Sustainable Computing-Informatics & Systems最新文献

{"title":"Smart grid stability prediction using artificial intelligence: A study based on the UCI smart grid stability dataset","authors":"Xuan Wang ,&nbsp;XiaoFeng Zhang ,&nbsp;Feng Zhou ,&nbsp;Xiang Xu","doi":"10.1016/j.suscom.2025.101175","DOIUrl":"10.1016/j.suscom.2025.101175","url":null,"abstract":"<div><div>Maintaining the stability of smart grids (SGs) helps ensure that power systems continue to function well and without interruption, as renewable sources and variable demand rise. Conventional ways of monitoring tend to miss the first signs of instability, prompting the need for more intelligent solutions. This work studies the employment of machine learning (ML) to help classify and forecast SG stability, aiming to improve reliability and systems’ operational efficiency. Six algorithms, Random Forest (RF), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Logistic Regression (LR), and Categorical Boosting (CatBoost), were tested using such robust metrics as accuracy, precision, recall, F1-score, ROC AUC, Log Loss, Cohen Kappa, and Matthews Correlation Coefficient. Performance of the models was increased by using GridSearchCV and Bayesian Optimization (BO) techniques. The finding is that BO-SVM achieved the highest accuracy, precision, recall, F1-score (all by 96.00 %) as well as greatest balanced accuracy and surpassed all the other methods investigated. Moreover, CatBoost and XGBoost had also steady and effective results when used with both optimization techniques. On the other hand, KNN exhibited overfitting and LR failed to capture stability patterns. These results prove that optimized SVM models are very useful for real-time monitoring of superconductor stability. Such models help make wise and prompt decisions which leads to stronger resilience in the smart grid and efficient energy use. Deploying these models under real-time, noisy, and dynamic grid environments for broader applicability would be more beneficial.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101175"},"PeriodicalIF":5.7,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144725089","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-heterogeneous renewable energy scheduling optimization based on time series algorithm and green computing-driven sustainable development","authors":"Chaoran Ma ,&nbsp;Puguang Hou","doi":"10.1016/j.suscom.2025.101173","DOIUrl":"10.1016/j.suscom.2025.101173","url":null,"abstract":"<div><div>The integration of heterogeneous renewable energy sources, such as wind and solar, poses significant challenges to the dynamic economic and environmental dispatch of power systems due to their intermittent and uncertain nature. Efficient coordination between generation and consumption is crucial to ensure stability, reduce emissions, and lower costs. Accurate forecasting of renewable outputs is a critical prerequisite for achieving optimal dispatch decisions. To address this, we propose a hybrid prediction and scheduling framework that leverages time series forecasting to support real-time dispatch optimization. Specifically, we develop a novel prediction model based on a Completely Input and Output-connected Long Short-Term Memory (CIAO-LSTM) network, whose parameters are optimized using an Improved Fruit Fly Optimization Algorithm (IFOA). This approach enhances the model’s ability to capture both linear and nonlinear temporal features and improves convergence through adaptive search strategies. The predicted outputs are then incorporated into a rolling real-time scheduling model that jointly minimizes generation costs and pollutant emissions. Simulation results on a six-unit power system demonstrate that our approach significantly improves prediction accuracy and dispatch performance, reducing average generation costs and emissions by over 8 % and 16 %, respectively. These results confirm the effectiveness of the proposed method in promoting green and sustainable power systems.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101173"},"PeriodicalIF":3.8,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695325","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":"Blockchain-integrated decentralized fault tolerance for secure and energy-efficient multi-cloud interoperability","authors":"V.M. Sivagami ,&nbsp;K.S. EaswaraKumar ,&nbsp;D. Jayanthi ,&nbsp;S. Kalavathi","doi":"10.1016/j.suscom.2025.101170","DOIUrl":"10.1016/j.suscom.2025.101170","url":null,"abstract":"<div><div>Cloud service provider, multi-cloud scheme has become a strategic fashion to maximize reliability, affordability, and performance. To pose major difficulties with regard to fault tolerance, interoperability, security, and muscularity economy. To address these issues, this employment suggests a unique