Scheduling Management Research Articles

Comprehensive Review of Crop Water Requirement Estimation Techniques: Approaches, Challenges, and Future Directions

In order to meet the growing demand for water, water scarcity is a significant issue that needs attention. Agriculture crops are not getting enough water because of this problem. Consequently, figuring out how much water a given crop needs requires using the right method. Accurate crop water requirements must be measured in order to schedule irrigation effectively, which in turn leads to efficient crop water management. To restore the lost moisture and promote the best possible growth for plants, irrigation is used. Water management and irrigation scheduling fundamentally depend on an accurate calculation of the crop's crop water requirements (ETc). Accurate evapotranspiration measurements are necessary for effective irrigation water management. Evapotranspiration (ET), a process that measures the amount of water lost from soil and crops through transpiration and evaporation processes, respectively, is dependent on a variety of meteorological factors. A significant factor in determining crop water requirements and irrigation schedules is reference evapotranspiration. There exist multiple theories and methodologies for estimating reference evapotranspiration, ranging from empirical to physical based. Reference Evapotranspiration is referred to the idea behind ET is to calculate ET based on a reference surface that is comparable to a deep surface of green grass that is consistently growing, completely covering the surface with enough water, and looking stable. The goal of irrigation futures is to choose a suitable model for estimating reference crop evapotranspiration. In order to calculate the amount of water needed for a crop, multiply ETo by the crop coefficient (Kc), which is dependent on the phases and length of a crop's growth. Regression, fuzzy logic, Penman-Monteith, Blaney-Criddle, Hargreaves, ANN and WNN, and other conventional and non-traditional methods are used to estimate ETo.

Optimization and energy management strategies, challenges, advances, and prospects in electric vehicles and their charging infrastructures: A comprehensive review

Electric vehicles (EVs) are at the forefront of global efforts to reduce greenhouse gas emissions and transition to sustainable energy systems. This review comprehensively examines the optimization and energy management strategies for EVs and their charging infrastructure, focusing on technological advancements, persistent challenges, and future prospects. By the end of 2023, the number of electric cars on the road globally reached 40 million, with 14 million new registrations recorded in 2023 alone—95% of which were in China, Europe, and the United States. Governments across the globe have introduced incentives and policies to promote EV adoption, and by 2030, EVs are expected to comprise a significant portion of light-duty vehicles in major regions. Despite these encouraging developments, challenges such as range anxiety, the relatively low energy density of 200–300 Wh/kg in Li-ion batteries (compared to 13,000 Wh/kg for petroleum), and insufficient public charging infrastructure remain key barriers to widespread EV adoption. This review also explores the critical role of smart grid technologies, vehicle-to-grid (V2G) systems, and renewable energy integration in supporting the growing EV market. V2G technologies are projected to enhance grid stability by 20–30% and reduce operational costs by 10–15% through load balancing and real-time energy price forecasting. By thoroughly analyzing optimization techniques such as load balancing, dynamic scheduling, and real-time energy management, this paper offers a roadmap for researchers, policymakers, and industry stakeholders to accelerate the integration of EVs into global energy systems and enhance sustainability in urban transportation networks.

Theory of AI-driven scheduling (TAIS): a service-oriented scheduling framework by integrating theory of constraints and AI

This paper introduces the Theory of AI-driven scheduling (TAIS), an innovative framework designed to revolutionise service-oriented scheduling (In the context of this paper, ‘service-oriented’ refers to the design and execution of scheduling processes that are specifically tailored to meet the dynamic and varied needs of service-manufacturing industries. This approach emphasises adaptability, customer-centric scheduling, and the efficient allocation of resources to enhance product and service delivery.) by integrating the theory of constraints (TOC) (see APPENDIX I) with cutting-edge Artificial Intelligence (AI) technologies. TAIS extends the traditional five steps of TOC by introducing three additional layers to enhance adaptability, efficiency, and applicability in service-oriented environments. TAIS incorporates continuous monitoring and adjustment mechanisms across all five TOC steps to improve adaptability, ensuring real-time responsiveness to dynamic scheduling challenges. To enhance efficiency, TAIS integrates lifecycle management and governance into the core framework, which helps in the efficient allocation of resources throughout the scheduling process. Lastly, TAIS includes robust security and compliance measures to bolster applicability. By leveraging AI, TAIS offers a predictive, flexible, and scalable solution capable of addressing the complexities and rapid changes inherent in dynamic scheduling tasks and providing a significant leap forward in scheduling and operations management.

