Network Management System Research Articles

Risk Analysis on Autonomous Vessels based on Systems Theory – Application of NET-HARMS method

Abstract The shift towards Maritime Autonomous Surface Ships is a significant development in the maritime logistics industry, with the potential to enhance efficiency, safety, and environmental sustainability. However, the integration of autonomous systems also presents new challenges and risks, particularly in the absence of empirical data for traditional risk assessment methodologies. This research tackles this problem by utilizing the Net-worked Hazard Analysis and Risk Management System (Net-HARMS) method, a systems thinking method that hasn’t been previously employed in examining MASS. The method analyses the risks associated with the EC-funded, H2020, MOSES Project, which included a concept for automating the manoeuvring and docking processes with autonomous tugboats. The Net-HARMS method offers a comprehensive and holistic approach to risk assessment, overcoming the limitations of conventional probabilistic models. By constructing a Hierarchical Task Analysis and a task network, the research maps the system’s operational framework and explores task interdependencies. The use of a risk mode taxonomy allows for the identification of task-specific and emergent risks, which are then assessed by utilising the risk matrix of the Risk-Based Assessment Tool developed by DNV, to assess the final risk as a function of the effectiveness of each risk mitigation layer and the severity of the identified task consequences. The findings provide valuable insights into critical tasks requiring enhanced risk control measures and contribute to the development of safety constraints necessary for the successful implementation of autonomous shipping technologies. By applying Net-HARMS method to the realm of autonomous ships, this research not only fills a significant gap in maritime risk analysis but also sets a precedent for future studies in this rapidly evolving field.

Prospectively identifying risks and controls for advanced brain-computer interfaces: A Networked Hazard Analysis and Risk Management System (Net-HARMS) approach

The introduction of advanced digital technologies continues to increase system complexity and introduce risks, which must be proactively identified and managed to support system resilience. Brain-computer interfaces (BCIs) are one such technology; however, the risks arising from broad societal use of the technology have yet to be identified and controlled. This study applied a structured systems thinking-based risk assessment method to prospectively identify risks and risk controls for a hypothetical future BCI system lifecycle. The application of the Networked Hazard Analysis and Risk Management System (Net-HARMS) method identified over 800 risks throughout the BCI system lifecycle, from BCI development and regulation through to BCI use, maintenance, and decommissioning. High-criticality risk themes include the implantation and degradation of unsafe BCIs, unsolicited brain stimulation, incorrect signals being sent to safety-critical technologies, and insufficiently supported BCI users. Over 600 risk controls were identified that could be implemented to support system safety and performance resilience. Overall, many highly-impactful BCI system safety and performance risks may arise throughout the BCI system lifecycle and will require collaborative efforts from a wide range of BCI stakeholders to adequately control. Whilst some of the identified controls are practical, work is required to develop a more systematic set of controls to best support the design of a resilient sociotechnical BCI system.

Automated PIM Detection in Wireless Networks via Smart Data-Driven Techniques

As the number of base stations keeps increasing due to ever-growing wireless services and pervasive connectivity, the operational costs for network service providers rises proportionally. In addition, with the evolution of wireless technologies and the development of next generation networks such as 5G and 6G, network operators are inevitably expected to encounter more complex challenges. One such network issue is the Passive Intermodulation (PIM) problem that is observed in both 4G and 5G networks. It degrades the user experience and radio resource efficiency while leading to an operational overhead for detecting and mitigating it on the operator side. Although there is a significant body of work regarding PIM detection and cancellation methods, the majority of such studies depends on hardware solutions and manual investigation by network engineers, which is costly in terms of time and labor. In this paper, we propose two methods using unsupervised and semi-supervised Machine Learning (ML) approaches, namely a time-series-based anomaly detection technique and an autoencoder-based one, for identifying PIM problems in network sites. The proposed solutions utilize a set of Key Performance Indicator (KPI) data of base stations obtained from network management systems for a significantly long time interval and detect possible PIM problems without the need for a human in the loop. We measure and analyze the performance of our solutions, with the guidance of experienced network engineers, on our collected dataset.

