Pub Date : 2025-03-05DOI: 10.1109/ACCESS.2025.3548517
Mohamed Massaoudi
The growing integration of distributed energy resources and increased interconnectivity in cyber-physical power systems (CPPSs) have heightened their complexity. This complexity has made voltage stability control more vulnerable, especially under cybersecurity threats. Cybersecurity threats enable the manipulation of critical system states, potentially causing blackouts and cascading failures. This highlights the need for adaptive, efficient, and resilient control mechanisms to ensure CPPS stability. This paper presents a novel Stability and voltage Protection Achieved with Resilient Soft Q-learning (SPARQ). The proposed approach leverages a Soft Q-Learning (SQL) framework to autonomously regulate voltage stability while addressing the impact of cyber attacks. The proposed SQL-based control system incorporates adaptive preprocessing mechanisms to normalize observations and enhance policy robustness. The study evaluates the performance of the SQL agent under both normal and cyber-attacked scenarios, with simulated disturbances such as voltage variability, stochastic load dynamics, and deliberate data injections. Comprehensive experiments on the IEEE 14-bus, reduced IEEE 118-bus, and IEEE 118-bus systems demonstrate the effectiveness of the SQL framework in achieving improved voltage regulation. Additionally, the SQL framework exhibits faster convergence and higher rewards compared to baseline reinforcement learning methods. Moreover, the framework’s effectiveness under cyber attack highlights its potential for resilient voltage stability control in modern CPPSs.
{"title":"SPARQ: A Cyber-Resilient Voltage Regulation Using Soft Q-Learning Approach for Autonomous Grid Operations","authors":"Mohamed Massaoudi","doi":"10.1109/ACCESS.2025.3548517","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548517","url":null,"abstract":"The growing integration of distributed energy resources and increased interconnectivity in cyber-physical power systems (CPPSs) have heightened their complexity. This complexity has made voltage stability control more vulnerable, especially under cybersecurity threats. Cybersecurity threats enable the manipulation of critical system states, potentially causing blackouts and cascading failures. This highlights the need for adaptive, efficient, and resilient control mechanisms to ensure CPPS stability. This paper presents a novel Stability and voltage Protection Achieved with Resilient Soft Q-learning (SPARQ). The proposed approach leverages a Soft Q-Learning (SQL) framework to autonomously regulate voltage stability while addressing the impact of cyber attacks. The proposed SQL-based control system incorporates adaptive preprocessing mechanisms to normalize observations and enhance policy robustness. The study evaluates the performance of the SQL agent under both normal and cyber-attacked scenarios, with simulated disturbances such as voltage variability, stochastic load dynamics, and deliberate data injections. Comprehensive experiments on the IEEE 14-bus, reduced IEEE 118-bus, and IEEE 118-bus systems demonstrate the effectiveness of the SQL framework in achieving improved voltage regulation. Additionally, the SQL framework exhibits faster convergence and higher rewards compared to baseline reinforcement learning methods. Moreover, the framework’s effectiveness under cyber attack highlights its potential for resilient voltage stability control in modern CPPSs.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"43830-43842"},"PeriodicalIF":3.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10912514","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-05DOI: 10.1109/ACCESS.2025.3548105
Qi Li;Shanwen Wu;Masato Edahiro
This paper presents a templated approach for automatic generation of optimized library functions using Halide as a replacement for the functions generated by Simulink. Although Simulink is widely used for the development of embedded systems, the automatically generated code may have limitations in compute-intensive models. Therefore, we propose library function generation using Halide from prewritten templates, extracting the Simulink model parameters using a model-based parallelizer. Experiments were conducted on central processing units (CPUs) and graphical processing units (GPUs) to evaluate performance. On CPUs, compared with compiler vectorization and the basic linear algebra subprograms (BLAS) library, Halide achieved up to 65.77 times speedup in multi-core and up to 36.20 times speedup in single-core scenarios. Although Halide did not always outperform BLAS for larger matrix sizes, it still showed considerable improvements. On GPUs, experiments on MX450 and Jetson platforms demonstrated that Halide’s performance was comparable to that of cuBLAS and even surpassed it for larger matrices.