Adaptive Multi-Function Radar Temporal Behavior Analysis

The performance of radar mode recognition has been significantly enhanced by the various architectures of deep learning networks. However, these approaches often rely on supervised learning and are susceptible to overfitting on the same dataset. As a transitional phase towards Cognitive Multi-Functional Radar (CMFR), Adaptive Multi-Function Radar (AMFR) possesses the capability to emit identical waveform signals across different working modes and states for task completion, with dynamically adjustable waveform parameters that adapt based on scene information. From a reconnaissance perspective, the valid signals received exhibit sparsity and localization in the time series. To address this challenge, we have redefined the reconnaissance-focused research priorities for radar systems to emphasize behavior analysis instead of pattern recognition. Based on our initial comprehensive digital system simulation model of a radar, we conducted reconnaissance and analysis from the perspective of the reconnaissance side, integrating both radar and reconnaissance aspects into environmental simulations to analyze radar behavior under realistic scenarios. Within the system, waveform parameters on the radar side vary according to unified rules, while resource management and task scheduling switch based on operational mechanisms. The target in the reconnaissance side maneuvers following authentic behavioral patterns while adjusting the electromagnetic space complexity in the environmental aspect as required. The simulation results indicate that temporal annotations in signal flow data play a crucial role in behavioral analysis from a reconnaissance perspective. This provides valuable insights for future radar behavior analysis incorporating temporal correlations and sequential dependencies.

Digital twin for decision support system of industrial utility management

Manufacturing and industrial operations rely heavily on energy that is generated mostly from fossil fuels, such as coal, oil, and natural gas, which harm the environment and contribute to climate change. Thus, renewable energy is being integrated into industrial processes to lessen environmental effects and reduce fossil fuel usage. However, the renewable source performance process can be greatly affected by disturbances and constraints, such as ambient air temperature and relative humidity, minimum utility consumption, and the total energy required, making effective control difficult. This study proposes a digital twin built with machine learning regression techniques for load demand forecasting as a decision-support system for industrial utility management. From the results, the ensemble tree (ET) model produced the highest accuracy, based on validation and test dataset root mean squared error values of 23.164 and 27.558, respectively, and R2 values of 0.96 and 0.95, respectively. The digital twin and load demand forecasting approaches effectively created an efficient operating schedule for industrial utility management. The ET model had a total error of 23.86%, substantially lower than the average load demand's total error of 65.29%. Therefore, the ET model with weather conditions in four scenarios could be recommended to optimize energy utilization when creating the operating schedule.

Achieving successful gas plant construction: A risk modelling framework with quantitative risk-based approach to schedule management

The construction of gas plants often experiences delays caused by various factors, which can lead to significant financial and operational losses. This research aims to develop an accurate risk model to improve the schedule performance of gas plant projects. The model uses Quantitative Risk Analysis (QRA) and Monte Carlo simulation methods to identify and measure the risks that most significantly impact project schedule performance. A comprehensive literature review was conducted to identify the risk variables that may cause delays. The risk model, pre-simulation modeling, result analysis, and expert validation were all developed using a Focused Group Discussion (FGD). Primavera Risk Analysis (PRA) software was used to perform Monte Carlo simulations. The simulation output provides information on probability distribution, histograms, descriptive statistics, sensitivity analysis, and graphical results that aid in better understanding and decision-making regarding project risks. The research results show that the simulated project completion timeline after mitigation suggested an acceleration of 61–65 days compared to the findings of the baseline simulation. This demonstrates that activity-based mitigation has a major influence on improving schedule performance. This research makes a significant contribution to addressing project delay issues by introducing an innovative and effective risk model. The model empowers project teams to proactively identify, measure, and mitigate risks, thereby improving project schedule performance and delivering more successful projects.

Deep-Learning-Based Automated Building Construction Progress Monitoring for Prefabricated Prefinished Volumetric Construction.