Hidden Markov models for predicting cell-level mobile networks performance degradation

The ubiquitous deployment of Fourth-generation (4G) and Fifth-generation (5G) networks, while expanding user connectivity over a larger geographic area, presents significant challenges for mobile network management. The surge in connected devices increase cell congestion, while user mobility, fading, and interference further deteriorate channel quality. The combined effect of these factors contribute to a gradual degradation in cell and network performance, straining the capabilities of Mobile Network Operators (MNOs) to maintain optimal service quality. The degradation progresses through distinct stages, and ultimately leading to cell outages. Existing cell degradation detection methods, such as key performance indicators (KPIs) monitoring and drive tests, rely on indicators such as signal strength (like reference signal received power (RSRP)), network measurements (like traffic volume and handover requests), and user complaints. However, these methods may not provide real-time insights, leading to delays in identifying and addressing performance issues. This paper proposes a Hidden Markov Model (HMM) approach for proactive cell degradation prediction using real-time time-series KPIs data collected from a telecom operator’s network management system. The NetMax system, a network management system specifically designed for ZTE networks, was used for KPIs data collection. RSRP, 3GPP-recommended signal strength metrics for degradation measure, defines hidden states, while traffic volume and handover requests represent the observable states. The HMM achieves an average prediction accuracy of 93.12%, F1 score of 91.81%, and precision of 92.82% with 23 observation lengths, demonstrating the models’s effectiveness in predicting mobile network’s cell degradation severity.

Hardening Active Directory Graphs via Evolutionary Diversity Optimization based Policies

Active Directory (AD) is the default security management system for Windows domain networks. An AD environment can be described as a cyber-attack graph, with nodes representing computers, accounts, etc., and edges indicating existing accesses or known exploits that enable attackers to move from one node to another. This paper explores a Stackelberg game model between one attacker and one defender on an AD attack graph. The attacker’s goal is to maximize their chances of successfully reaching the destination before getting detected. The defender’s aim is to block a constant number of edges to minimize the attacker’s chance of success. The paper shows that the problem is #P-hard and, therefore, intractable to solve exactly. To defend the AD graph from cyber attackers, this paper proposes two defensive approaches. In the first approach, we convert the attacker’s problem to an exponential sized Dynamic Program that is approximated by a Neural Network (NN). Once trained, the NN serves as an efficient fitness function for defender’s Evolutionary Diversity Optimization based defensive policy. The diversity emphasis on the defender’s solution provides a diverse set of training samples, improving the training accuracy of our NN for modeling the attacker. In the second approach, we propose a RL based policy to solve the attacker’s problem and Critic network assisted Evolutionary Diversity Optimization based defensive policy to solve defender’s problem. Experimental results on synthetic AD graphs show that the proposed defensive policies are scalable, highly effective, approximate attacker’s problem accurately, and generate good defensive plans.

A Review of Traffic Flow Prediction Models in 5G Using Machine Learning Techniques

Abstract: Wireless technology has advanced significantly since its origin and is now an essential aspect of our daily life. The advancement of wireless communication from the first generation (1G) to the fifth generation (5G) of technology has been revolutionary. An extensive summary of the development of wireless communication from 1G to 5G has been given in this paper. Cellular networks are heading towards becoming more diverse, broadband, integrated, and intelligent networks with the introduction of 5G networks. The goals of 5G wireless technology are to provide more users with more consistent user experiences, ultralow latency, vast network capacity, faster multi-Gbps peak data speeds and increased reliability. While the resources needed for computation and communication are also growing with the maturity of 5G technology .At the same time, cellular traffic has increased dramatically due to the widespread use of smart devices. Cellular traffic prediction is a crucial component of the resource management system for cellular networks but it confronts many difficulties due to strict standards for accuracy and dependability. Among the most important issues is how to enhance the predictive performance of Mobile data traffic. This review describes the need of traffic forecasting in cellular network in 5G technology. A study of different models for network analysis and traffic prediction by different researchers is presented in this paper. The distinctiveness and guidelines of earlier research for traffic prediction in 5G are examined. To determine the distinctive qualities of each method used for traffic prediction in mobile network, a thorough analysis of the most popular techniques using Machine learning for predictive analysis are discussed.