{"title":"Multi-Architecture Halide Template-Driven Automatic Library Function Generation for Simulink Models","authors":"Qi Li;Shanwen Wu;Masato Edahiro","doi":"10.1109/ACCESS.2025.3548105","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548105","url":null,"abstract":"This paper presents a templated approach for automatic generation of optimized library functions using Halide as a replacement for the functions generated by Simulink. Although Simulink is widely used for the development of embedded systems, the automatically generated code may have limitations in compute-intensive models. Therefore, we propose library function generation using Halide from prewritten templates, extracting the Simulink model parameters using a model-based parallelizer. Experiments were conducted on central processing units (CPUs) and graphical processing units (GPUs) to evaluate performance. On CPUs, compared with compiler vectorization and the basic linear algebra subprograms (BLAS) library, Halide achieved up to 65.77 times speedup in multi-core and up to 36.20 times speedup in single-core scenarios. Although Halide did not always outperform BLAS for larger matrix sizes, it still showed considerable improvements. On GPUs, experiments on MX450 and Jetson platforms demonstrated that Halide’s performance was comparable to that of cuBLAS and even surpassed it for larger matrices.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"42866-42873"},"PeriodicalIF":3.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10910117","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As autonomous driving technology advances, the demand for unmanned mobility applications continues to grow. However, due to the imperfections in current autonomous driving systems, incidents still occur, highlighting the challenges of full driverless services. Moreover, the computation of complex autonomous driving algorithms requires an on-board computing unit, which consumes a large amount of energy. To address these limitations, tele-operated driving (ToD) has emerged as a promising solution for enhancing autonomous intelligent transportation systems (ITS). By enabling remote entities, such as remote users or servers, to control vehicles and manage edge cases in autonomous driving, ToD combines the benefits of both unmanned mobility and human oversight. To support ToD service, a real-time sensor sharing system for vehicles is essential, and cellular vehicle-to-everything (C-V2X) communication is suitable for the required network connectivity. However, most research has not focused on high-volume data transmission, which is required for sensor sharing systems. Additionally, the energy consumption of C-V2X, which directly impacts the battery efficiency of electric vehicles (EVs) as an example, has not been thoroughly examined. In this paper, we propose an evaluation framework for energy consumption analysis of ToD. Based on this framework, we analyze the energy consumption of vehicle for sensor data transmission over 5G C-V2X under varying channel conditions and multi-user scenarios. We also investigate the extent to which using ToD is energy-saving compared to the energy consumption of an on-board high-performance computing unit. Our findings indicate that the uplink-based sensor sharing system is more energy-efficient than its sidelink-based counterpart. Additionally, sensor sharing for ToD can save more energy of the battery in the vehicle compared to relying on the high-performance on-board computing unit.