Prefabricated prefinished volumetric construction (PPVC) is a relatively new technique that has recently gained popularity for its ability to improve flexibility in scheduling and resource management. Given the modular nature of PPVC assembly and the large amounts of visual data amassed throughout a construction project today, PPVC building construction progress monitoring can be conducted by quantifying assembled PPVC modules within images or videos. As manually processing high volumes of visual data can be extremely time consuming and tedious, building construction progress monitoring can be automated to be more efficient and reliable. However, the complex nature of construction sites and the presence of nearby infrastructure could occlude or distort visual data. Furthermore, imaging constraints can also result in incomplete visual data. Therefore, it is hard to apply existing purely data-driven object detectors to automate building progress monitoring at construction sites. In this paper, we propose a novel 2D window-based automated visual building construction progress monitoring (WAVBCPM) system to overcome these issues by mimicking human decision making during manual progress monitoring with a primary focus on PPVC building construction. WAVBCPM is segregated into three modules. A detection module first conducts detection of windows on the target building. This is achieved by detecting windows within the input image at two scales by using YOLOv5 as a backbone network for object detection before using a window detection filtering process to omit irrelevant detections from the surrounding areas. Next, a rectification module is developed to account for missing windows in the mid-section and near-ground regions of the constructed building that may be caused by occlusion and poor detection. Lastly, a progress estimation module checks the processed detections for missing or excess information before performing building construction progress estimation. The proposed method is tested on images from actual construction sites, and the experimental results demonstrate that WAVBCPM effectively addresses real-world challenges. By mimicking human inference, it overcomes imperfections in visual data, achieving higher accuracy in progress monitoring compared to purely data-driven object detectors.

A novel mixed-integer linear programming formulation for continuous-time inventory routing

Inventory management, vehicle routing, and delivery scheduling decisions are simultaneously considered in the context of the inventory routing problem. This paper focuses on the continuous-time version of this problem where, unlike its more traditional discrete-time counterpart, the distributor is required to guarantee that inventory levels are maintained within the desired intervals at any moment of the planning horizon. In this work, we develop a compact mixed-integer linear programming formulation to model the continuous-time inventory routing problem. We further discuss means to expedite its solution process, including the adaptation of well-known rounded capacity inequalities to tighten the formulation in the context of a branch-and-cut algorithm. Through extensive computational studies on a suite of 90 benchmark instances from the literature, we show that our branch-and-cut algorithm outperforms the state-of-the-art approach. We also consider a new set of 63 instances adapted from a real-life dataset and show our algorithm’s practical value in solving instances with up to 20 customers to guaranteed optimality.

Assessing forecast performance of daily reference evapotranspiration: A comparison of equations, machine and deep learning using weather forecasts

An accurate forecast of short-term reference evapotranspiration (ET0) is crucial for effective farm and irrigation scheduling management. The techniques of forecasting ET0 have progressed from empirical equations to artificial intelligence-based models. However, gaps have remained in comprehensively evaluating the ET0 forecast performance discrepancies between various methods based on weather forecasts in addition to historical meteorological data, as well as investigating the effect of the amount of input variables on ET0 forecast accuracy. Here, the study evaluated the forecast accuracy of five conventional equations calibrated and six machine learning (ML) and deep learning (DL) models in predicting daily ET0 for a lead time of 1–7 days in the North China Plain (NCP). Comparative evaluations indicate that the Analytical Penman-Monteith (APM) is the optimum empirical equation for forecasting ET0, but its accuracy decreases as lead times increase. Conversely, ML and DL models consistently outperform empirical equations, characterized by lower mean absolute error (MAE) and root mean square error (RMSE) as well as correlation coefficient and Nash-Sutcliffe efficiency coefficient approaching 1 across all lead times. Notably, the Bidirectional Long short-term memory (Bi-LSTM) model outperforms other models, maintaining robust and effective forecast performance even on day 7. Moreover, with the increasing input variables, combining weather forecasts and historical meteorological data, the forecast performance of all models is improved, with significant enhancement observed in the Bi-LSTM model. This work provides valuable insights for choosing appropriate models to forecast ET0, holding essential in regional managing farm and irrigation systems.

The role of big data technology in project schedule management: the case of Amazon

With the rapid development of the Internet, big data technology has received widespread attention in the field of management. Traditional project schedule management methods cannot adapt to the complex and changing environment, and some researchers believe that big data technology has become a key tool to improve and optimize project management. However, there is a lack of mature theoretical systems and practical experience to guide the application of big data technology. Based on the case of Amazon, this paper analyses how the company uses big data technology to optimize project schedule management. It is found that the application of big data technology in project management brings significant benefits. It is able to provide empirical and innovative support for project schedule management. This paper discusses the application of big data technology in project schedule management, highlighting its capability to enable timely adjustments. Real-time monitoring and forecasting facilitate proactive management of project directions and potential risks. Moreover, it leverages real-time data to optimize resource allocation and enhance resource utilization. Furthermore, the paper addresses the challenges and proposes countermeasures associated with big data technology in this context. To tackle the issue of uneven data quality, a robust data collection mechanism should be established.

A multi-objective approach for timber harvest scheduling to include management of at-risk species and spatial configuration objectives.

