Sustainable Computing-Informatics & Systems最新文献

{"title":"PPAS-MiCs: Peak-power-aware scheduling of fault-tolerant mixed-criticality systems","authors":"Shayan Shokri ,&nbsp;Sepideh Safari ,&nbsp;Shaahin Hessabi ,&nbsp;Mohsen Ansari","doi":"10.1016/j.suscom.2025.101156","DOIUrl":"10.1016/j.suscom.2025.101156","url":null,"abstract":"<div><div>Multi-core platforms have become the dominant trend in designing Mixed-Criticality Systems (MCSs). The most well-known MCS is the dual-criticality system, which consists of high and low-criticality tasks. With the increase in the number of cores, the occurrence rate of faults has also increased in MCSs. For this reason, employing fault-tolerant techniques has become crucial. Although exploiting fault-tolerant techniques can improve system reliability, it might lead to increasing the temperature of the system beyond safe limits. In this paper, we present peak-power-aware scheduling for MCSs that employs the checkpointing technique while guaranteeing the timing, reliability, and thermal design power (TDP) constraints. In the proposed method, first, the minimum number of checkpoints for each task is calculated and assigned to the different execution sections of the tasks. Afterward, the cores are divided into safety-critical and non-safety-critical pairs, and tasks are mapped to cores and scheduled. It should be noted that this is a preliminary division and does not mean isolating the cores from each other. At each dedicated point in the schedule, if the TDP is violated, tasks are shifted from the last checkpoint until this constraint is not violated. Finally, the existing slack times are exploited to improve the QoS and reduce the average power consumption of the system. The proposed method is compared with the state-of-the-art fault-tolerant techniques, resulting in 35.6% and 36.5% improvement in all scenarios and in feasible scenarios, respectively, while the TDP constraint is not violated.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101156"},"PeriodicalIF":3.8,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596504","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 optimization framework to response flexible energy demand based on target market in a smart grid: A case study of greenhouses","authors":"Mehran Salehi Shahrabi","doi":"10.1016/j.suscom.2025.101163","DOIUrl":"10.1016/j.suscom.2025.101163","url":null,"abstract":"<div><div>Unlike many energy-consuming sectors, greenhouses can operate with varying energy inputs while producing crops of different qualities. Supplying greenhouse energy from the main grid faces two main challenges: fluctuating energy prices throughout the day and the risk of planned or unplanned outages. Similarly, relying solely on renewable energy resources is constrained by their intermittent availability. Consequently, this study investigates energy supply planning for greenhouses with flexible demand by leveraging renewable resources within a smart grid. In this respect, a bi-objective energy planning model is developed for greenhouses, aiming to minimize energy consumption costs and maximize crop quality. This model accounts for variable main grid energy prices, the opportunity to sell renewable electricity back to the grid, and limitations on renewable energy supply during specific hours. The extended epsilon-constraint method solves the model, generating non-dominated points that define various production modes. From these results, 9 distinct production modes are presented, allowing decision-makers to select based on preferences such as desired crop quality levels and/or the quantity of electricity sold to the grid. Furthermore, sensitivity analysis is performed under two scenarios: cost reduction and crop quality improvement. Results for the first scenario show that increasing the electricity selling price reduces production costs and increases the amount sold to the main grid. In the second scenario, a significant 25 % reduction in required energy leads to a substantial decrease in production costs, a key finding of this study.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101163"},"PeriodicalIF":3.8,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596183","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":"Maximizing solar energy harvesting efficiency: Optimal hybrid deep neural learning - based MPPT for Photovoltaic systems under complex partial shading conditions","authors":"SeyedJalal SeyedShenava,&nbsp;Peyman Zare,&nbsp;Iraj Faraji Davoudkhani","doi":"10.1016/j.suscom.2025.101159","DOIUrl":"10.1016/j.suscom.2025.101159","url":null,"abstract":"<div><div>The declining viability of fossil fuels and their adverse environmental impacts are accelerating the global transition to Renewable Energy Sources (RESs), with solar energy emerging as a key pillar due to its versatility and scalability. Photovoltaic (PV) systems enable direct solar-to-electric conversion but face challenges such as nonlinear behavior and multiple Local Maximum Power Points (LMPPs) under Complex Partial Shading Conditions (CPSCs). This study introduces an enhanced Maximum Power Point Tracking (MPPT) method based on a hybrid Artificial Neural Network–Improved Incremental Conductance (ANN-IINC) model. The ANN is trained using representative datasets capturing diverse shading patterns to estimate optimal reference voltages dynamically, while