{"title":"Energy Consumption Analysis of 5G C-V2X Sensor Sharing for Tele-Operated Driving","authors":"Hanyoung Park;Yongjae Jang;Kanghyun Ko;Ji-Woong Choi","doi":"10.1109/ACCESS.2025.3548116","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548116","url":null,"abstract":"As autonomous driving technology advances, the demand for unmanned mobility applications continues to grow. However, due to the imperfections in current autonomous driving systems, incidents still occur, highlighting the challenges of full driverless services. Moreover, the computation of complex autonomous driving algorithms requires an on-board computing unit, which consumes a large amount of energy. To address these limitations, tele-operated driving (ToD) has emerged as a promising solution for enhancing autonomous intelligent transportation systems (ITS). By enabling remote entities, such as remote users or servers, to control vehicles and manage edge cases in autonomous driving, ToD combines the benefits of both unmanned mobility and human oversight. To support ToD service, a real-time sensor sharing system for vehicles is essential, and cellular vehicle-to-everything (C-V2X) communication is suitable for the required network connectivity. However, most research has not focused on high-volume data transmission, which is required for sensor sharing systems. Additionally, the energy consumption of C-V2X, which directly impacts the battery efficiency of electric vehicles (EVs) as an example, has not been thoroughly examined. In this paper, we propose an evaluation framework for energy consumption analysis of ToD. Based on this framework, we analyze the energy consumption of vehicle for sensor data transmission over 5G C-V2X under varying channel conditions and multi-user scenarios. We also investigate the extent to which using ToD is energy-saving compared to the energy consumption of an on-board high-performance computing unit. Our findings indicate that the uplink-based sensor sharing system is more energy-efficient than its sidelink-based counterpart. Additionally, sensor sharing for ToD can save more energy of the battery in the vehicle compared to relying on the high-performance on-board computing unit.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"42547-42558"},"PeriodicalIF":3.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10910110","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-05DOI: 10.1109/ACCESS.2025.3548552
Naqash Afzal;Irfan Hussain;Zejian Zhou;Domenico Prattichizzo;Lakmal Seneviratne;Yuru Zhang;Dangxiao Wang
Presenting information privately such as alertness levels and time on the wrist via vibrotactile feedback proves invaluable for visually impaired individuals. Additionally, in situations where the visual channel is occupied, this serves as a discreet solution for sighted users, allowing them to stay informed during meetings or tasks without the need to overtly check their watches, thus minimizing potential distractions. However, it is a challenging task to present time accurately and efficiently to the users using vibrotactile modality due to the perceptual limits of human’s haptic channel. Inspired by the metaphors of mechanical and digital watches that have been widely used in our daily lives, we proposed two novel spatial-temporal vibrotactile encoding strategies. By varying the location, number, and duration of the vibrotactile stimuli, these strategies are capable of presenting the exact information about the current time through a series of encoded tactile cues. A physical prototype was developed and fifteen participants were recruited to evaluate the two solutions. Two experiments were performed to evaluate the two encoding strategies. The results showed that the mechanical and digital encoding strategies achieved an average correct rate of $90.55 pm 5.2%$ and $95.22 pm 4.1%$ during the focused state, and $95.28 pm 3.3%$ and $97.78 pm 3.8%$ during the distracted state, respectively $(mean pm SD)$ . Experimental results provide deep insights into utilizing the spatial-temporal patterns of vibrotactile stimuli for developing industrial-scale wearable haptic devices to present time and quantitative information efficiently and privately to the users.
{"title":"Sensory Substitution Device for Time Presentation: Spatial–Temporal Vibrotactile Encoding for Presenting Time on the Human Wrist","authors":"Naqash Afzal;Irfan Hussain;Zejian Zhou;Domenico Prattichizzo;Lakmal Seneviratne;Yuru Zhang;Dangxiao Wang","doi":"10.1109/ACCESS.2025.3548552","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548552","url":null,"abstract":"Presenting information privately such as alertness levels and time on the wrist via vibrotactile feedback proves invaluable for visually impaired individuals. Additionally, in situations where the visual channel is occupied, this serves as a discreet solution for sighted users, allowing them to stay informed during meetings or tasks without the need to overtly check their watches, thus minimizing potential distractions. However, it is a challenging task to present time accurately and efficiently to the users using vibrotactile modality due to the perceptual limits of human’s haptic channel. Inspired by the metaphors of mechanical and digital watches that have been widely used in our daily lives, we proposed two novel spatial-temporal vibrotactile encoding strategies. By varying the location, number, and duration of the vibrotactile stimuli, these strategies are capable of presenting the exact information about the current time through a series of encoded tactile cues. A physical prototype was developed and fifteen participants were recruited to evaluate the two solutions. Two experiments were performed to evaluate the two encoding strategies. The results showed that the mechanical and digital encoding strategies achieved an average correct rate of <inline-formula> <tex-math>$90.55 pm 5.2%$ </tex-math></inline-formula> and <inline-formula> <tex-math>$95.22 pm 4.1%$ </tex-math></inline-formula> during the focused state, and <inline-formula> <tex-math>$95.28 pm 3.3%$ </tex-math></inline-formula> and <inline-formula> <tex-math>$97.78 pm 3.8%$ </tex-math></inline-formula> during the distracted state, respectively <inline-formula> <tex-math>$(mean pm SD)$ </tex-math></inline-formula>. Experimental results provide deep insights into utilizing the spatial-temporal patterns of vibrotactile stimuli for developing industrial-scale wearable haptic devices to present time and quantitative information efficiently and privately to the users.