Yongjiang Zhao, Haoyi Zhong, Chang Cyoon Lim^*

CMC-Computers, Materials & Continua, Vol.79, No.1, pp. 449-471, 2024, DOI:10.32604/cmc.2024.048771

Abstract This paper examines the difficulties of managing distributed power systems, notably due to the increasing use of renewable energy sources, and focuses on voltage control challenges exacerbated by their variable nature in modern power grids. To tackle the unique challenges of voltage control in distributed renewable energy networks, researchers are increasingly turning towards multi-agent reinforcement learning (MARL). However, MARL raises safety concerns due to the unpredictability in agent actions during their exploration phase. This unpredictability can lead to unsafe control measures. To mitigate these safety concerns in MARL-based voltage control, our study introduces a novel approach: Safety-Constrained Multi-Agent Reinforcement Learning… More >

Yuejiao Wang, Zhong Ma^*, Chaojie Yang, Yu Yang, Lu Wei

CMC-Computers, Materials & Continua, Vol.79, No.1, pp. 819-836, 2024, DOI:10.32604/cmc.2024.047108

Abstract The quantization algorithm compresses the original network by reducing the numerical bit width of the model, which improves the computation speed. Because different layers have different redundancy and sensitivity to data bit width. Reducing the data bit width will result in a loss of accuracy. Therefore, it is difficult to determine the optimal bit width for different parts of the network with guaranteed accuracy. Mixed precision quantization can effectively reduce the amount of computation while keeping the model accuracy basically unchanged. In this paper, a hardware-aware mixed precision quantization strategy optimal assignment algorithm adapted to low bit width is proposed,… More >

Yutao Hu¹, Yuntao Zhao^1,*, Yongxin Feng², Xiangyu Ma¹

CMC-Computers, Materials & Continua, Vol.79, No.1, pp. 509-530, 2024, DOI:10.32604/cmc.2024.042216

Abstract In the face of the increasingly severe Botnet problem on the Internet, how to effectively detect Botnet traffic in real-time has become a critical problem. Although the existing deep Q network (DQN) algorithm in Deep reinforcement learning can solve the problem of real-time updating, its prediction results are always higher than the actual results. In Botnet traffic detection, although it performs well in the training set, the accuracy rate of predicting traffic is as high as%; however, in the test set, its accuracy has declined, and it is impossible to adjust its prediction strategy on time based on new data… More >

Yong Ma¹, Han Zhao², Kunyin Guo^3,*, Yunni Xia^3,*, Xu Wang⁴, Xianhua Niu⁵, Dongge Zhu⁶, Yumin Dong⁷

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.1, pp. 907-927, 2024, DOI:10.32604/cmes.2024.048759

Abstract Mobile Edge Computing (MEC) is a technology designed for the on-demand provisioning of computing and storage services, strategically positioned close to users. In the MEC environment, frequently accessed content can be deployed and cached on edge servers to optimize the efficiency of content delivery, ultimately enhancing the quality of the user experience. However, due to the typical placement of edge devices and nodes at the network’s periphery, these components may face various potential fault tolerance challenges, including network instability, device failures, and resource constraints. Considering the dynamic nature of MEC, making high-quality content caching decisions for real-time mobile applications, especially… More >

Tezara Cionita^1,*, Mohammad Hazim Mohamad Hamdan², Januar Parlaungan Siregar^3,4,*, Deni Fajar Fitriyana⁵, Ramli Junid⁶, Wong Ling Shing⁷, Jamiluddin Jaafar⁸, Agustinus Purna Irawan⁹, Teuku Rihayat¹⁰, Rifky Ismail¹¹, Athanasius Priharyoto Bayuseno¹¹, Emilianus Jehadus¹²

Journal of Renewable Materials, Vol.12, No.3, pp. 457-483, 2024, DOI:10.32604/jrm.2024.045814

Abstract Recent decades have seen a substantial increase in interest in research on natural fibres that is aligned with sustainable development goals (SDGs). Due to their renewable resources and biodegradability, natural fiber-reinforced composites have been investigated as a sustainable alternative to synthetic materials to reduce the usage of hazardous waste and environmental pollution. Among the natural fibre, jute fibre obtained from a bast plant has an increasing trend in the application, especially as a reinforcement material. Numerous research works have been performed on jute fibre with regard to reinforced thermoset and thermoplastic composites. Nevertheless, current demands on sustainable materials have required… More >