Sustainable forestry typically involves integration of several economic and ecological objectives which, at times, may not be compatible with one another. Multi-objective prioritization via harvest scheduling programs can be used to elucidate these relationships and explore solutions. One such program is a spatially explicit harvest scheduler that adopts the Metropolis-Hastings algorithm to iteratively find management solutions to achieve multiple objectives (Habplan). Although this program has been used to address forest management scheduling and simulation-based tasks, its utility is constrained by time-intensive data preparation and challenges with incorporating spatial configuration objectives. To address these shortcomings, we introduce an open-source software package, HabplanR, streamlines data preparation, sets parameters, visualizes results, and assesses spatial components of ecological objectives. We developed four example objectives to incorporate into a multi-objective management problem: habitat quality indices for three species "types" (open, closed, and intermediate-canopy-associated species), and harvested pine pulpwood (revenue). We demonstrate the utility of this package to find management schedules that can accommodate potentially conflicting habitat needs of species, while achieving economic targets. We produced 100 software runs and prioritized individual objectives to select four management schedules for further comparisons. We compared outcome differences of the four schedules, including a spatial comparison of two high performing schedules. The software package makes costs and benefits of different schedules explicit and allows for consideration of the spatial configuration of management outcomes in decision-making.

Development of an estimation formula for preparation time of anesthesia induction and surgery accounting for clinical department factors in optimal surgery schedule management

Efficient operating room management is essential and requires precise surgery scheduling. We hypothesized that an estimation formula for the preparation time for anesthesia induction and surgery could be developed by incorporating anesthesia and surgical factors, as well as the ‘clinical department,’ into the formula. This retrospective observational study analyzed 12,528 scheduled surgical cases. A regression analysis that included the clinical department, six anesthesia factors, and five surgical factors was conducted. This analysis aimed to develop both an analytical framework and an equation for estimating the time required for both anesthesia induction and surgical preparation. Our estimation formula wielded high accuracy (R2 = 0.801). Particularly, there was only a difference of less than 3 min for surgeries under general anesthesia. In addition, modeling preparation time using “medical interventions performed in the operating room” as a factor instead of patient characteristics was found to be beneficial. It was possible to develop a highly accurate formula for estimating preparation time of anesthesia induction and surgery by analyzing the anesthesia factors and the surgical factors and incorporating the clinical department as an estimation factor. However, this study represents the development phase of the estimation formula. A multicenter study is essential to validate its generalizability and robustness across different settings before broader application.

Massive Point Cloud Processing for Efficient Construction Quality Inspection and Control.

The construction of large-scale civil infrastructures requires massive spatiotemporal data to support the management and control of scheduling, quality control, and safety monitoring. Existing artificial-intelligence-based data processing algorithms rely heavily on experienced engineers to adjust the parameters of data processing, which is inefficient and time-consuming when dealing with huge datasets. Limited studies have compared the performance of different algorithms on a unified dataset. This study proposes a framework and evaluation system for comparing different data processing policies for processing huge spatiotemporal data in construction quality control. The proposed method compares the combination of multiple types of algorithms involved in the processing of massive point cloud data. The performance of data processing strategies is evaluated through this framework, and the optimal point cloud processing strategies are explored based on registration accuracy and data fidelity. Results show that a reasonable choice of combinations of point cloud sampling, filtering, and registration algorithms can significantly improve the efficiency of point cloud data processing and satisfy engineering demands for data accuracy and completeness. The proposed method can be applied to the civil engineering problem of processing a large amount of point cloud data and selecting the optimal processing method.

Telemedicine and time management in primary care.

Information and communication technologies (ICTs) can enable workers to structure work in novel ways, allow for better time management, and increase work scheduling autonomy. Time management and work scheduling are important factors in the field of clinical practice in primary care. Time limits on consultation are a key constraint on the delivery of good care since the length of patient-physician consultation impacts its quality. This research aimed to examine the experiences of primary care physicians (PCPs) when using telemedicine technologies (TTs), a type of ICT, in their communication with patients. During 2023 in-depth interviews were conducted with 20 Israeli PCPs: family physicians and pediatricians. Perception and management of time emerged as a focal subject in the interviews. The PCPs interviewed described several effects of TTs on time management in primary care. They portrayed TTs as saving time for patients and having a mixed effect on the healthcare organization: both saving and wasting their work time. TTs were described as impacting their time management in the context of work-life balance, allowing them to manage their time during and between appointments. For PCPs, TTs can be beneficial for managing time in the clinic, which can contribute to better healthcare. This article, concerning TTs as a type of ICT, contributes to the existing literature which suggests that ICTs can allow for better time management and increase work scheduling autonomy. It also presents several recommendations for better implementation of TTs in healthcare organizations.