the IINC module accelerates convergence with reduced oscillations. To validate the proposed method, three CPSC scenarios are simulated and compared with traditional perturb and observe and INC techniques, as well as recent metaheuristic optimization algorithms. Sensitivity and descriptive statistical analyses confirm that the ANN-IINC approach not only achieves faster convergence (81.9 ms) and higher tracking accuracy (up to 99.9096 %) but also reduces standard deviation in power output by 11.3 %–14.8 % compared to classical methods. Furthermore, confidence intervals for efficiency are narrowed by over 20 %, demonstrating improved robustness and statistical significance. The method's computational complexity is optimized, maintaining real-time applicability without sacrificing precision. A comprehensive adaptive analysis and hyperparameter sensitivity study further reinforce the superiority and practical relevance of the hybrid architecture. The study offers a scalable, stable, and efficient solution to the MPPT problem under dynamic environmental conditions. These results highlight the ANN-IINC technique’s capacity to outperform both classical and metaheuristic MPPT strategies, contributing meaningfully to the advancement of intelligent PV control under CPSCs.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101159"},"PeriodicalIF":3.8,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144580914","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":"Enhancing sustainable agriculture using attention convolutional bidirectional Gated recurrent based modified leaf in wind algorithm: Integrating AI and IoT for efficient farming","authors":"V. Sellam ,&nbsp;N. Kannan ,&nbsp;S. Senthil Pandi ,&nbsp;I. Manju","doi":"10.1016/j.suscom.2025.101160","DOIUrl":"10.1016/j.suscom.2025.101160","url":null,"abstract":"<div><div>Sustainable agriculture is essential for ensuring global food security while mitigating environmental impacts. The possibilities of using remote sensing data and artificial intelligence in agricultural practices emphasize optimizing resource use, minimizing waste, and fostering resilient farming systems to adapt to changing climate conditions in the agriculture field. Multiple studies employed in utilizing remote sensing data and AI for diagnosing disease and environmental monitoring but they face challenges due to factors such as distortions and changes in climates like huge rainfall and extreme droughts affecting the farming environment. Therefore this article develops a novel Attention Convolutional Bidirectional Gated Recurrent based Modified Leaf in Wind Algorithm for assessing the disease of the plants and environmental monitoring. The algorithm leverages diverse datasets including PlantVillage, plantDoc, Soil Type, Advanced IoT Agriculture, and IDADP, and robust data preprocessing techniques such as normalization, standardization, and imbalanced data handling are essential for refining dataset integrity and optimizing model performance. Additionally, the developed model incorporates a convolutional neural network for spatial feature extraction, bidirectional gated-recurrent units for sequential context modeling, and attention mechanisms fuse the Convolutional Neural Network and bidirectional gated-recurrent units, focused on increasing the activity of the proposed network to obtain optimal results, by applying weighting model to each time steps. Moreover, to improve feature integration and optimize model performance, the proposed algorithm incorporates Modified Leaf in Wind optimization strategies. Through experimental validation, the proposed method procures the best performance in four scenarios with a precision of 97.5 % for SC1, 98.5 % for SC2, 96.9 % for SC3 %, and 97.6 % for SC4. The proposed model empowers farmers to make data-driven decisions that enhance productivity.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101160"},"PeriodicalIF":3.8,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144556903","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":"Multi-objective hybrid green anaconda skill optimization enabled energy and cache based QoS aware routing in delay tolerant–IoT network","authors":"Ashapu Bhavani ,&nbsp;Attada Venkataramana ,&nbsp;A.S.N. Chakravarthy","doi":"10.1016/j.suscom.2025.101158","DOIUrl":"10.1016/j.suscom.2025.101158","url":null,"abstract":"<div><div>Delay-Tolerant Network (DTN) is developed to overcome the challenges of environments where classical networking models fail due to unstable connectivity and high latency. The DTN offers stable connections between nodes and operates effectively in scenarios where nodes frequently experience disruptions or only sporadic communication opportunities. However, the classical techniques allowed limited data communication and did not apply to the network with reduced resources and which had low delivery rates and high delays. Therefore, this research aims to develop a Green Anaconda Skill Optimization (GASO) for an eQoS-aware routing solution for a DTN-IoT network. Initially, the DTN-IoT network is simulated by considering energy and mobility models. Then, for predicting the energy, Recurrent Radial Basis Function Networks (RRBFN) is used. After that, Cluster Head (CH) selection is executed by GASO, considering multiple objectives, like cache ratio, residual energy, predicted energy, throughput, distance, trust factors, and delay. Finally, GASO is employed for routing, and the above-mentioned multi-objectives are considered. Here, the GASO is established through the fusion of Green Anaconda Optimization (GAO) and Skill Optimization Algorithm (SOA). The evaluation results highlight that the GASO accomplished a reduced distance of 0.253 m, low energy consumption of 0.783 J, and minimal delay of 0.270 sec, with an increased throughput of 0.313 Mbps.