Towards transactional integrity issues in policy based network management systems

Towards transactional integrity issues in policy based network management systems

Analysis of methods of data flow management in mobile radio communication means

The article analyzes the existing methods of managing data flows in mobile radio communications. During the analysis, the peculiarities of the functioning and construction of these networks were considered. It has been established that such networks have features different from other networks, such as mobility, dynamic topology, independent organization, use of mobile means of communication, lack of fixed data transmission routes, etc. The task of providing routing in mobile radio communication devices, mobile radio networks, and the types of routing in communication networks are considered. The conditions for the implementation of the routing task and the features that characterize the routing process have been established. The levels of the OSI open systems model and the most well-known protocols that work at these levels and are used in data flow management are considered. Data flow management methods are classified by type and a list of requirements for the process of data flow transmission in mobile radio networks is defined, taking into account the peculiarities of the functioning of mobile radio communication means, which must be taken into account when building a mobile radio network management system. It has been established that at the current stage of information technology development, data flow management methods are mostly adapted for use in computer, wired or fixed networks and do not take into account the conditions of use in mobile radio communication devices. It has been established that the construction and operation of an effective data flow control subsystem in the control systems of mobile radio networks and mobile radio communication means requires the use of the latest technologies and modern approaches in the development of data flow control methods and methods that will ensure the functioning of the corresponding data flow control subsystem. When choosing protocols, methods, methods of managing data flows, it is proposed to focus on adaptation, modification of approaches or their combined use based on the target function, taking into account the peculiarities of the functioning of mobile radio networks and mobile radio communication means.

Streamlining ICT Network Resources, Processes and Operations through a Centralized Management System: A Development and Evaluation

This study aims to provide an inventory and monitoring system for the ICT Network and Telecommunication Department at Lyceum of the Philippines University Cavite. As it streamlines the management and documentation of network equipment and IP addresses under a single, centralized system, it incorporates integrated management features to carry out and improve network resource management operations. The development of the system was presented with the use of the Agile Model, which illustrates the client's workflow, allowing for changes and discussions based on the client's feedback; the model involves planning, design, implementation, testing, and evaluation, allowing continuous improvement, and providing high-quality systems that met the client's requirements. In addition, the system's components were tested for unit functionality and browser compatibility by the technical adviser, (2) administrators, and (5) IT experts. Furthermore, the system also underwent an evaluation process based on ISO 25010 to measure its Compatibility, Usability, Reliability, Functional Suitability, Security, Portability, Maintainability, and Performance Efficiency, participated by (1) a technical adviser, (2) administrators, (10) IT Experts, and (10) end users. The findings revealed that the system was fully operational and could carry out its designated functions, with an average result of 98.93% passing rate. No component failed during testing in the presence of the specified test respondents. From the responses of the determined evaluators, all aspects of the system are deemed “Highly Acceptable.” The implications of these findings indicate that the ICT Network Resource Management System for LPU Cavite has met the requirements and expectations set forth. The system's compliance with ISO 25010 requirements, successful test results, and high-end user acceptability highlight its potential to enhance the management and monitoring processes, leading to more efficient and effective management for the university’s ICT network and telecommunication department. Keywords: ICT, Network Management System, ICT Network Resources, Streamlining ICT Resources Received Date: April 12, 2024Revised Date: May 17, 2024Accepted Date: May 26, 2024

Learning to Diagnose: Meta-Learning for Efficient Adaptation in Few-Shot AIOps Scenarios