blockchain-integrated decentralized error allowance system. The advice model uses Proof of Stake (PoS) as the consensus chemical mechanism to improve DOE economy while preserving strong security measure and performance criteria. By around 30 %, smart contracts help to automatically reclaim defect, therefore greatly let down migration costs and downtime. To guarantee data integrity and secrecy across heterogenous swarm environs, the model as well flux a multi-layered security computer architecture desegregate homomorphic encryption, Zero-Knowledge Proofs (ZKP), and Decentralized Identity (DIDs). Atomic swop and cross-chain bridgework avail to enable cross-chain interoperability, hence enabling flawless and good data point exchanges with lower limit delay. Validating the achiever of the indicate strategy, the data-based finding point important addition in free energy efficiency, certificate success rate outdo 90 %, and lour migration costs. These results show the hypothesis of the suggested model to change multi-cloud direction strategies, thereby offering a strong ground for future investigations and practical applications.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101170"},"PeriodicalIF":3.8,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703774","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 comprehensive IoT and blockchain-integrated framework for autonomous water management in sustainable urban ecosystems","authors":"R. Sheeba ,&nbsp;Hadeel Alsolai ,&nbsp;Randa Allafi ,&nbsp;K. Nithya ,&nbsp;Munya A. Arasi ,&nbsp;B. Karthikeyan ,&nbsp;D. Sudarvizhi ,&nbsp;S. Vivek","doi":"10.1016/j.suscom.2025.101171","DOIUrl":"10.1016/j.suscom.2025.101171","url":null,"abstract":"<div><div>Different approaches to urbanization, decaying infrastructure, and climate change may blend into multiple pressures on the urban water management system. It would turn the limelight towards the intrinsic weaknesses of the systems in terms of traditional, centralized-inherently reactive, opaque, and unreliable-public systems. This proposed research brings a new decentralized paradigm synergistically utilizing IoT, blockchain technology, and machine learning in mutual respect and strength for resilient urban ecosystems. The architecture consists of IoT sensors for real-time monitoring and data collection, with water quality sensors and flow meters sending data through edge devices to a blockchain network, thereby ensuring integrity, security, and resistance to tampering. Respectively, machine learning algorithms embedded in the system will use historical and real-time data to perform predictive analytics to forecast future water demand and detect water-quality anomalies. This multi-layer architecture allows for real-time monitoring, transparency, automated decision-making, and intelligent resource reallocation. The results show significant improvements: predictive analytics for water demand forecasting achieved an F1-score of 91 %; the blockchain achieved 95 % fault tolerance; and energy efficiency improved by as much as 75 % at low-load conditions. Furthermore, the system provided low-latency communication and high transactions throughput, proving its scalability and applicability in different urban settings.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101171"},"PeriodicalIF":3.8,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144686076","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":"Stability improvement of multimachine power system using DRL based wind-PV-controller","authors":"Deshveer Narwal,&nbsp;Deepesh Sharma","doi":"10.1016/j.suscom.2025.101168","DOIUrl":"10.1016/j.suscom.2025.101168","url":null,"abstract":"<div><div>A significant challenge in modern electric power grids is the stability of power systems, particularly under extreme events such as demand surges and disruptions. Integrating renewable energy into the current system present a viable approach for meeting the growing demand. Furthermore, apart from efficiently meeting the increasing need, these renewable energy systems, with their supplementary circuitry, can substantially improve the stability of the power system. This research suggests a new method that combines deep reinforcement learning (DRL) with a Fractional Order deep Q network (FO-DQN) to address stability problems in multimachine power systems. Incorporating wind and PV systems, which function as STATCOM when necessary, introduces intricacy to the system's dynamics. The proposed DRL based controller facilitates dynamic real-time control of power flow, guaranteeing voltage stability throughout the system. The controller based on DRL is able to autonomously modify the settings of the PV Static Synchronous Compensator (STATCOM) and unified inter-phase power controller (UIPC) operated wind turbine (WT) system. This adjustment helps to provide reactive power compensation and stabilize the system during extreme conditions. This results in a high level of resilience and flexibility. The efficacy of the suggested approach for enhancing stability of multimachine power systems is proven through thorough simulations and comparative analysis. The results demonstrate higher system performance, reduced voltage drop, and optimal reactive power compensation in the presence of diverse operating circumstances and disturbances (fault).