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"44385-44402"},"PeriodicalIF":3.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10912496","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-05DOI: 10.1109/ACCESS.2025.3548151
Tao Dai;Qi Wang;Yuancheng Shen;Shang Gao
Neural networks have been widely employed in the field of object detection. Transformers enable effective object detection through global context awareness, modular design, scalability, and adaptability to diverse target scales. However, small object detection requires careful consideration due to its comprehensive computations, data requirements, and real-time performance challenges. To address these issues, we present SwinVision, an innovative framework for small object detection in low-light environments. This research shows a balanced approach between computational efficiency and detection accuracy for advancing object detection in low-light scenarios. Firstly, a Swin Transformer-based computing network is introduced and optimized for object detection in large-scale areas. The framework balances computational power and resource efficiency, surpassing conventional transformers. Secondly, we present the STLE module, which enhances the features of low-light images for beneficial object detection. The last building block is a specialized Swin-based detection block for accurate detection of small, detailed objects in resource-constrained scenarios. Experiments conducted on the VisDrone dataset significantly ameliorated existing methods such as YOLOv8x, with a 6.31% increase in mAP and 12.55% in AP50. SwinVision’s effectiveness in low-light environments, especially with small objects, establishes a foundation for robust detection systems adapting to various environmental challenges.
{"title":"SwinVision: Detecting Small Objects in Low-Light Environments","authors":"Tao Dai;Qi Wang;Yuancheng Shen;Shang Gao","doi":"10.1109/ACCESS.2025.3548151","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548151","url":null,"abstract":"Neural networks have been widely employed in the field of object detection. Transformers enable effective object detection through global context awareness, modular design, scalability, and adaptability to diverse target scales. However, small object detection requires careful consideration due to its comprehensive computations, data requirements, and real-time performance challenges. To address these issues, we present SwinVision, an innovative framework for small object detection in low-light environments. This research shows a balanced approach between computational efficiency and detection accuracy for advancing object detection in low-light scenarios. Firstly, a Swin Transformer-based computing network is introduced and optimized for object detection in large-scale areas. The framework balances computational power and resource efficiency, surpassing conventional transformers. Secondly, we present the STLE module, which enhances the features of low-light images for beneficial object detection. The last building block is a specialized Swin-based detection block for accurate detection of small, detailed objects in resource-constrained scenarios. Experiments conducted on the VisDrone dataset significantly ameliorated existing methods such as YOLOv8x, with a 6.31% increase in mAP and 12.55% in AP50. SwinVision’s effectiveness in low-light environments, especially with small objects, establishes a foundation for robust detection systems adapting to various environmental challenges.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"42797-42812"},"PeriodicalIF":3.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10910170","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-05DOI: 10.1109/ACCESS.2025.3548133
Mostafa Farouk Senussi;Mahmoud Abdalla;Mahmoud Salaheldin Kasem;Mohamed Mahmoud;Bilel Yagoub;Hyun-Soo Kang
Overcoming occlusions in light field (LF) imaging is a challenging yet complex task crucial for scene understanding, image quality enhancement, and restoring visual details in obstructed scenes. This review examines contemporary occlusion removal methods, spanning from classical techniques to advanced deep learning approaches that leverage LF data’s spatial and angular dimensions. We categorize these methods into two domains: (1) single-view inpainting methods often adapted for LF contexts, and (2) specialized LF occlusion removal techniques that exploit multi-view data. The review explores how these methods mitigate occlusion artifacts and also investigates LF acquisition technologies, representations, and the role of loss functions in optimizing model performance. A discussion of publicly available datasets and performance evaluation metrics addresses the challenges of handling large occlusions. The review concludes with future research directions, emphasizing hybrid approaches, refined loss functions, and scalable solutions for LF occlusion removal.
