Sustainable Computing-Informatics & Systems最新文献

{"title":"Efficient and adaptive design of RBF neural network for maximum energy harvesting from standalone PV system","authors":"Mohand Akli Kacimi ,&nbsp;Celia Aoughlis ,&nbsp;Toufik Bakir ,&nbsp;Ouahib Guenounou","doi":"10.1016/j.suscom.2025.101083","DOIUrl":"10.1016/j.suscom.2025.101083","url":null,"abstract":"<div><div>This paper deals with a topical topic, the maximum energy harvest of standalone PV system under varying conditions. It introduces a new approach based on the use of artificial intelligence and machine learning to overcome the usual weaknesses of conventional Maximum Power Point Tracking (MPPT) techniques and to improve solutions to meet growing energy demand and further promote sustainable development. The proposal consists of using Radial Basis Function Neural Network (RBFNN) tuned by a PSO algorithm as MPPT controller. The main aim of this combination (RBFNN-PSO) is to achieve the best compromise between the control accuracy and complexity, while using a simple optimization algorithm. This aim is motivated by the potential of the neural networks to learn from any tasks and to generalize the acquired knowledge to other situation never seen before. The proposal reaches a high efficiency and high energy harvesting with a yield greater than 99 %. The performed comparative study with other intelligent techniques from literature prove the superiority and the promising potential of the introduced approach. The developed work presented in this paper is developed with MatLab/Simulink environment.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101083"},"PeriodicalIF":3.8,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143172618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An energy efficient location aware geographic routing protocol based on anchor node path planning and optimized Q-learning model","authors":"K. Bhadrachalam ,&nbsp;B. Lalitha","doi":"10.1016/j.suscom.2025.101084","DOIUrl":"10.1016/j.suscom.2025.101084","url":null,"abstract":"<div><div>A wireless sensor network (WSN) is made up of many nodes that can send sensed data to the base station or sink directly or through intermediary nodes. However, geographically based routing requires accurate sensor node location data. The precise localization of dispersed sensors within a designated region is a critical problem in WSN development. This study proposes a new location-aware geographic routing protocol, which is based on the Q-learning model and anchor node path planning. Initially, the location of an unknown node is detected using an Integrated Received Signal Strength Indicator (RSSI) and Cosine rule-based path planning model. After detecting the unknown nodes, each node is forwarded through a HELLO message to identify the routing neighbour nodes. Then, the Optimal Osprey Q-Learning (O²QL) model is used in multi-objective optimization to choose the best path routing. Then, the Q-learning model's reward function is responsible for both end-to-end latency and energy consumption. Moreover, the Q-learning parameters of the suggested protocol can be adaptively updated to accommodate the high process degrees found in WSNs. Simulations have been conducted to prove the efficacy of the method based on different metrics. The proposed approach has been compared with the existing recently introduced routing protocols in WSN. As a result, the proposed location-aware energy-efficient geographic routing techniques show performance in terms of average end-to-end delay of nodes (2.88), packet loss ratio of nodes (0.058), residual energy of nodes (0.199), average energy consumption of nodes (1.53) and packet delivery rate of nodes (98.96).</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101084"},"PeriodicalIF":3.8,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143172619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Strategic feasibility outlook for blue energy investments using an integrated decision-making approach","authors":"Serkan Eti ,&nbsp;Serhat Yüksel ,&nbsp;Hasan Dinçer","doi":"10.1016/j.suscom.2025.101085","DOIUrl":"10.1016/j.suscom.2025.101085","url":null,"abstract":"<div><div>Conducting feasibility analysis in blue energy investments is very critical to provide performance analysis of the projects. However, a significant portion of the studies in the literature focus on general energy projects. Nevertheless, there are not enough studies for a more specific area such as blue energy. This situation significantly increases the need for this type of priority analysis. Accordingly, the purpose of this study is to identify the most appropriate strategies to increase the effectiveness of the feasibility analysis of blue energy investments via a novel decision-making model. In the first stage of the model, the importance levels of experts are computed using machine learning technique. The second stage