</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101168"},"PeriodicalIF":3.8,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694907","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":"Point cloud recognition of street tree canopies in urban Internet of Things based on laser reflection intensity","authors":"Xu Liu ,&nbsp;Qiujie Li ,&nbsp;Youlin Xu ,&nbsp;Shakir Khan ,&nbsp;Fa Zhu","doi":"10.1016/j.suscom.2025.101169","DOIUrl":"10.1016/j.suscom.2025.101169","url":null,"abstract":"<div><div>Light Detection and Ranging (LiDAR) technology, as a core component of the IoT perception layer, has become a research focus for street tree canopy target recognition. However, traditional methods relying on point cloud geometric features often struggle to achieve accurate identification in complex scenarios where tree canopies intertwine with adjacent objects. To address this issue, this study proposes a novel point cloud recognition method based on laser reflection intensity. First, a 2D LiDAR combined with Mobile Laser Scanning (MLS) technology was employed to collect training datasets (distance-intensity and incidence angle-intensity) for constructing an intensity correction model. Subsequently, urban street point cloud intensity data were acquired using a 2D LiDAR-based MLS system, followed by distance and incidence angle correction. Finally, the intensity threshold for canopy recognition was determined based on the probability density distribution of the corrected intensity data. To validate the method’s effectiveness, the intensity threshold calibrated from a 40-meter road segment was applied to another 80-meter segment within the same street scene. The performance of the original and corrected intensity thresholds was then compared. Experimental results demonstrated that the corrected intensity threshold achieved an F1-score of 0.84 for canopy point cloud recognition, representing a 31 % improvement over the original threshold (F1-score: 0.64). This confirms that the proposed method significantly enhances recognition accuracy in complex urban environments.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101169"},"PeriodicalIF":3.8,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653392","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":"Machine learning-based model for predicting freshwater production and power consumption in solar-assisted desalination systems","authors":"Yue Hu","doi":"10.1016/j.suscom.2025.101164","DOIUrl":"10.1016/j.suscom.2025.101164","url":null,"abstract":"<div><div>Traditional modeling techniques frequently fail to address the complex, multi-variable optimization problem that arises when freshwater generation and energy efficiency are combined in greenhouse systems. Resolving this issue is essential to improving the sustainability of controlled agricultural settings, especially in areas with limited water resources or high energy consumption. In order to improve operational planning and system design, this study suggests a strong machine learning-based framework for precisely predicting power consumption and freshwater production in a greenhouse-integrated system. Five-fold cross-validation, hybrid Grey Wolf Optimizer (GWO) tuning, SHAP sensitivity analysis, and Taylor diagrams were used to assess a variety of machine learning models, such as XGBoost, CatBoost, SVR, MLP, KNN, and ElasticNet. The XGBoost-GWO model outperformed the others, obtaining the highest R² values (up to 0.9991) and the lowest RMSE (0.4933 for freshwater, 0.0311 for power). Plus, deep learning models such as LSTM and DNN show limited performance in freshwater prediction with high errors and longer runtimes, whereas XGBoost proves more accurate and computationally efficient for this application. Greenhouse width was found to be the most significant design parameter by feature importance and sensitivity analyses. Additionally, an ideal configuration that produced 99.80 m³ of freshwater per day with a mere 2.75 kWh/m³ energy consumption was found using a multi-objective optimization approach. This combined modeling and optimization method promotes resource efficiency and sustainable agriculture by providing a useful tool for designing greenhouse systems that have significant practical applications in resolving freshwater scarcity in arid and semi-arid areas.