 5G networks. A Software Defined Networking (SDN) and Network Function Virtualization (NFV) are two extensively used strategies for slicing the physical infrastructure according to use cases. The most efficient use of virtual networks is realized by the application of optimal resource allocation algorithms. Numerous research papers on 5G network resource allocation focus on network slicing or on the best resource allocation for the sliced network. This study uses network slicing and optimal resource allocation to achieve performance optimization using requirement-based network slicing. The proposed approach includes three phases: (1) Slice Creation by Machine Learning methods (SCML), (2) Slice Isolation through Resource Allocation (SIRA) of requests via a multi-criteria decision-making approach, and (3) Slice Management through Resource Transfer (SMART). We receive a set of Network Service Requests (NSRs) from users. After receiving the NSRs, the SCML is used to form slices, and SIRA and SMART are used to allocate resources to these slices. Accurately measuring the acceptance ratio and resource efficiency helps to enhance overall performance. The simulation results show that the SMART scheme can dynamically change the resource allocation according to the test conditions. For a range of network situations and Network Service Requests (NSRs), the performance benefit is studied. The findings of the simulation are compared to those of the literature in order to illustrate the usefulness of the proposed work.

A policy gradient approach to solving dynamic assignment problem for on-site service delivery

The paper studies the resource allocation problem for delivering on-site services in urban areas. Requests for services are received spontaneously, with deliveries to be assigned dynamically. Real-life examples of such applications include the dispatch of traffic officers to scenes of accidents and the deployment of mechanics to sites of maintenance works. The dynamic assignment problem is to be solved via a policy gradient approach that dynamically assigns workers to different locations so that each customer involved would experience a minimum delay. Our solution framework adopts the transformer architecture with layers of inter-task and inter-agent communications as the approximator. This approximator is trained with the vanilla policy gradient algorithm. To improve computational effectiveness, we introduce an option of withholding an assignment, where workers may not be assigned at a decision point even if a service request is received, to enhance the flexibility of actions. Extensive computational experiments with a varying number of orders, order frequencies, and spatial sparsity are conducted. Our proposed method is shown to outperform other benchmarking methods, including the genetic algorithm and other online heuristics, in terms of stability of effectiveness, computational efficiency, and solution quality. Our experimental results suggest that the proposed method would have a reduced advantage over other benchmarking algorithms if the on-site service time is long.

Distributed Denial-of-Service (DDoS) Attack Detection using 1D Convolution Neural Network (CNN) and Decision Tree Model

The major problem of internet security is a Distributed Denial-of-Service (DDoS) attack, which can’t be detected easily. This attack is said to have occurred when lots of service requests are simultaneously received at a server on the internet. This makes the server too busy to provide normal services for others. The Distributed Denial of Service (DDoS) attacks nature on large networks on the Internet demanding to develop the effective detection and response methods. The deployment of these technique should perform not only at the network core but also at the edge. A DDoS attack detection framework is presented based on transfer learning model consisting of 1D Convolution Neural Network (CNN) and decision tree classifier. The 1D CNN model utilizes for features extraction from the input network traffic data. This operation also reduces the dimension of the data thereby removing the redundancy in the data. These features are given to the decision tree model for classification. The proposed framework identified the DDoS attacks with good accuracy. This system could identify attacks in real-time and provide network security.

A Distributed Pricing Strategy for Edge Computation Offloading Optimization in Autonomous Driving

The increase of on-vehicle applications has brought explosive computation demands to autonomous vehicles and overwhelmed their limited onboard resources. Edge computing can offload application load and effectively alleviate this problem. However, the introduction of edge computing faces significant challenges, including the considerable amount of resource contention due to the scarcity of edge resources and the competition among edge computing resource providers to earn users' services requests. We notice that the problem is not purely technical as solutions for these two problems can become conflicting to each other. In this paper, we propose a distributed pricing strategy to achieve full use of computing resources at the edge and maximize the revenue of service operators, both with guaranteed quality-of-service of on-vehicle applications. More specifically, we first use the multi-leader multi-follower Stackelberg game theory to model the pricing of on-vehicle task offloading under edge computing. Next, we propose a distributed pricing strategy to enable edge servers to adjust their local price distributions so that edge servers can bargain with offloading requesters independently. Experimental results confirm that the proposed distributed pricing strategy can provide more optimized server computing resource utilization while guaranteeing the performance of in-vehicle applications.

Cooperative Service Placement and Request Routing in Mobile Edge Networks for Latency-Sensitive Applications

The emergence of mobile applications like self-driving cars, networked gaming, virtual reality, and augmented reality has created a demand for computation-intensive and latency critical applications. The dense deployment of base stations (BSs) makes the overlapping coverage of BS that induces the placement of services and routing the requests to the appropriate node is a challenging issue. Further, the limited resources at the edge node invite additional problems of allocating the existing limited edge resources cooperatively to fulfil the user demands. To address the problems mentioned above, we formulate the cooperative service placement and routing problem by placing the diversified latency critical services to maximize the time utility with the deadline and resource constraints. The problem is formulated as an integer linear programming problem for cooperative service placement in mobile edge networks. A greedy and randomized rounding technique is presented to solve the service caching and request routing problems decomposed from the proposed problem. Further, a heuristic algorithm based on the circular convex set is presented to solve the proposed NP-hard problem. Extensive simulation results demonstrate that the proposed cooperative service placement schemes significantly improve the delay, cache hit ratio, load on cloud, and time utility performance compared with existing mechanisms.