includes weighting the feasibility criteria set for blue energy project investment by Fermatean fuzzy entropy. After that, the strategic alternatives for increasing the capacity of blue energy projects are ranked with Fermatean fuzzy CoCoSo. The main contribution of this study to the literature is making a detailed evaluation to generate appropriate strategies for the feasibility analysis of the blue energy investments via a novel decision-making model. The integration of AI system provides some advantages to the proposed model. In this way, the decision matrix is obtained by calculating the importance weights of each expert. This situation allows to have more accurate analysis results. It is defined that the technological infrastructure of the company plays the most critical role (weight: 0.173) when conducting feasibility analysis for blue energy investments. Similarly, it is also identified that the financial performance of the business (weight: 0.172) is also important to conduct a more successful feasibility analysis for blue energy investments. On the other side, the ranking results demonstrate that collaborating with the investment-ready companies for increasing the innovative technologies is the most appropriate strategy to increase the capacity of blue energy projects.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101085"},"PeriodicalIF":3.8,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143172617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic analysis and performance optimization of scalable computing systems in the context of industry 4.0","authors":"John William Vásquez Capacho ,&nbsp;G. Pérez-Zuñiga ,&nbsp;L. Rodriguez-Urrego","doi":"10.1016/j.suscom.2024.101067","DOIUrl":"10.1016/j.suscom.2024.101067","url":null,"abstract":"<div><div>Escalating energy costs and sustainability concerns in high-performance computing (HPC) and industrial-scale systems demand advanced models for energy-efficient operations. Traditional discrete event system (DES) models, while valuable tools, often struggle with the complexities of real-world systems, particularly when dealing with simultaneous events, partial sequences, and false positives. To address these limitations, this paper introduces V-nets, a novel formalism that offers a more robust approach to modeling and analyzing complex event sequences. V-nets excel at handling concurrent events, incorporating temporal constraints, and accurately detecting partial sequences, leading to improved system diagnostics and energy efficiency. By leveraging V-nets, we can gain deeper insights into the behavior of complex systems, identify potential bottlenecks, and optimize resource allocation. This can lead to significant energy savings and improved system performance. For example, in HPC systems, V-nets can be used to monitor the energy consumption of individual components, identify idle resources, and optimize workload scheduling. In industrial settings, V-nets can help detect anomalies in production processes, leading to timely interventions and reduced downtime. The potential applications of V-nets are vast, extending beyond HPC systems to various industrial domains. As AI-driven workloads continue to grow in complexity, V-nets can play a crucial role in monitoring and optimizing energy consumption in these systems. By bridging the gap between theoretical advancements and real-world applications, V-nets have the potential to revolutionize the field of DES modeling and contribute to the development of more sustainable and efficient systems.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"45 ","pages":"Article 101067"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096401","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}

{"title":"Application of nonparametric ML on forecasting the production of a large-scale solar power plant: Kom-Ombo case study","authors":"M. Hammad ,&nbsp;Sarah Khalil ,&nbsp;I.M. Mahmoud","doi":"10.1016/j.suscom.2024.101074","DOIUrl":"10.1016/j.suscom.2024.101074","url":null,"abstract":"<div><div>Renewable Energy grew by 50 % globally in 2023, where three quarters of this energy is coming from solar PVs. The variable production of solar energy needed for PVs makes the prediction of the output power vital for avoiding technological and economic issues. Machine Learning (ML) models were used as a nonparametric approach to predict power output in several studies but only on small-scale solar power plants. This work investigates the implementation of several ML algorithms to predict the PV output power of large-scale solar power plants, where the Kom Ombo 26 MW power plant is taken as a case study. The Liner Regression (LR), Decision Tree (DT), and Random Forest (RF) algorithms were tested, where the LR model showed the lowest RMSE and R² values and was further improved after removing the night hours from the dataset. In addition, the Long Short-Term Memory (LSTM) model showed the highest accuracy when used with the historical records of the Kom Ombo power plant. Finally, the LSTM model was used to predict the PV output power for the Kom Ombo power plant to choose the maintenance day of the plant which resulted in substantial power and profit savings. Similarly to [6] who used Quantile Regression Forests (QRF) on a 2 MW solar power plant, we were able to show that nonparametric ML can be reliable in forecasting power output from a 20 MW solar power plant.