{"title":"A Comprehensive Review on Light Field Occlusion Removal: Trends, Challenges, and Future Directions","authors":"Mostafa Farouk Senussi;Mahmoud Abdalla;Mahmoud Salaheldin Kasem;Mohamed Mahmoud;Bilel Yagoub;Hyun-Soo Kang","doi":"10.1109/ACCESS.2025.3548133","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548133","url":null,"abstract":"Overcoming occlusions in light field (LF) imaging is a challenging yet complex task crucial for scene understanding, image quality enhancement, and restoring visual details in obstructed scenes. This review examines contemporary occlusion removal methods, spanning from classical techniques to advanced deep learning approaches that leverage LF data’s spatial and angular dimensions. We categorize these methods into two domains: (1) single-view inpainting methods often adapted for LF contexts, and (2) specialized LF occlusion removal techniques that exploit multi-view data. The review explores how these methods mitigate occlusion artifacts and also investigates LF acquisition technologies, representations, and the role of loss functions in optimizing model performance. A discussion of publicly available datasets and performance evaluation metrics addresses the challenges of handling large occlusions. The review concludes with future research directions, emphasizing hybrid approaches, refined loss functions, and scalable solutions for LF occlusion removal.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"42472-42493"},"PeriodicalIF":3.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10910139","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-05DOI: 10.1109/ACCESS.2025.3548539
Moisés J. B. B. Davi;Mario Oleskovicz;Felipe V. Lopes
This paper presents a performance review of existing fault classifiers when applied to Inverter-Based Resource (IBR) interconnection lines and proposes a new high-sensitivity time-domain fault classification methodology. The proposed method is based on self-adjusting thresholds, and it is investigated regarding its performance when applied to IBR or conventional generator terminals, being validated for different grid short-circuit levels, various IBR topologies/controls, and considering several fault types, inception angles, resistances, and locations. A typical IBR interconnection system topology is modeled using the PSCAD software for such studies. Comparisons with the main state-of-the-art phase-selection and fault classification methods highlight the superiority of the proposed one that, besides overcoming the challenges presented by IBRs for this task, provides shorter operating times by not relying on phasor estimation techniques.
{"title":"A Novel High-Sensitivity Time-Domain Fault Classifier Applied to Inverter-Based Resource Interconnection Lines","authors":"Moisés J. B. B. Davi;Mario Oleskovicz;Felipe V. Lopes","doi":"10.1109/ACCESS.2025.3548539","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548539","url":null,"abstract":"This paper presents a performance review of existing fault classifiers when applied to Inverter-Based Resource (IBR) interconnection lines and proposes a new high-sensitivity time-domain fault classification methodology. The proposed method is based on self-adjusting thresholds, and it is investigated regarding its performance when applied to IBR or conventional generator terminals, being validated for different grid short-circuit levels, various IBR topologies/controls, and considering several fault types, inception angles, resistances, and locations. A typical IBR interconnection system topology is modeled using the PSCAD software for such studies. Comparisons with the main state-of-the-art phase-selection and fault classification methods highlight the superiority of the proposed one that, besides overcoming the challenges presented by IBRs for this task, provides shorter operating times by not relying on phasor estimation techniques.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"41590-41606"},"PeriodicalIF":3.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10912499","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-05DOI: 10.1109/ACCESS.2025.3548146
Xiaofang Li;Pei Hu;Jiulong Zhu
Supply chain design (SCD) is a complex optimization challenge that involves coordinating various elements of a supply chain to ensure efficient production, distribution, and fulfillment of customer demands. This paper proposes an improved equilibrium optimizer (IEO) algorithm to develop a supply chain network. The first novelty lies in considering the uncertainty of customer demands, the upper and lower product limits of manufacturers, and product discounts to minimize the total economic cost. The second novelty concerns the improvements to the EO algorithm in the equilibrium pool, control parameters, and position correction. Position correction ensures that solutions meet the various constraints of SCD, and improves the feasibility of the algorithm. For small-, medium-, and large-scale test cases, the proposed algorithm has been observed to outperform the original EO algorithm and four well-known algorithms, the imperialist competitive algorithm (ICA), a hybrid algorithm of grey wolf optimizer and particle swarm optimization (GWOPSO), the whale optimization algorithm (WOA), and the teaching-learning based optimization algorithm (TLBO), in terms of optimal solutions and operational efficiency. IEO demonstrates outstanding performance in solving SCD problems.
