Sustainable Computing-Informatics & Systems最新文献

{"title":"A predominant intrusion detection system in IIoT using ELCG-DSA AND LWS-BiOLSTM with blockchain","authors":"Basava Ramanjaneyulu Gudivaka ,&nbsp;Rajya Lakshmi Gudivaka ,&nbsp;Raj Kumar Gudivaka ,&nbsp;Dinesh Kumar Reddy Basani ,&nbsp;Sri Harsha Grandhi ,&nbsp;Sundarapandian Murugesan ,&nbsp;M.M. Kamruzzaman","doi":"10.1016/j.suscom.2025.101127","DOIUrl":"10.1016/j.suscom.2025.101127","url":null,"abstract":"<div><div>The growing connectivity of Industrial Internet of Things (IIoT) systems has increased cyber threats, necessitating early detection of intrusions. However, existing systems often lack focus on intermediate and continuous multifactor authorization between IIoT and Industrial Control Systems (ICS). To overcome this, an efficient IDS for IIoT using an Exponential Linear Congruential Generator - Digital Signature Algorithm (ELCG-DSA) and Log Wave Sigmoid-Bidirectional Once Long Short-Term Memory (LWS-BiOLSTM) is proposed. Initially, the industry and vehicle details are registered in the blockchain network, and the Polychoric Entropy Correlation-Tiger Hashing Algorithm (PEC-Tiger) generates hash codes through smart contract creation. From the generated hash codes, a partial digital signature is created by using the ELCG-DSA technique. After login, the registered details are processed for enhancing security using Montgomery Modulo Curve Cryptography (MMCC). Then, the details are verified by using PEC-Tiger, and if the hash code matches, the key generation centre is notified for the creation of a fully digital signature. After verification, the Luus–Jaakola Sequence-based Pelican Optimization Algorithm (LJS-POA) is applied for load balancing. Next, the data security is verified in the IDS training set, in which the features are extracted from preprocessed data. Then, the Synthetic Minority Oversampling Technique (SMOTE) is utilized for data balancing, and LWS-BiOLSTM is implemented to classify attacks. Furthermore, the attacked data is blocked, and non-attacked data is stored in the ICS through digital signature verification. Thus, the experimental results of the proposed framework outperform the other conventional techniques by achieving 98.78 % accuracy and 98.71 % security level.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101127"},"PeriodicalIF":3.8,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143873980","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 energy harvesting techniques for underwater aquatic systems with multi-source and low-energy solutions","authors":"S. Jayanthi ,&nbsp;R. Lakshmana Kumar ,&nbsp;P. Punitha ,&nbsp;BalaAnand Muthu ,&nbsp;C.B. Sivaparthipan","doi":"10.1016/j.suscom.2025.101126","DOIUrl":"10.1016/j.suscom.2025.101126","url":null,"abstract":"<div><div>Underwater Internet of Things (IoT) systems are essential for monitoring and conserving aquatic ecosystems. These systems are deployed with limited energy resources, harsh environmental conditions and high energy consumption during communication. Standalone solar or wave-based energy harvesting techniques are insufficient because of ecological conditions and variable energy availability. In addition, conventional communication protocols are power-hungry and limit the operation time of underwater nodes. This work introduces a strong, energy-efficient combination of Multi-Source Energy Harvesting Systems and Low-Energy Communication Protocols. The proposed approach will ensure constant energy flow irrespective of the submarine's changing environment by intermixing wave energy with thermal energy, microbial fuel cells, and backup solar systems. The supplementary alternative energy sources avoid the need for batteries, which could result in sustainable operations. Additionally, incorporating low-power communication techniques such as Frequency Shift Keying (FSK) and sleep-wake scheduling significantly reduces energy consumption during data transmission. It is the most power-intensive operation in IoT networks. The proposed work addresses gaps in existing energy harvesting and communication frameworks by optimizing energy generation and consumption. This dual approach enhances the sustainability of underwater IoT systems and improves reliability in diverse and unpredictable aquatic environments. The proposed low-energy communication protocol achieves a transmission success rate of 98.5 %, energy harvesting efficiency of 90 %, and a battery lifetime of over 72 h, optimized for underwater environments.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101126"},"PeriodicalIF":3.8,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851450","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":"Deep reinforcement learning-driven intelligent portfolio management with green computing: Sustainable portfolio optimization and management","authors":"Yi Xu","doi":"10.1016/j.suscom.2025.101125","DOIUrl":"10.1016/j.suscom.2025.101125","url":null,"abstract":"<div><div>Portfolio management remains a key area in quantitative trading. To address limitations in existing deep reinforcement learning (DRL)-based models, which fail to adapt trading strategies and properly utilize supervisory information, we propose a Dynamic Predictor Selection-based Deep Reinforcement Learning (DPDRL) model. The DPDRL model integrates multiple predictors to forecast stock movements and dynamically selects the most accurate predictions, optimizing investment allocation via a market environment evaluation module. Our model was evaluated using daily candlestick data from the SSE 50 and CSI 500 indices. The results show that DPDRL outperforms other models in key evaluation metrics: it achieves a 48.99 % Annualized Rate of Return (ARR), a Sharpe ratio of 2.34, an Annualized Volatility (AVoL) of 0.1390, and a Maximum Drawdown (MDD) of 8.21 %, significantly improving risk-return performance. Ablation experiments confirm the contributions of the dynamic predictor selector and market evaluation module to the model's accuracy and decision-making quality.