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"45 ","pages":"Article 101074"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimating energy consumption of neural networks with joint Structure–Device encoding","authors":"Chaopeng Guo,&nbsp;Shiyu Wang,&nbsp;Ruolan Xie,&nbsp;Jie Song","doi":"10.1016/j.suscom.2024.101062","DOIUrl":"10.1016/j.suscom.2024.101062","url":null,"abstract":"<div><div>The surge in IoT devices has led to an increase in energy consumption, necessitating the optimization of neural networks deployed on these energy-constrained devices to reduce power usage. Although various techniques, such as pruning and quantization, can reduce the size and computational requirements of neural networks, the resulting energy savings still need to be verified through resource-intensive inference processes, which require cumbersome adjustments to measurement devices and neural network deployment. To address these challenges, we propose SDEnergy, a novel approach that combines Structure–Device encoding to quickly and accurately predict the Energy consumption of neural networks across various devices. SDEnergy utilizes graph neural networks to extract structural features of neural networks and employs fully connected networks to extract device features, using their fusion for energy consumption prediction. Experimental validation demonstrates that SDEnergy has established state-of-the-art results on our dataset based on NAS-Bench-101 and various IoT device parameter scenarios, with a mean absolute percentage error of 5.35%.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"45 ","pages":"Article 101062"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving energy efficiency in WSN through adaptive memetic-based clustering and routing for resource management","authors":"Vimalarani C ,&nbsp;CP Thamil Selvi ,&nbsp;B. Gopinathan ,&nbsp;T. Kalavani","doi":"10.1016/j.suscom.2024.101073","DOIUrl":"10.1016/j.suscom.2024.101073","url":null,"abstract":"<div><div>Efficient resource allocation in Wireless Sensor Networks (WSNs) is essential due to the constrained energy resources of sensor nodes and complex network dynamics. Existing clustering and routing methods often fail to optimize energy usage and ensure network stability under varying conditions. This research article introduces the Hybrid Memetic Evolutionary Algorithm (HMEA), which combines adaptive memetic-based clustering and evolutionary optimization to address energy-efficient clustering and routing. The HMEA dynamically selects cluster heads and optimizes transmission paths considering node energy levels and network topology, minimizing energy consumption and extending network lifetime. Simulation results demonstrate that the HMEA outperforms conventional methods, including Particle Swarm Optimization and Genetic Algorithm, in terms of energy efficiency, network throughput, and packet delivery ratio, particularly in large-scale networks. This approach advances robust resource allocation mechanisms for sustainable WSN operations.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"45 ","pages":"Article 101073"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bi-level decision tree-based smart electricity analysis framework for sustainable city","authors":"Tariq Ahamed Ahanger ,&nbsp;Munish Bhatia ,&nbsp;Abdullah Albanyan ,&nbsp;Abdulrahman Alabduljabbar","doi":"10.1016/j.suscom.2024.101069","DOIUrl":"10.1016/j.suscom.2024.101069","url":null,"abstract":"<div><div>The revolutionizing influence of the Internet of Things (IoT) paradigm has greatly enhanced the service-delivery aspects of electricity consumption, allowing for smart energy distribution and trustworthy electric appliances. The current research presents a novel technique for detecting electricity usage in smart homes using IoT technology. Poor electricity distribution has greatly impacted daily life along with inefficient power resource allocation. This research assesses the spatial–temporal efficiency with which power grid operators distribute electrical energy resources. The efficient distribution of energy resources is achieved by calculating the spatial–temporal utilization measure for each residence of a geographical region. Also, to help power grid managers optimize the spatial–temporal allocation of energy resources, a two-level threshold-based decision-tree model is presented. For performance assessment, four smart homes are tracked for 2 months in a simulated environment. Statistical results acquired for Delay (119.61s), Reliability (82.23%), Stability (71.12%), Classification Effectiveness (Precision (95.56%), Sensitivity (95.96%), and Specificity (95.25%)), and Decision-making Efficiency (92.21%) show that the presented approach significantly outperforms state-of-the-art data analysis techniques.