{"title":"Equilibrium Optimizer for Supply Chain Design Under Demand Uncertainty","authors":"Xiaofang Li;Pei Hu;Jiulong Zhu","doi":"10.1109/ACCESS.2025.3548146","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548146","url":null,"abstract":"Supply chain design (SCD) is a complex optimization challenge that involves coordinating various elements of a supply chain to ensure efficient production, distribution, and fulfillment of customer demands. This paper proposes an improved equilibrium optimizer (IEO) algorithm to develop a supply chain network. The first novelty lies in considering the uncertainty of customer demands, the upper and lower product limits of manufacturers, and product discounts to minimize the total economic cost. The second novelty concerns the improvements to the EO algorithm in the equilibrium pool, control parameters, and position correction. Position correction ensures that solutions meet the various constraints of SCD, and improves the feasibility of the algorithm. For small-, medium-, and large-scale test cases, the proposed algorithm has been observed to outperform the original EO algorithm and four well-known algorithms, the imperialist competitive algorithm (ICA), a hybrid algorithm of grey wolf optimizer and particle swarm optimization (GWOPSO), the whale optimization algorithm (WOA), and the teaching-learning based optimization algorithm (TLBO), in terms of optimal solutions and operational efficiency. IEO demonstrates outstanding performance in solving SCD problems.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"42285-42295"},"PeriodicalIF":3.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10910140","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-05DOI: 10.1109/ACCESS.2025.3548096
Jianbin Chen;Chengyu Yang;Jianjun Zou;Kai Chen
Power factor correction (PFC) plays a crucial role in power electronics, particularly in enhancing the efficiency and stability of power systems. As continuous conduction mode (CCM) boost PFC converters become increasingly prevalent, research into their control strategies has deepened. While average current mode (ACM) control is commonly used, it faces several challenges in practical applications. Traditional ACM control methods struggle with input impedance regulation, especially within certain frequency ranges, where maintaining constant input impedance is difficult. This leads to issues such as current distortion and reduced efficiency. Additionally, bandwidth adjustment and ripple disturbance suppression with standard control procedures remain significant challenges. To address these issues, this paper proposes a novel multiplier-operated controller specifically designed for CCM boost PFC converters. The controller employs an innovative methodology to effectively modify and maintain input impedance at a defined constant within a specific frequency range. Furthermore, a specialized compensator is integrated to optimize bandwidth and minimize ripple disturbances. Experimental results from a 600W prototype demonstrate that the proposed controller achieves a power factor of up to 0.98 and significantly enhances efficiency and other performance metrics. This study provides new insights and technical approaches for improving the control strategies of CCM boost PFC converters.