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101125"},"PeriodicalIF":3.8,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817181","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 tri-objective model for cloudlet server placement problem in wireless metropolitan area networks","authors":"Bahareh Bahrami ,&nbsp;Mohammad Reza Khayyambashi","doi":"10.1016/j.suscom.2025.101124","DOIUrl":"10.1016/j.suscom.2025.101124","url":null,"abstract":"<div><div>To reduce latency and save energy, cloudlet computing enables tasks to be offloaded from user equipment to Cloudlet Servers (CSs). Determining the optimal number of CSs and the appropriate locations for their placement are two major challenges in building an efficient computing platform. Placing a CS at the closest location to the user can improve the QoS. Additionally, providing additional CSs to cover each user ensures that the user's needs are met even if the designated server is unable to provide services. However, to minimize energy consumption and costs, service providers tend to use a minimum number of CSs. Since the coverage zones of different CSs may overlap, fewer additional servers need to be deployed in such areas. This paper examines the problem of CS placement in a Wireless Metropolitan Area Network (WMAN) and introduces a three-objective model that aims to optimize transmission distance, coverage with overlap control, and energy consumption. To obtain an appropriate Pareto front, the performance of the NSGA-II, binary MOPSO, and binary MOGWO algorithms is examined through four different scenarios under the Shanghai Telecom dataset. Comparing the results of the Hyper-Volume (HV) indicator reveals that the NSGA-II algorithm has higher values in all studied scenarios. A higher HV value means that the solution set is closer to an optimal Pareto set. In the best and worst case, the HV values for the NSGA-II were equal to 0.2275 and 0.1883, respectively.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101124"},"PeriodicalIF":3.8,"publicationDate":"2025-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143799113","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":"IoT-based optical sensor network for precision agriculture","authors":"Amit Sharma ,&nbsp;Diksha Srivastava ,&nbsp;Ramkumar Krishnamoorthy ,&nbsp;Sanjay Kumar Sinha ,&nbsp;P. Jhansirani ,&nbsp;Amit barve","doi":"10.1016/j.suscom.2025.101112","DOIUrl":"10.1016/j.suscom.2025.101112","url":null,"abstract":"<div><div>Precision agriculture is a modern agricultural method that employs state-of-the-art technology and data-driven decision-making to increase yields. In this context, there is much potential to improve agricultural operations by integrating Internet of Things devices and optical sensors. The accurate data extraction and analysis provided by sensor networks and Machine Learning based tracking devices are in high demand. This study aims to promote intelligent farming while lowering agricultural risks. Insects and other pathogens can cause plant illnesses, which may decrease yield output if not handled promptly. Therefore, in this research, we provide a novel Artificial Swarm Fish Optimized Naïve Bayes technique to monitor the soil's quality and guard against diseases that affect cotton leaves. The present study uses Internet of Things devices with optical sensors to track several metrics vital to crop development and health. These sensors record information about temperature, humidity, light intensity, chlorophyll content, and other important environmental variables. The acquired data is then wirelessly communicated to a centralized server, where the suggested approach is used to process and analyze the data. After identifying the infection, through an Android app. Soil parameter like humidity, temperature, and moisture may be presented with the chemical level in a container using the Android app. The power source and chemical sprinkler system may be managed by turning the relay on or off using an Android app. The experimental results show that the suggested strategy performs better when compared to conventional methods of illness detection.