With the advancement of technologies like 5G, cloud computing, and microservices, the complexity of network management systems and the variety of technical components have greatly increased. This rise in complexity has rendered traditional operations and maintenance methods inadequate for current monitoring and maintenance demands. Consequently, artificial intelligence for IT operations (AIOps), which harnesses AI and big data technologies, has emerged as a solution. AIOps plays a crucial role in enhancing service quality and customer satisfaction, boosting engineering productivity, and reducing operational costs. This article delves into the primary tasks involved in AIOps, such as anomaly detection, and log fault analysis and classification. A significant challenge identified in many AIOps tasks is the scarcity of fault sample data, indicating a natural alignment of these tasks with few-shot learning. Inspired by model-agnostic meta-learning (MAML), we propose a new anomaly detector, MAML-KAD, for application in various AIOps tasks. Observations confirm that meta-learning algorithms effectively enhance AIOps tasks, showcasing the wide-ranging application prospects of meta-learning algorithms in the field of AIOps. Moreover, we introduced an AIOps platform that embeds meta-learning within its diagnostic core and features streamlined log collection, caching, and alerting to automate the AIOps workflow.

Integrating management systems in the energy sector: the case of the electricity industry in New Zealand

The New Zealand Electricity Engineers Association (EEA) asked for advice about development of a guide for a public safety management system (PSMS) for electricity distribution networks based on ISO45001 Occupational health and safety management systems. This would help eliminate overlap between legislation and standards while maintaining compliance with legal requirements. At Victoria University of Wellington we have been working on such an integrated approach and this article reports on the project and suggests how the results can be extended to include other areas of management while retaining the ability for appropriate elements to be audited and certified in accordance with systems required by legislation. The project reviewed an earlier report and literature review on PSMS for the Electricity Networks Association. Development of the legal requirements for a PSMS were reviewed and use of the International Standards Organization (ISO) framework for all management system standards proposed to encompass ISO45001 and similar standards. Relevant management content was incorporated in the high-level structure and key stakeholders contributed technical content. Use of the ISO Annex SL as a template enabled development of an integrated management system incorporating other management system standards, that would still support legal compliance while enabling elimination of duplication and clutter, and waste of resources at a time of technology change. The work was carried out in New Zealand (NZ) and may not apply in other countries with different legal requirements. Auditors may resist integrated management systems although this may not be a limitation if documentation is appropriately written. The electricity networks businesses in NZ may move to implementation of the PSMS guide but this will be an internal decision and results may take some years to declutter documentation and reduce overlapping audits under management system standards. Over the next decade the context of the New Zealand electricity industry will undergo major shifts with the need to adapt to increasing expectations for occupational health and safety and public safety, adaptation to climate change and accelerated implementation of new technologies. The electricity industry will need to apply its resources to those changes while avoiding duplicated efforts to implement multiple management systems. Developing an integrated management system that incorporates several management systems and public safety may aid protection of non-workers who cannot otherwise be “controlled” by a business.

Flood Prediction Using Artificial Neural Networks: A Case Study in Temerloh, Pahang

Floods in Malaysia happen every year, especially in East Coast Peninsular Malaysia, due to the Northeast Monsoon and climate change, which may lead to heavy rainfall throughout the end of the year. Temerloh is one of the districts in Pahang that frequently encounters flood events, especially between November and January every year. The study used a dataset from the National Hydrological Network Management System (SPRHiN), which consists of hydrological data, and weather underground for the meteorological data in the location. The correlation analysis found that stream flow and water level are highly correlated to floods, with correlation coefficients (r values) of 0.83 and 0.76, respectively, while the temperature is inversely related to floods with a -0.28 correlation value. A lower temperature has a higher chance of rain and subsequent flooding. The results show that the model, by using an artificial neural network (ANN), has produced an accuracy of 0.9909 and a good performance of the area under the receiver operating characteristic curve (ROC) curve (AUC) at 0.888. The model also shows a low error with the mean squared error (MSE) of 0.009 and the root-mean-squared error (RMSE) of 0.096. The R2 value of 0.768 and F1 value of 0.875 indicate that the model has high precision and recall. Besides predictive modeling, a flood monitoring dashboard was created to visualize the data interactively. This research is vital in understanding the flood factors in Pahang and would offer academic insight for future research in floods.