Proposal and appraisal of novel indicators and performance metrics for project monitoring

Project monitoring is a critical process for guaranteeing its excellence, ensuring the delivery of activities both on planned time and budget. Despite its importance, numerous discussions have arisen regarding which indicator is the most appropriate, and how and when to measure it. The primary objective of this article is to evaluate novel duration indicators based on the Earned Value Management (EVM), Earned Schedule Management (ESM) and Earned Duration Management (EDM) methodologies, and to assess new performance metrics. This involves the determination of the limits of the control charts through extensive Monte Carlo Simulations and their performance under several out-of-control scenarios. The robustness of the control charts is tested using performance metrics within a statistical control approach. The secondary objective consists of evaluating the impact of new probability distributions that describe the project activities, such as the Gamma and Conway–Maxwell–Poisson (CMP) distributions. The contributions of this study are threefold: firstly, the Duration Performance Index (DPI) from the EDM is a reliable indicator for monitoring the overall project duration. Secondly, the probability of overreaction (PO) and the accuracy (Ac) are the performance metrics that most produced robust indicators. Lastly, it is observed that different probability distributions, specifically Gamma and Conway–Maxwell–Poison (CMP) distributions, seem to interfere with the correct generation of control charts signals, although they do not significantly affect the overall duration of the entire project.

Automatic Planning Method of Construction Schedule under Multi-Dimensional Spatial Resource Constraints

To enhance the application of building information modeling (BIM) in schedule management for engineering projects, improve spatial planning capabilities, and minimize subjective factors in schedule preparation, this paper presents a framework and method for automatic construction schedule planning based on BIM and data-driven approaches under multi-dimensional spatial resource constraints. The method includes data acquisition, construction process reasoning, time parameter calculation, and schedule generation and scheduling. Initially, the construction data from the BIM model and manual input are imported into the reasoning system to establish the logical relationships of the construction process. Construction time parameters and spatial resource requirements are then automatically calculated using MySQL. Subsequently, the spatial layout and resource allocation data exported from the BIM model are compared to assess whether the space meets the project requirements. Finally, a construction schedule that satisfies the space constraints is generated. The method was validated through a case study, demonstrating its effectiveness in automatic schedule planning under human-computer interaction. This study introduces an innovative approach that considers spatial conflicts in the automatic scheduling process, improving planning efficiency and reducing the risk of spatial conflicts on construction sites.

Comparative analysis of advanced deep learning models for predicting evapotranspiration based on meteorological data in bangladesh.

Evapotranspiration is one of the crucial elements in water balance equations and plays a pivotal role in the water and energy cycle of an area. An accurate and precise estimation and prediction of reference evapotranspiration (ETo) is necessary for regional management of water resources and irrigation scheduling. The challenge of predicting daily evapotranspiration with limited meteorological data in Bangladesh. This study aims to predict daily evapotranspiration using limited meteorological data of Bangladesh by three deep learning (CNN, GRU, LSTM) and one hybrid (CNN-GRU) model. The novel method of hybrid CNN-GRU models, which have not been commonly used for this purpose. The performance of models was evaluated by five accuracy matrices R2, RMSE, MAE, MAPE, and CE and comparison is visualized by radar graphs. The study's novelty lies in the use of hybrid CNN-GRU models to estimate reference evapotranspiration, as this algorithm has not been commonly used for this purpose. In the case of the Rangpur station, the hybrid CNN-GRU algorithm outperformed other models, achieving the best values across various statistical metrics during both the training and testing phases. The highest correlation coefficient values of approximately 0.994 and 0.995. Moreover, during training and testing stages, the hybrid model had the lowest MAE (0.076, 0.068) and RMSE (0.138, 0.106) at the Rangpur station. Additionally, in the Sreemangal station, it can be notable that the statistical parameter RSME found superior results in the hybrid model around 0.225 and 0.174, respectively. In addition, the highest R2 and CE values were noted as 0.986, 0.987 and 0.985, 0.986 during the training and testing phases, respectively. The comparison suggests that the hybrid model will be best suited for prediction with the limited meteorological data. The outcome of the present research signifies the ability of deep learning methods in the prediction of evapotranspiration and the dominant variables affecting the changes the in context of Bangladesh.