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101112"},"PeriodicalIF":3.8,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906112","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 packet routing and security in MANETs with the H-MAntnetSVM algorithm for energy efficiency and blackhole detection","authors":"Kalaiselvi Gopalasamy ,&nbsp;Kavitha Govindarajan Muthaiya","doi":"10.1016/j.suscom.2025.101123","DOIUrl":"10.1016/j.suscom.2025.101123","url":null,"abstract":"<div><div>With increasing use of mobile adhoc networks (MANETs) in various applications, the demand for powerful routing protocols has also surged to cater for possible failures or security threats within the network. The operation of efficient packet routing proves highly essential in maintaining reliable communication in MANETs. Energy efficiency plays a crucial role in determining the suitability of a routing technique in MANETS. Packet transmission can be threatened by many types of attacks as Black Hole, gray hole, and sybil attacks. This research proposes a novel hybrid Antnet and Support Vector Machine-The H-MAntnetSVM routing algorithm for energy-efficient routing and Black Hole detection of optimal routing solution. It is basically an adaptive machine learning algorithm that makes the overall network function more effectively in shifting scenarios. The Antnet protocol increases energy usage and provides effective packet routing, while the integration of SVM identifies alibes and basically isolates them so that they do not disturb the routing process. The results obtained with the proposed method show 92.31 % accuracy in detecting the Black Hole attack and 75 % improvement in throughput along with 13.34 % enhancement in the packet delivery ratio. This gives a prominent development in terms of network performance and safety against Black Hole threats.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101123"},"PeriodicalIF":3.8,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835145","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":"Improved sensor localization with intelligent trust model in heterogeneous wireless sensor network in Internet of Things (IoT) environment","authors":"Priyan Malarvizhi Kumar ,&nbsp;Tayyaba Shahwar ,&nbsp;C. Gokulnath","doi":"10.1016/j.suscom.2025.101122","DOIUrl":"10.1016/j.suscom.2025.101122","url":null,"abstract":"<div><div>Heterogeneous Wireless Sensor Network (HWSN) based Internet of Things (IoT) applications are highly trending. It also consists of serious challenges in improving the network longitivity and security regarding data processing and communication. In earlier research several algorithms and models were introduced to enhance the performance of HWSN network in various applications in terms of energy saving process. But still management of a huge number of devices in IoT is under an open research area. Still, it needs improvement in energy efficiency improvisation and device safety. To improve the overall performance of the HWSN network in IoT background the authors of this paper proposed an improved sensor localization with an intelligent trust model in HWSN (ISL-ITMH) network. The major categories of this proposed ISL-ITMH include data transmission process, energy consumption model, trust based communication among the devices in the network and threshold-based energy model. With these processes' presence, communication among each device in the network is effectively analyzed and monitored so that both the trust calculations and energy efficiency is maximum and that helps to attend maximum performance in data transmission in the HWSN network. The implementation of this concept is demonstrated in the software NS3 and certain parameters are measured for the result analysis: energy efficiency, packet delivery ratio, routing overhead, trust score, network throughput and end to end delay. From the result outcome, the proposed ISL-ITMH obtained results which increases the energy efficiency, throughput and data delivery rate throughout the entire iteration compared with the earlier baseline methodologies.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101122"},"PeriodicalIF":3.8,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843898","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":"Joint deep reinforcement learning strategy in MEC for smart internet of vehicles edge computing networks","authors":"Jiabin Luo ,&nbsp;Qinyu Song ,&nbsp;Fusen Guo ,&nbsp;Haoyuan Wu ,&nbsp;Hafizan Mat Som ,&nbsp;Saad Alahmari ,&nbsp;Azadeh Noori Hoshyar","doi":"10.1016/j.suscom.2025.101121","DOIUrl":"10.1016/j.suscom.2025.101121","url":null,"abstract":"<div><div>The Internet of Vehicles (IoV) has a limited computing capacity, making processing computation tasks challenging. These vehicular services are updated through communication and computing platforms. Edge computing is deployed closest to the terminals to extend the cloud computing facilities. However, the limitation of the vehicular edge nodes, satisfying the Quality of Experience (QoE) is the challenge. This paper developed an imaginative IoV scenario supported by mobile edge computing (MEC) by constructing collaborative processes such as task offloading decisions and resource allocation in various roadside units (RSU) environments that cover multiple vehicles. After that, Deep reinforcement Learning (DRL) is employed to solve the joint optimisation issue. Based on this joint optimisation model, the offloading decisions and resource allocations are gained to reduce the cost obtained in end-to-end delay and expense of resource computation. This problem is formulated based on the Markov Decision Process (MDP) designed functions like state, action, and reward. The proposed model's performance evaluations and numerical results achieve less average delay for 30 vehicle nodes in simulation.