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101158"},"PeriodicalIF":3.8,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144534814","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":"eSMARTGreen (ESG): A scalable IoT-Based architecture for multi-greenhouse management","authors":"Fatima Abou-Mehdi-Hassani ,&nbsp;Atef Zaguia ,&nbsp;Darine Ameyed ,&nbsp;Hassan Ait Bouh ,&nbsp;Abdelhak Mkhida","doi":"10.1016/j.suscom.2025.101152","DOIUrl":"10.1016/j.suscom.2025.101152","url":null,"abstract":"<div><div>Concerns about agricultural productivity and sustainability have driven the need for smart greenhouse architectures. However, significant challenges remain in ensuring seamless data exchange, interoperability, and efficient management across multiple greenhouses. This paper introduces the eSMARTGreen (ESG) model, a novel IoT-based smart greenhouse architecture designed for scalable multi-greenhouse management. ESG features fault-tolerant, modular, and flexible deployment strategy, integrating a robust decision-making system and an interoperable framework aligned with ISO/IEC 30141 standards. The ESG model was validated through a simulation conducted using CPN Tools across a network of five greenhouses. Performance metrics showed low average latencies (19–25 ms) and reception rates of up to 72 %, confirming ESG’s responsiveness and communication efficiency under diverse operational conditions. By facilitating seamless coordination and automation, ESG contributes to greater efficiency and sustainability in smart farming. Future applications of ESG could include predictive maintenance, adaptive climate control, large-scale deployment in agricultural clusters, and integration with renewable energy systems to further enhance sustainability and operational efficiency.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101152"},"PeriodicalIF":3.8,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144472260","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":"Energy-efficient cloud-edge collaborative model integrating digital twins and machine learning for scalable and adaptive distributed networks","authors":"Lei Han,&nbsp;Min Lei,&nbsp;Guilin He,&nbsp;Yangyang Li,&nbsp;Yaopeng Zhao","doi":"10.1016/j.suscom.2025.101157","DOIUrl":"10.1016/j.suscom.2025.101157","url":null,"abstract":"<div><div>The exponential growth of distributed networks, as seen in smart grids, IoT, and industrial automation, have added to the demands for effective and adaptive optimization systems. Traditional cloud solutions, while successful in providing global insights and scalability, often suffer from high latency and limited responsiveness, whereas edge-based models excel at instant decision making but lack global synergy and scale. In an effort to overcome these constraints, this paper proposes a novel Cloud-Edge Collaborative Optimization Framework, which leverages the latest machine learning and digital twin algorithms, to scale up distribution networks. The model relies on Long Short-Term Memory (LSTM) networks at the edge layer to forecast traffic in real time and make local decisions, and Multi-Agent Reinforcement Learning (MARL) at the cloud layer to coordinate resources across the globe. Digital twins facilitate real-time flexibility, dynamic simulation and feedback for continuous improvement. This proposed model was extensively tested against actual network datasets. We noted a 50 % reduction in latency compared to cloud-only architectures, with latency on average, baselined at 35.34 ms, reduced to 17.67 ms; additionally, we noted 23 % more resource utilization compared to edge-only setups based on the average of 10 simulation runs. We had real world IoT traffic data for the experimentation with throughput of 50–100 Mbps and PDR greater than 90 % (consistently), which demonstrates that the network operated robustly under changing conditions; we averaged the results for reliability and significance. This study provides an ideal foundation for future work on digital-twin-enhanced cloud-edge architectures.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101157"},"PeriodicalIF":3.8,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144472259","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":"A LIME-LSTSNM approach based green building sustainability prediction using BIM design","authors":"Yan Xia ,&nbsp;Yaning Li ,&nbsp;Siqin Liu","doi":"10.1016/j.suscom.2025.101155","DOIUrl":"10.1016/j.suscom.2025.101155","url":null,"abstract":"<div><div>This research presents a climate change-based parameter optimisation approach for sustainable green building design. The process begins with a Building Information Modeling (BIM)-based design, followed by a Design-Builder simulation. Climatic data is collected and pre-processed, and building parameters are optimized using SA2O, considering this data. BIM-based building parameters and the optimized data are then extracted. The simulation output, along with sensor and historical data, are fused using the Multiresolution Kalman Filter (MKF) technique. Incomplete data is handled with Penalized K-Log Euclidean Neighbor (PKLEN), followed by season-based grouping using KMA. Non-linear dynamics are analyzed, and features are extracted from both the grouped and non-linear data. The sustainability factor is predicted using Local Interpretable Model-agnostic Explanations (LIME), with Long Short-Term Skip Norm Memory (LSTSNM), and feedback is provided to optimise the building parameters for sustainable green building design. Experimental results show that this model achieved an accuracy of 98.24 %, demonstrating the effectiveness of the proposed approach in enhancing sustainability in building design while considering climate change.