Traumatic Native Hip Dislocations: An Audit at a Major Trauma Centre and Assessment of Clinical Practice at Centres Across the United Kingdom.

Native hip dislocations are defined as traumatic dislocations of the hip, typically high-energy and associated with polytrauma. The majority of these injuries occur following motor vehicle accidents (MVAs). Due to the inherent stability of the hip joint, a significant force is required to cause dislocation. It is critical that such injuries are managed and reduced in a timely manner. We evaluated the current practice in a major trauma centre (MTC) in Cardiff and gathered information from emergency departments (EDs) in Wales and MTCs around the United Kingdom (UK). We did an evaluation of the current practice with a retrospective audit of all traumatic native hip dislocations presenting to the MTC at Cardiff from August 2018 to February 2021. Data was obtained from Trauma Audit and Research Network (TARN), medical records, radiology and theatre management systems. An online survey was developed and disseminated to EDs in Wales and MTCs across the UK. There were 15 traumatic hip dislocation cases over the period evaluated. Sixty percentof cases were due to MVA. Eighty-six percent of patients had an associated fracture, with one Pipkin type IV fracture dislocation. The mean time to reduction from injury was 532 minutes (240-804 minutes), with 28.6% reduced within 6 hours and 71.4% reduced within 12 hours. Two patients had reduction performed in the ED (mean time to reduction, 275 minutes). There was one occurrence of avascular necrosis (AVN) and one of chondrolysis at the follow-up. The response rate to the survey was 80% and 83% in Wales and MTCs nationally, respectively. The majority (82%) of departments did not have an established pathway in place for managing traumatic native hip dislocations with a preference for reduction in the operating theatre. Native hip dislocations are rare, high-energy injuries associated with significant morbidity. The available evidence suggests time to reduction is imperative in reducing the risk of future complications. The establishment of a pathway to guide management and having a mechanism to perform reductions in the ED may produce significant reductions in this time, impacting outcomes.

Mathematical model of the topological structure of the urban water supply network

To effectively manage urban water supply networks, utility companies providing water supply and drainage (hereinafter referred to as KP "Vodokanal") need to solve the following problems: - use of topographic maps of scales 1:500, 1:1000, 1:2000, which include both ground-based buildings , as well as adjacent underground communications - water supply and sewerage, electrical networks, gas supply networks, heat supply, communications, etc.; - hydraulic calculations of the water supply network to determine the condition, analysis and optimization of the network structure; - prompt elimination of emergency situations and re-sumption of the network after the emergency is eliminated; - control and management of drinking water quality; - availability of pressure, flow and piezometer monitoring devices; - automated control of pumping stations; - saving energy resources; – network inventory. A comprehensive solution to these problems is provided by a geoinformation automated water supply network management system. Automated network management is carried out using geoinformation technologies, mathematical and geoinformation models of the water supply network. The work proposes a mathematical model of the topological structure of the water supply network, defines geospatial data bases about network objects and the interrelation-ships of these objects, taking into account the topological structure of the network to provide geoinformation and mathematical modeling of the hydraulic state of the water supply net-work, solving problems of emergency processing, monitoring the quality of drinking water, and optimizing the network, energy saving. To construct a digital model of the branched-ring structure of a topological graph, digital vector topographic maps are used as follows: - based on the results of geodetic surveys, water supply network facilities are marked on the topog-raphic map with symbols; - analysis of information-graphic diagrams of well details indicates the presence of pressure/flow regulators and hydrants. If there are regulators, their symbols are applied to the polyline of the water supply section at the symbol of the well at the point where the water pipe is inserted into the well, their diameters and the percentage of opening are indicated; - if there is a hydrant, the symbol for a well without a hydrant is replaced with the symbol for a well with a hydrant; - for all objects of the water supply network, the values of technical and graphic parameters are determined; - the orientation of the graph is deter-mined - the direction of water flow; – a matrix of incidents of vertices and contours is formed.