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101121"},"PeriodicalIF":3.8,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817182","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 Unscented Transformation based approach for probabilistic design of Wide-Area Damping Controllers","authors":"Wesley Peres","doi":"10.1016/j.suscom.2025.101116","DOIUrl":"10.1016/j.suscom.2025.101116","url":null,"abstract":"<div><div>Low-frequency oscillations with insufficient damping can compromise the integrity of power systems. Various control mechanisms exist to mitigate these oscillations, with Wide Area Damping Controllers (WADC) being notably efficient by utilizing remote signals captured by Phasor Measurement Units. A primary challenge in developing a WADC framework is the latency associated with transmitting these remote signals. This challenge is exacerbated by uncertainties, making deterministic methods for WADC tuning potentially impractical. This study introduces an optimization methodology for the probabilistic design of a WADC that accounts for uncertainties in power loads and signal transmission delays. This methodology incorporates the likelihood of meeting security and stability criteria as constraints and employs Particle Swarm Optimization and Unscented Transformation for problem resolution. The efficacy of the proposed method is demonstrated through its application to a Brazilian test system, highlighting its promising results in terms of precision and computational efficiency compared to the Monte Carlo simulation.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101116"},"PeriodicalIF":3.8,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143738663","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":"Advanced frequency stabilization framework for multi-area renewable energy grids with EV aggregator support: A multi-stage control perspective","authors":"Muhammad Inshal Shahzad ,&nbsp;Muhammad Majid Gulzar ,&nbsp;Salman Habib ,&nbsp;Md Shafiullah ,&nbsp;Aqsa Shahzad ,&nbsp;Muhammad Khalid","doi":"10.1016/j.suscom.2025.101120","DOIUrl":"10.1016/j.suscom.2025.101120","url":null,"abstract":"<div><div>In the modern world, the surge of renewable energy has become a focal point, drawing global attention due to its ability to merge cost-effectiveness with sustainability. This shift has made renewable energy an inescapable component of our power grids. A fresh approach is being proposed for load frequency control (LFC) in multi-area power systems, integrating diverse energy sources like photovoltaic (PV), electric vehicles, wind turbines, and thermal plants. This study dives deep into the complex domain of control systems by examining the intercommunication between multi-stage controllers, specifically comparing the 2DOF proportional integral and derivative with filter-PI (2 Degrees of Freedom PIDn-PI) models against the classic PI and 2DOF-PIDn controllers. The key differentiator here lies in introducing an enhanced coyote optimization algorithm (ECOA), aimed at determining the optimal parameters for these advanced controllers. A unique facet of this research is its inclusion of uncertainty, addressing variability by allowing the system parameters to fluctuate within a range of ± 40 %. The robustness of the suggested controllers is tested under dynamic load changes, with these variations applied independently across multiple regions. Two distinct test scenarios are employed, each subject to varying disturbances, to gauge the controllers' adaptability. The operational restrictions of the governor dead band (GDB) impact on the reheat thermal governor unit and generation rate constraint (GRC) in the reheat thermal generating units are simulated using the proper dynamic models. This research includes GDB after the governor unit and GRC after re-heat unit and studies the effect of nonlinearity in power system. CTD is added before the controller and because, in a realistic scenario, there is a time delay in communication with the system. So, the proposed controller helps to give the results as close as the real-time scenario. The findings reveal that by incorporating the GRC, GDB and CTD, the oscillations are damp successfully and even rise under uncertainty situations. The stability analysis also performs the proposed technique upon comparison with previously established methods. The simulated results imply that the proposed multi-staged 2DOF PIDn-PI control system, optimized by ECOA, exhibits remarkable efficiency and resilience. For instance, in case of perturbation in the system, the cumulative settling time of the proposed controller is 1.137 sec while compared with GA-PI, PSO-PID, ABC-PIDn, COA-PI, COA-PIDn, MPA-PIDn has settling time of 28.972 sec, 26.42 sec, 24.52 sec, 17.68 sec, 15.125 sec and 14.01 sec respectively. Its ability to manage load frequency control across multi-area power systems sets it apart, offering a sophisticated solution to the complexities of modern energy management.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":"46 ","pages":"Article 101120"},"PeriodicalIF":3.8,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143777337","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}