Efficacy of various herbicides for weed management in irrigated chickpea (Cicer arietinum)

Chickpea is a short-stature crop with slow initial growth and limited leaf area development due to which it is heavily infested with a wide spectrum of weeds. The menace of weeds has increased to such an extent that an ef- fective weed management schedule has become a necessity. A research study was conducted during the rabi season of 2021–22 at the Agronomy Research Farm, Chaudhary Charan Singh Haryana Agricultural University, Hisar, Haryana. Thirteen weed control treatments viz., pre-plant incorporation (PPI) and pre-emergence (PRE) pendimethalin at 1,000 g/ha, PPI imazethapyr at 75 g/ha and 100 g/ha, PRE imazethapyr at 75 g/ha and 100 g/ha, post-emergence (PoE) imazethapyr at 75 g/ha and 100 g/ha, PPI and PRE pendimethalin + imazethapyr Ready mix (RM) at 1,000 g/h and two hand hoeings at 30 and 50 DAS were compared with weedy check and weed free in a randomized block design and replicated thrice. Among the herbicides, lowest weed dry weight was observed un- der PPI and PRE pendimethalin + imazethapyr (RM) at 1,000 g/ha respectively. PoE application of imazethapyr displayed phytotoxicity symptoms like stunting, leaf crinkling, and chlorosis as indicated by phytotoxicity scale ranging from 1-5. Significantly higher seed yield was obtained by pendimethalin + imazethapyr (1,827 kg/ha) over other combinations. Therefore, the PRE-application of pendimethalin + imazethapyr (RM) at 1,000 g/ha was the most suitable herbicide for efficient weed management in chickpea as it not only controlled the diverse weed flora but also improved seed yield.

Web-Based System Enhances Extracurricular Management Efficiency in Educational Institutions

Background: The advancement of information technology has significantly influenced educational management, particularly in managing extracurricular activities within schools. Specific Background: Traditional methods of managing these activities often lead to time-consuming processes and ineffective communication, highlighting the need for a more efficient system. Knowledge Gap: While various management systems exist, few specifically address the challenges faced in managing extracurricular activities effectively and transparently. Aims: This research aims to develop and implement a web-based Extracurricular Management Information System (SIMAK) to enhance efficiency and transparency in managing extracurricular activities. Results: Utilizing Agile methodology with the Scrum model and the Laravel framework, the study successfully developed the SIMAK application, which supports activity registration, schedule management, attendance tracking, and student assessments. The implementation of SIMAK resulted in improved administrative efficiency, streamlined processes, and increased transparency in information access for administrators, coaches, and students. Novelty: This study presents a unique approach to extracurricular management by leveraging modern technology and methodologies to address existing inefficiencies in educational settings. Implications: The findings suggest that the SIMAK application not only enhances the management of extracurricular activities but also encourages greater student participation and provides schools with better data for decision-making. Overall, the application significantly contributes to optimizing students' educational experiences outside the classroom, promoting a more organized and transparent approach to extracurricular management. Highlights: Efficiency: Streamlines registration and scheduling processes for extracurricular activities. Transparency: Improves information access for all users involved. Engagement: Increases student participation in extracurricular activities. Keywords: Extracurricular Management, Information System, Agile Methodology, Transparency, Education Technology

A joint vehicular device scheduling and uncertain resource management scheme for Federated Learning in Internet of Vehicles

Federated learning (FL) offers an effective framework for the efficient process in vehicular edge computing. However, FL encompasses the process of distributing and uploading model parameters, which are inevitably transmitted in a wireless network environment. Some challenges in FL-assisted Internet of Vehicles (IoV) sceneries gradually emerging, such as data heterogeneity, concerned device resources, and unstable communication environment, which necessitate intelligent vehicle selection schemes that accelerate training efficiency. Based on these, we consider a new scenario, specifically an FL-assisted IoV system under uncertain communication conditions, and develop an interval many-objective vehicle selection and bandwidth allocation (IMoVSBA) joint optimization scheme. This scheme takes into account computation latency, energy consumption, server utilization, and data quality, while meeting multi-criteria resource optimization requirements. Among these, server utilization is a new objective designed specifically for this joint optimization problem. For the proposed problem, a novel interval many-objective evolutionary algorithm with individual comprehensive indicator to control the evolution direction (IMaOEACI) is designed. Simulation results demonstrate that this method outperforms other schemes in terms of accuracy, training cost, and server utilization, effectively improving training efficiency in wireless channel environments and reasonably utilizing bandwidth resources. It provides significant scientific value and application potential in the field of the IoVs.