Joseph O. Dirisu^1,*, Imhade P. Okokpujie^2,3,*, Olufunmilayo O. Joseph¹, Sunday O. Oyedepo¹, Oluwasegun Falodun⁴, Lagouge K. Tartibu³, Firdaussi D. Shehu¹

Journal of Renewable Materials, Vol.12, No.3, pp. 485-511, 2024, DOI:10.32604/jrm.2024.045188

Abstract Research into converting waste into viable eco-friendly products has gained global concern. Using natural fibres and pulverized metallic waste becomes necessary to reduce noxious environmental emissions due to indiscriminately occupying the land. This study reviews the literature in the broad area of green composites in search of materials that can be used in automotive brake pads. Materials made by biocomposite, rather than fossil fuels, will be favoured. A database containing the tribo-mechanical performance of numerous potential components for the future green composite was established using the technical details of bio-polymers and natural reinforcements. The development of materials with diverse compositions… More > Graphic Abstract

A. MADHAN KUMAR¹, K. JAYAKUMAR^2,*, M. SHALINI³

Journal of Polymer Materials, Vol.39, No.3-4, pp. 269-281, 2022, DOI:10.32381/JPM.2022.39.3-4.7

Abstract Polylactic acid (PLA) is the most popular thermoplastic biopolymer providing a stiffness and strength alternative to fossil-based plastics. It is also the most promising biodegradable polymer on the market right now, thus gaining a substitute for conservative artificial polymers. Therefore, the current research focuses on synthesizing and mechanical characterization of particlereinforced PLA composites. The hot compression molding technique was used to fabricate PLA-based composites with 0, 2.5, 5, and 7.5 weight % of sawdust, rice husk, and bagasse particle reinforcements to enhance the performance of the PLA. The pellets of PLA matrix were taken with an average size of 3… More >

XINGMIN XU¹, QINGQING SUN², AIRONG XU², XINBAO GUO²

Journal of Polymer Materials, Vol.39, No.1-2, pp. 167-181, 2022, DOI:10.32381/JPM.2022.39.1-2.11

Abstract Silk fibroin (SF) with renewability, biocompatibility and biodegradability shows potential application in various fields including biomedicine, tissue engineering, and wearable electronic devices. Herein, SF is used to exert effective reinforcement of polyvinyl alcohol (PVA) composite film to further improve its practicability. As such, PVA/SF composite films were prepared for the first time using a facile approach. The films were characterized to investigate possible interaction of PVA with SF. Meanwhile, systematic investigations have also been completed to explore the influences of PVA/SF mass ratio on the mechanical properties (tensile strength, elongation at break), biodegradability and biocompatibility, the morphology, crystallinity, chemical structure… More >

Jiangang Lu, Ruifeng Zhao^*, Zhiwen Yu, Yue Dai, Kaiwen Zeng

CMC-Computers, Materials & Continua, Vol.78, No.3, pp. 4453-4469, 2024, DOI:10.32604/cmc.2024.048020

Abstract Time synchronization (TS) is crucial for ensuring the secure and reliable functioning of the distribution power Internet of Things (IoT). Multi-clock source time synchronization (MTS) has significant advantages of high reliability and accuracy but still faces challenges such as optimization of the multi-clock source selection and the clock source weight calculation at different timescales, and the coupling of synchronization latency jitter and pulse phase difference. In this paper, the multi-timescale MTS model is conducted, and the reinforcement learning (RL) and analytic hierarchy process (AHP)-based multi-timescale MTS algorithm is designed to improve the weighted summation of synchronization latency jitter standard deviation… More >

Sepehr Soltani¹, Ehsan Ghafourian², Reza Salehi³, Diego Martín^3,*, Milad Vahidi⁴

Intelligent Automation & Soft Computing, Vol.39, No.1, pp. 93-108, 2024, DOI:10.32604/iasc.2024.042693

Abstract For many years, researchers have explored power allocation (PA) algorithms driven by models in wireless networks where multiple-user communications with interference are present. Nowadays, data-driven machine learning methods have become quite popular in analyzing wireless communication systems, which among them deep reinforcement learning (DRL) has a significant role in solving optimization issues under certain constraints. To this purpose, in this paper, we investigate the PA problem in a -user multiple access channels (MAC), where transmitters (e.g., mobile users) aim to send an independent message to a common receiver (e.g., base station) through wireless channels. To this end, we first train… More >