FineMon: An Innovative Adaptive Network Telemetry Scheme for Fine-Grained, Multi-Metric Data Monitoring with Dynamic Frequency Adjustment and Enhanced Data Recovery

Network telemetry, characterized by its efficient push model and high-performance communication protocol (gRPC), offers a new avenue for collecting fine-grained real-time data. Despite its advantages, existing network telemetry systems lack a theoretical basis for setting measurement frequency, struggle to capture informative samples, and face challenges in setting a uniform frequency for multi-metric monitoring. We introduce FineMon, an innovative adaptive network telemetry scheme for precise, fine-grained, multi-metric data monitoring. FineMon leverages a novel Two-sided Frequency Adjustment (TFA) to dynamically adjust the measurement frequency on the Network Management System (NMS) and infrastructure sides. On the NMS side, we provide a theoretical basis for frequency determination, drawing on changes in the rank of multi-metric data to minimize monitoring overhead. On the infrastructure side, we adjust the frequency in real-time to capture significant data fluctuations. We propose a robust Enhanced-Subspace-based Tensor Completion (ESTC) to ensure accurate recovery of fine-grained data, even with noise or outliers. Through extensive experimentation with three real datasets, we demonstrate FineMon's superiority over existing schemes in reduced measurement overhead, enhanced accuracy, and effective capture of intricate temporal features.

Enhanced PON and AMCC Joint Transmission with GMM-Based Probability Shaping Techniques

In ITU-T standards, auxiliary management and control channels (AMCCs), as defined, facilitate the rapid deployment and efficient management of wavelength division multiplexing passive optical network (WDM-PON) systems. The super-imposition of an AMCC introduces additional interference to a PON signal, resulting in the degradation of the performance of the overall transmission. In prior research, we proposed employing a Gaussian mixture model (GMM) to fit a baseband-modulated AMCC signal. Following the analysis of the interference model and the distribution characteristics of received signal errors, we propose a combined optimization method for a transmitter and receiver in this paper. This method, grounded in probabilistic shaping (PS) techniques, optimizes the probability distribution of the transmitted signal based on the AMCC interference model, with the objective of reducing the error rate in PON signal transmission. We have validated this approach within a 50G-PON experimental system by utilizing PAM4 modulation. The experimental results demonstrate the effectiveness of this method for mitigating the impact of baseband-modulated AMCC, thereby reducing the error rate in PON signal transmission. The approach presented in this paper can further minimize the performance degradation introduced by baseband-modulated AMCC in WDM-PON systems, enhancing the efficiency of WDM-PON deployment.

Flood Prediction Using Artificial Neural Networks: A Case Study in Temerloh, Pahang