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"45 ","pages":"Article 101069"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143135637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing task offloading with metaheuristic algorithms across cloud, fog, and edge computing networks: A comprehensive survey and state-of-the-art schemes","authors":"Amir Masoud Rahmani ,&nbsp;Amir Haider ,&nbsp;Parisa Khoshvaght ,&nbsp;Farhad Soleimanian Gharehchopogh ,&nbsp;Komeil Moghaddasi ,&nbsp;Shakiba Rajabi ,&nbsp;Mehdi Hosseinzadeh","doi":"10.1016/j.suscom.2024.101080","DOIUrl":"10.1016/j.suscom.2024.101080","url":null,"abstract":"<div><div>The Internet of Things (IoT) significantly impacts various industries, enabling better connectivity and real-time data exchange for applications ranging from smart cities to healthcare. Integrating cloud, fog, and edge computing is essential for managing increased data and processing needs as IoT networks become complex. Cloud computing provides extensive storage and powerful computing capabilities but can experience delays due to the distance data must travel. Fog computing addresses these delays by processing data closer to its source, while edge computing reduces them even further by processing data directly on IoT devices. Effective management of these computing layers requires strategic task offloading, which involves moving tasks to the most appropriate computing layer to balance latency, energy consumption, and operational efficiency. Several strategies have been developed to optimize network communication and task offloading, with metaheuristic algorithms emerging as promising approaches. Inspired by natural processes, these algorithms are skilled at searching complex spaces to find near-optimal solutions for efficient and dynamic task offloading. This review provides a detailed analysis of how metaheuristic algorithms optimize task offloading. It evaluates their effectiveness in improving system performance, managing resources, and reducing costs. The review also identifies the current challenges in this area and suggests future research directions to advance this field.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"45 ","pages":"Article 101080"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sustainable supply chain management: A green computing approach using deep Q-networks","authors":"Di Yuan,&nbsp;Yue Wang","doi":"10.1016/j.suscom.2024.101063","DOIUrl":"10.1016/j.suscom.2024.101063","url":null,"abstract":"<div><div>This paper addresses the challenges of resource allocation and inventory management in supply chain systems by constructing an intelligent supply chain optimization model based on Deep Q-Networks (ISCO-DQ), emphasizing eco-efficiency. Initially, the study builds a supply chain model that incorporates supplier-customer relationships, guided by the principles of green computing to minimize environmental impact. The model applies Markov Decision Processes to develop a framework for sustainable supplier inventory control, focusing on reducing waste and optimizing resource usage. Utilizing the function approximation capabilities of Deep Q-Networks, the model not only achieves intelligent resource allocation but also prioritizes energy-efficient practices in inventory management. Experimental results indicate that the ISCO-DQ inventory control model converges to approximately −41,400 and −181,300 after around 100 and 300 cycles, respectively, under customer demand distributions that follow normal distributions. Furthermore, compared to traditional single-period stochastic and fixed-order quantity inventory control models, the total cost of the ISCO-DQ model is reduced by an average of 6.7 % and 16 %, respectively, while minimizing carbon emissions associated with overproduction and excess inventory. Additionally, the ISCO-DQ model significantly mitigates costs arising from demand uncertainty by quickly adapting to fluctuations and optimizing inventory strategies, thereby fostering a circular economy. This demonstrates that the ISCO-DQ inventory control model effectively addresses inefficiencies, inflexibility, and suboptimal resource allocation in conventional supply chain management, ultimately promoting sustainable development and environmental stewardship for enterprises.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"45 ","pages":"Article 101063"},"PeriodicalIF":3.8,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143135636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}