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101164"},"PeriodicalIF":5.7,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144829380","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":"Smart home Demand-Side Management Based on rooftop deep learning photovoltaic power forecasting","authors":"Pasquale De Falco ,&nbsp;Giancarlo Sperlí ,&nbsp;Marcello Vestri ,&nbsp;Andrea Vignali","doi":"10.1016/j.suscom.2025.101162","DOIUrl":"10.1016/j.suscom.2025.101162","url":null,"abstract":"<div><div>Price-responsive consumers in smart homes can apply Demand-Side Management to controllable loads, based on the availability of energy produced from rooftop photovoltaic systems and on contractual tariffs, ultimately enhancing household energy efficiency and reducing operational costs. However, several key research gaps remain unaddressed: the limited integration of Photovoltaic power forecasting with optimal load scheduling, the underutilization of Numerical Weather Predictions to improve forecasting accuracy, and the lack of comprehensive scheduling strategies for heterogeneous loads, such as shiftable, curtailable, and sheddable appliances To bridge these gaps we propose an integrated methodology that predicts energy generation and optimizes the load allocation upon energetic and economic criteria. Since low forecast accuracy worsens load scheduling, forecasting systems based on deep learning-based architectures are developed and compared. The novel day-ahead scheduling module is formulated as a Mixed Integer Constrained Nonlinear Programming problem, solved with a Differential Evolution Algorithm. The proposed approach is applied to a real household equipped with a rooftop photovoltaic system. Results show that our method achieves up to 48% additional economic savings and reduces visual and thermal discomfort by six and one orders of magnitude, respectively, compared to an unscheduled operation.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101162"},"PeriodicalIF":3.8,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144695324","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 resource provisioning in cloud data centers","authors":"Manoj Kumar Dixit,&nbsp;Dilip Kumar","doi":"10.1016/j.suscom.2025.101167","DOIUrl":"10.1016/j.suscom.2025.101167","url":null,"abstract":"<div><div>In recent years, energy efficiency has become a challenging issue in large data centers. Energy-efficient resource provisioning manages the usage of each computing resource and shares virtual machines (VMs) so that energy consumption can be reduced. Thus, to maintain energy consumption, the proposed study aims to develop an effective resource provisioning mechanism (Eff-RPM) in cloud data centers. The proposed framework contains the following stages: workload pre-processing, workload clustering, and optimized resource provisioning. Initially, the incoming workloads are pre-processed to remove the noisy and invalid requests. The pre-processing stage allocates a specific ID number for each request, which helps to make the Service Level Agreement (SLA) table for each workload. Then, the pre-processed workloads are clustered through the Enhanced Genetic K-means (EGKM) algorithm. Meanwhile, the enhanced genetic algorithm is hybridized with K-means clustering to categorize the workloads in clouds depending on the quality of service (QoS) requirements. The proposed clustering stage helps to reduce the makespan and computation time. Finally, the new Hybrid Optimal Convolutional Neural Network (HOCNN) model is proposed for provisioning suitable resources to the workloads. Here, the workloads are predicted using a Convolutional Neural Network (CNN), and the Cuckoo Search Optimization (CSO) algorithm is employed for optimally provisioning the resources by regulating parameters like response time, makespan, resource utility, and energy consumption. The proposed Eff-RPM is implemented in the CloudSim platform, and the performances are evaluated against various evaluation criteria and compared to existing methods. On the evaluations, the proposed approach resulted in an overall energy consumption of 76.504 kWh, total cost of 236,001 C$, SLA violation rate of 6.541 %, delay of 6.197 s, resource utilization of 88.922 %, response time of 278.84 s, and makespan of 111.531 s, respectively. As a result, the proposed Eff-RPM has achieved superior performance for resource provisioning against the existing methods.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"47 ","pages":"Article 101167"},"PeriodicalIF":3.8,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144686075","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":"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}