{"title":"Multiplier Operated Controller for CCM Boost PFC Converter With Regulated Input Impedance and Improved Power Factor","authors":"Jianbin Chen;Chengyu Yang;Jianjun Zou;Kai Chen","doi":"10.1109/ACCESS.2025.3548096","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548096","url":null,"abstract":"Power factor correction (PFC) plays a crucial role in power electronics, particularly in enhancing the efficiency and stability of power systems. As continuous conduction mode (CCM) boost PFC converters become increasingly prevalent, research into their control strategies has deepened. While average current mode (ACM) control is commonly used, it faces several challenges in practical applications. Traditional ACM control methods struggle with input impedance regulation, especially within certain frequency ranges, where maintaining constant input impedance is difficult. This leads to issues such as current distortion and reduced efficiency. Additionally, bandwidth adjustment and ripple disturbance suppression with standard control procedures remain significant challenges. To address these issues, this paper proposes a novel multiplier-operated controller specifically designed for CCM boost PFC converters. The controller employs an innovative methodology to effectively modify and maintain input impedance at a defined constant within a specific frequency range. Furthermore, a specialized compensator is integrated to optimize bandwidth and minimize ripple disturbances. Experimental results from a 600W prototype demonstrate that the proposed controller achieves a power factor of up to 0.98 and significantly enhances efficiency and other performance metrics. This study provides new insights and technical approaches for improving the control strategies of CCM boost PFC converters.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"44750-44759"},"PeriodicalIF":3.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10910123","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-05DOI: 10.1109/ACCESS.2025.3548318
Yeonwoo Kim;Bosung Jeon;Jonghyuk Park;Woo Young Choi
Hardware spiking neural networks (SNNs) are gaining increasing attention as promising next-generation computing approaches owing to their parallel computing and energy-efficient nature. Recent SNNs have achieved excellent performance by introducing artificial neural networks (ANN) to the SNN conversion training method. However, SNNs face significant challenges when implemented on hardware platforms. These challenges include achieving low energy consumption, difficulties in minimizing conversion error, and representing ANN functions other than the rectified linear unit activation function. This paper proposes mixed-signal complementary metal-oxide-semiconductor time-frame integrate-and-fire (TIF) neuron circuits and corresponding SNNs to achieve high accuracy with low energy consumption. TIF neurons integrate synaptic inputs during a time-frame and generate output spikes under synchronization signals based on the integrated input. When building SNNs with TIF neurons, bias and max-pooling can be effectively implemented, which is difficult to achieve using conventional SNNs with integrate-and-fire (IF) neuron circuits. In addition, TIF neurons support pipelining operations, further enhancing the inference throughput of the system. Simulation results with the CIFAR-10 dataset show that SNNs with TIF neurons achieve 0.48 %p higher classification accuracy while consuming 92 % lower neuron energy than conventional IF-based SNNs.
{"title":"Time-Frame Integrate-and-Fire Neuron Circuit for Low Energy Inference Hardware Spiking Neural Networks","authors":"Yeonwoo Kim;Bosung Jeon;Jonghyuk Park;Woo Young Choi","doi":"10.1109/ACCESS.2025.3548318","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3548318","url":null,"abstract":"Hardware spiking neural networks (SNNs) are gaining increasing attention as promising next-generation computing approaches owing to their parallel computing and energy-efficient nature. Recent SNNs have achieved excellent performance by introducing artificial neural networks (ANN) to the SNN conversion training method. However, SNNs face significant challenges when implemented on hardware platforms. These challenges include achieving low energy consumption, difficulties in minimizing conversion error, and representing ANN functions other than the rectified linear unit activation function. This paper proposes mixed-signal complementary metal-oxide-semiconductor time-frame integrate-and-fire (TIF) neuron circuits and corresponding SNNs to achieve high accuracy with low energy consumption. TIF neurons integrate synaptic inputs during a time-frame and generate output spikes under synchronization signals based on the integrated input. When building SNNs with TIF neurons, bias and max-pooling can be effectively implemented, which is difficult to achieve using conventional SNNs with integrate-and-fire (IF) neuron circuits. In addition, TIF neurons support pipelining operations, further enhancing the inference throughput of the system. Simulation results with the CIFAR-10 dataset show that SNNs with TIF neurons achieve 0.48 %p higher classification accuracy while consuming 92 % lower neuron energy than conventional IF-based SNNs.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"43728-43740"},"PeriodicalIF":3.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10910109","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：