Flood is one of the natural disasters that causes damage to properties, and sometimes loss of lives. Floods in Malaysia happen every year, especially in East Coast Peninsular Malaysia, due to the Northeast Monsoon and climate change, which may lead to heavy rainfall throughout the end of the year. Temerloh is one of the districts in Pahang that frequently encounters flood events, especially between November and January every year. Even though there are multiple efforts in flood mitigation and preparation, the damage to citizens and properties every year has cost thousands of Ringgits and the time taken to clean the damages caused by floods. Despite this, research on flood prediction in the state needs to be done using machine learning techniques. Due to this, this research explored the hydrological and meteorological factors that caused the flood in Temerloh and developed a machine-learning model capable of predicting the flood occurrence. The study used a dataset from the National Hydrological Network Management System (SPRHiN), which consists of hydrological data, and weather underground for the meteorological data in the location. The correlation analysis found that stream flow and water level are highly correlated to floods, with correlation coefficients (r values) of 0.83 and 0.76, respectively, while the temperature is inversely related to floods with a -0.28 correlation value. A lower temperature has a higher chance of rain and subsequent flooding. The results show that the model, by using an artificial neural network (ANN), has produced an accuracy of 0.9909 and a good performance of the area under the receiver operating characteristic curve (ROC) curve (AUC) at 0.888. The model also shows a low error with the mean squared error (MSE) of 0.009 and the root-mean-squared error (RMSE) of 0.096. The R2 value of 0.768 and F1 value of 0.875 indicate that the model has high precision and recall. Afterwards, a flood monitoring dashboard was created to visualize the data interactively. This research is vital in understanding the flood factors in Pahang and would offer academic insight for future research in floods. In addition, the flood monitoring dashboard will significantly assist governments and authorities in focusing the flood management efforts in areas at high risk of flood and be used to aid the state's future development.

Network Slicing in 5G Systems: Challenges, Opportunities and Implementation Approaches

The introduction of the fifth-generation (5G) of network technology has radically transformed the telecommunications landscape by providing high-speed, low-latency communication suitable for a range of innovative applications. However, this transformation also introduces novel network complexity and resource management challenges. An emerging solution to these formidable challenges is 'Network Slicing,' a powerful technology that plays a crux role in the efficient management of 5G network systems. Network slicing, enabled by key technologies such as Software-Defined Networking (SDN) and Network Function Virtualization (NFV), allows the creation of multiple virtual and independent networks operating on a shared physical infrastructure. This ability contributes to a more flexible, scalable, and efficient network system, making it aptly suited for diverse 5G applications. In this paper, we conduct an in-depth examination of network slicing in 5G systems, its implementation strategies, associated challenges, and potential solutions. Two real-world case studies underline its practical applications, while a discussion on the future outlook anticipates advances in AI and ML to refine network slicing management. The paper posits that while network slicing brings its own set of complexities, its continuous evolution and relentless innovations gear towards overcoming such challenges, paving the way to a future of 5G networking marked by versatility, reliability, and efficiency of unprecedented levels.

Faktor Kinerja Sistem Irigasi pada Tiga Daerah Irigasi di Kabupaten Dharmasraya

From the results of initial observations, it was found that the irrigation network management system in irrigation areas in Dharmasraya district was not managed properly and optimally, so that the impact was that many irrigation channels were found that were damaged and not well maintained. The purpose of this study was to identify the dominant factors and factors that influence the performance of the irrigation system in the three irrigation areas in Dharmasraya Regency, as well as to optimize the operation and maintenance of the network. This study used a quantitative method by distributing questionnaires to respondents. The results of the research conducted revealed 6 factors that influence the performance of the irrigation system in the three irrigation areas in Dharmasraya Regency, namely the P3A condition factor, the physical infrastructure condition factor, the planting productivity factor, the personnel organization factor, the facility factor. supporting, documentation factor

인공지능 기반 농작물 성숙도 체크와 농산물 시장가격 변동을 고려한 출하시기 결정시스템 연구

This study aims to develop an integrated agricultural distribution network management system to improve the quality, profit, and decision-making efficiency of agricultural products. We adopt two key techniques: crop maturity detection based on the YOLOX target detection algorithm and market price prediction based on the Prophet model. By training the target detection model, it was possible to accurately identify crops of various maturity stages, thereby optimizing the shipment timing. At the same time, by collecting historical market price data and predicting prices using the Prophet model, we provided reliable price trend information to shipping decision makers. According to the results of the study, it was found that the performance of the model considering the holiday factor was significantly superior to that of the model that did not, proving that the effect of the holiday on the price was strong. The system provides strong tools and decision support to farmers and agricultural distribution managers, helping them make smart decisions during various seasons and holidays. In addition, it is possible to optimize the distribution network of agricultural products and improve the quality and profit of agricultural products.