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101155"},"PeriodicalIF":3.8,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144501505","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":"Decentralized energy-efficient microgrid control Using Graph neural networks and LSTM-based Event-Triggered control","authors":"Xiaoqian Meng,&nbsp;Yajie Zhao,&nbsp;Sijia Zheng,&nbsp;Zi Ye,&nbsp;Heping Wang","doi":"10.1016/j.suscom.2025.101154","DOIUrl":"10.1016/j.suscom.2025.101154","url":null,"abstract":"<div><div>As microgrid systems become more complex and interconnected, traditional control strategies face significant challenges in terms of scalability, efficiency, and responsiveness. Existing models, often relying on time-triggered approaches, result in excessive communication, energy waste, and slower system responses. The main purpose of this work is to formulate a decentralized control architecture that communicates better, regulates voltage and frequency, and stabilizes the microgrids. To address these limitations, this research introduces an innovative decentralized control framework that combines Graph Neural Networks (GNNs) and Long Short-Term Memory (LSTM) networks, integrated with Event-Triggered Control to optimize microgrid operations. This methodology applies GNNs to capture the spatial dependencies among microgrid components like generators, storage, and loads. Meanwhile, the LSTMs identify the temporal dynamics associated with variations in load and generation. System control actions are then triggered only when necessary, hence reducing communication overhead considerably. The results demonstrates 55 % less communication load was reported, voltage regulation accuracy increased by 45 %, and other efficiency measures for frequency regulation improved by 35 %. Along with these, other performance metrics indicate a 30 % improvement of the Voltage Stability Index (VSI) going from 0.47 to 0.33 and lowering the Frequency Regulation Error (FRE) by 20 % from 4.5 % to 3.6 %. All of which consolidated the evidence of the efficiency of the approach suggested to control microgrid operations in a real-time adaptive energy-efficient manner. These findings highlight the powerful combination of GNNs and LSTMs for achieving adaptive, energy-efficient, and real-time control in decentralized microgrid systems.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101154"},"PeriodicalIF":3.8,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144479965","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":"DEEPCO-RIS: Joint BD-RIS and hybrid NOMA/OMA optimization for energy-efficient vehicular networks","authors":"Nada Alzaben ,&nbsp;Nadhem Nemri ,&nbsp;Wahida Mansouri ,&nbsp;Othman Alrusaini ,&nbsp;Mukhtar Ghaleb ,&nbsp;Jihen Majdoubi","doi":"10.1016/j.suscom.2025.101145","DOIUrl":"10.1016/j.suscom.2025.101145","url":null,"abstract":"<div><div>Next-generation vehicular networks require wireless infrastructures that deliver ultra-reliable, energy-efficient, and low-latency communication under highly dynamic conditions. Traditional RIS-aided and hybrid NOMA/OMA designs face critical limitations, including rigid phase control, high successive interference cancellation (SIC) complexity, and limited adaptability to rapid vehicular mobility. To address these challenges, this paper proposes <strong>DEEPCO-RIS</strong> (Dinkelbach-Enhanced Energy-Efficient Optimization with Beyond-Diagonal RIS), a unified optimization framework that integrates BD-RIS phase configuration, hybrid NOMA/OMA access mode selection, user scheduling, and power allocation. These components are jointly optimized under realistic constraints, including SIC feasibility, power budgets, RIS energy costs, and QoS guarantees. The energy efficiency maximization problem is formulated as a mixed-integer non-convex program and solved using a modular approach combining Dinkelbach’s method, block coordinate descent, successive convex approximation, and manifold-based optimization for BD-RIS tuning. Extensive simulations demonstrate that DEEPCO-RIS achieves up to 22 Mbits/Joule energy efficiency, maintains outage probabilities below 6% even under stringent QoS targets, and exhibits strong robustness against SIC imperfections and network load variations. These results establish DEEPCO-RIS as a scalable and sustainable solution for next-generation vehicular communication networks.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101145"},"PeriodicalIF":3.8,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144271255","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}