Optimizing Service Redeployment in Migration-Oriented IoT Networks

The Internet of Things (IoT) paradigm has established an effective platform to promote the collaboration of resource-limited and duty-cycle IoT nodes, in order to support relative complex service requests that can hardly be achieved by any single IoT node. The functionalities of IoT nodes are typically encapsulated into IoT services, and the satisfaction of service requests is implemented as IoT service composition. Generally, IoT nodes work in turn in terms of their pre-specific working cycles, and IoT network topology is constantly varied due to their active/sleeping behaviour switching, causing unscheduled response latency. IoT service composition instantiation should be dynamically adjusted and partially re-deployed on-demand for supporting request processing efficiently. To remedy this issue, this paper proposes a Migration-oriented Service re-Deployment (MSrD) mechanism by migrating certain IoT services from their hosted IoT nodes to neighboring ones, in order to support functionally continuous availability.We formulate this problem as a game-theoretic approach, which is reduced to a potential game, where a Nash equilibrium solution is searched for optimizing this service re-deployment game. Extensive experiments are conducted, and numerical results show that our MSrD mechanism is promising, compared with the state-of-art techniques, in achieving service re-deployment optimization with efficient energy consumption and timely response latency simultaneously.

Microservice-Oriented Service Placement for Mobile Edge Computing in Sustainable Internet of Vehicles

The integration of Mobile Edge Computing (MEC) and microservice architecture drives the implementation of the sustainable Internet of Vehicles (IoV). The microservice architecture enables the decomposition of a service into multiple independent, fine-grained microservices working independently. With MEC, microservices can be placed on Edge Service Providers (ESPs) dynamically, responding quickly and reducing service latency and resource consumption. However, the burgeoning of IoV leads to high computation and resource overheads, making service resource requirements an imminent issue. What’s more, due to the limited computation power of ESPs, they can only host a few services. Therefore, ESPs should judiciously decide which services to host. In this paper, we propose a Microservice-oriented Service Placement (MOSP) mechanism for MEC-enabled IoV to shorten service latency, reduce high resource consumption levels and guarantee long-term sustainability. Specifically, we formulate the service placement as an integer linear programming program, where service placement decisions are collaboratively optimized among ESPs, aiming to address spatial demand coupling, service heterogeneity, and decentralized coordination in MEC systems. MOSP comprises an upper layer to map the service requests to ESPs and a lower layer to adjust the service placement of ESPs. Evaluation results show that the microservice-oriented service deployment mechanism offers dramatic improvements in terms of resource savings, latency reduction, and service speed.

Renewable Energy Provision and Energy-Efficient Operational Management for Sustainable 5G Infrastructures

The energy consumption of mobile network infrastructures has been witnessed to rise significantly in recent years due to the massive growth of mobile traffic triggered by the increasing adoption of 5G networks and massive applications of the internet of things (IoT). The increase in network traffic not only demands network densification but also increases the operational expenditure (OPEX) of the mobile network operators as well as the environmental and sustainability concerns. To address such a challenge, green energy technology has received increasing attention. However, keeping the density of small cell base stations (SCBSs) and matching the dynamics of available energy variations to the user service request arrivals are non-trivial that need further investigation. This paper proposes to utilize the microgeneration of renewable energy (RE) infrastructure with traffic-aware load offloading integrated with advanced sleep mode (ASM) operation. The centralized renewable energy microgeneration approach is adopted to power the high density of SCBSs installed at a dispersed geographical location. The stochastic modeling-based traffic offloading can offload the macro base station (MBS) users to SCBSs depending on the traffic intensity. The advanced sleep mode stochastic model is presented to gradually manage the underutilized SCBSs into sleep modes based on the traffic load. The proposed scheme is developed to reduce the on-grid energy consumption whilst meeting the quality of service (QoS) requirement in terms of blocking probability and reactivation delay. The numerical results demonstrated that the proposed solution can achieve a significant amount of energy-saving depending upon the renewable energy availability and MBS traffic offloading with ASMs policies.

The Multi-Trip Autonomous Mobile Robot Scheduling Problem with Time Windows in a Stochastic Environment at Smart Hospitals

Autonomous mobile robots (AMRs) play a crucial role in transportation and service tasks at hospitals, contributing to enhanced efficiency and meeting medical demands. This paper investigates the optimization problem of scheduling strategies for AMRs at smart hospitals, where the service and travel times of AMRs are stochastic. A stochastic mixed-integer programming model is formulated to minimize the total cost of the hospital by reducing the number of AMRs and travel distance while satisfying constraints such as AMR battery state of charge, AMR capacity, and time windows for medical requests. To address this objective, some properties of the solutions with time window constraints are identified. The variable neighborhood search (VNS) algorithm is adjusted by incorporating the properties of the AMR scheduling problem to solve the model. Experimental results demonstrate that VNS generates high-quality solutions. Both enhanced efficiency and the meeting of medical demands are achieved through intelligently arranging the driving routes of AMRs for both charging and service requests, resulting in substantial cost reductions for hospitals and enhanced utilization of medical resources.