Sustainable Computing-Informatics & Systems最新文献

Network security situation assessment (NSSA) is imperative and active defense technology in the network security situation. By examining NSSA data, one can examine the threat of network security and examine the network attack phase and hence fully grasp the complete network security situation. With the quick design of 5 G, the cloud model and Internet of things (IoT), the network platform is increasingly complicated and resulting in diversity of network threats which discover the accuracy. Thus, a new blockchain based cyber-security threat intelligence (CTI) and situational awareness system is devised for intrusion alert prediction. A blockchain-based CTI model is considered where data acquired are allowed to linear normalization. Here, the cyber situational awareness engine is used for alert segregation, which is implemented with entropy weighting power k means algorithm wherein weights generated during alert segregation are updated using Adaptive Transit Search (ATS). Then, the feature selection is implemented using hybrid Soergel and Lorentzian. The selected features are fed to Deep Maxout Network (DMN) for performing intrusion alert prediction. Finally, the cyber attack mitigation is carried out by blacklisting based on predicted result. The modified DMN outperformed with highest F-measure of 95.2%, precision of 96.9% and recall of 94.7%.

Under the background of "carbon neutrality ", data center enterprises are confronted with the challenges of high energy costs and the need to manage carbon emissions. Compared with traditional energy sources, renewable energy possesses the advantages of being low-carbon and cost-effective, making it an essential avenue for data centers to enhance their utilization of renewable energy. By employing a spatio-temporal scheduling method for computing power load, data center enterprises can maximize the benefits of renewable energy, achieve low-carbon and cost-effective operation, and enhance the consumption of renewable energy. This study developed a spatio-temporal scheduling model for computing load in data centers, with a specific focus on optimizing the utilization of renewable energy while considering the goals of low-carbon emissions and cost-effectiveness. A two-stage spatio-temporal scheduling algorithm (ESTS) was designed and implemented, and three sets of experiments were conducted to assess the effectiveness and applicability of offline load scheduling using offline load data from Alibaba's cluster-trace-v2018. The results demonstrate that the proposed scheduling method can achieve a significant reduction of carbon emissions by 70% and operating costs by 40% across various scenarios. Moreover, during the summer season when renewable energy is abundant, the application of this scheduling method in a single data center can effectively achieve the objectives of managing low-carbon emissions and minimizing costs.

Estimating the parameters of a Photovoltaic (PV) cell is crucial, given the significant integration of the PV systems into electrical power systems. One of the primary challenges in the estimation of PV cell parameters is identifying a generalized method applicable to any PV system, irrespective of environmental variations and power ratings. This paper introduces a novel application of an optimized deep neural network designed to estimate the parameters of the PV systems across a range of temperatures, irradiance values, and PV module ratings. The network undergoes a training process by utilizing data obtained from the PV module block located within the Simulink library. In order to evaluate the effectiveness of the proposed methodology, the network is subjected to a series of assessments. These assessments encompass the utilization of PV cell data from the Simulink library, comparisons with recently developed methods, and practical evaluations using experimental PV cell data to estimate the PV cell parameters. The findings underscore the simplicity and precision of the proposed method across diverse PV cells.

With the digitization of the entire world and huge requirements of understanding unknown patterns from the data, clustering becomes an important research area. The quick and accurate division of large datasets with a range of properties or features becomes challenging. The parallel implementation of clustering algorithms must satisfy stringent computational requirements to handle large amounts of data. This can be achieved by designing a GPU based optimal computational model with a heuristic approach. Swarm Intelligence (SI), a family of bio-inspired algorithms, that has been effectively applied to a number of real-world clustering problems. The Gravitational Search Algorithm (GSA) is a heuristic search optimization approach based on Newton's Law of Gravitation and mass interactions. Although it has a slow searching rate in the last iterations, this strategy has been proved to be capable of discovering the global optimum. This paper presents GPU based hybrid parallel algorithms for data clustering. A newly developed, hybrid Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA) i.e., PSOGSA achieves the global optima. PSOGSA utilizes novel training methods for enhanced Neural Networks (NN) in order to examine the efficiency of algorithms and resolves the challenges of trapping in local minima. This also shows the sluggish convergence rate of standard evolutionary learning algorithms. The Nearest Neighbour Partition (Partitioning of the Neighbourhood) algorithm can be used to improve the performance of NN. A parallel version of Hybrid PSOGSA with NN is implemented to achieve optimal results with better computational time. Compared to the CPU-based regular PSO, the suggested Hybrid PSOGSA with NN achieved optimal clustering with 71% improved computational time.

The deployment of mobile renewable energy charging stations plays a crucial role in facilitating the overall adoption of electric vehicles and reducing reliance on fossil fuels. This study addresses the dynamic capacitated facility location problem in mobile charging stations from a sustainability perspective. This paper proposes Two-stage stochastic programming with recourse that performs well for this application, and the location of the mobile renewable energy charging station (MRECS) management addresses the complex dynamics of reusable items. To solve this problem, we suggested dealing with differential evolutionary (DE) and DE Q-learning (DEQL) algorithms, as two novel optimization and reinforcement learning approaches, are presented as solution approaches to validate their performance. Evaluation of the outcomes reveals a considerable disparity between the algorithms, and DEQL performs better in solving the presented problem. In addition, DEQL could minimize the total operation cost and carbon emission by 7% and 20%, respectively. In contrast, the DE could decrease carbon emissions and total operation costs by 5% and 2.5%, respectively.

Nowadays, the capability to remotely monitor indoor and outdoor environments would allow to reduce energy consumption and improve the overall management and users’ experience of network application systems. The most known solutions adopting remote control are related to domotics (e.g., smart homes and industry 4.0 applications). An important stimulus for the development of such smart approaches is the growth of the Internet of Things (IoT) technologies and the increasing investment in the development of green houses, buildings, and, in general, heterogeneous environments. While the benefits for the humans and the environment are evident, a pervasive adoption and distribution of remote monitoring solutions are hindered by the following issue: modeling, designing, prototyping, and further developing the remote applications and underlying architecture require a certain amount of time. Moreover, such systems must be often customized on the basis of the need of the specific domain and involved entities. For such reasons, in this paper, we provide the experience made in addressing some relevant indoor and outdoor case studies through IoT-targeted tools, technologies and protocols, highlighting the advantages and disadvantages of the considered solutions as well as insights that can be useful for future practitioners.

Load balancing effectively distributes network load and balances the load during the scheduling and allocation process. Hence various load balancing techniques in task scheduling and resource allocation along with VM migration has been presented previously but they have a heavy load on some VM and violate cloud service level agreement with a single point of failure. Therefore, a novel Intelligent PSO-based Feedback Controller has been proposed with regulated Scheduling, Allocation, and VM migration to perform optimal load balancing. In this proposed technique, a novel Intelligent Weighted filtering based PSO Approach is used to reduce computation time during task scheduling and resource allocation. This approach uses a multi-objective PSO algorithm with Pareto dominance to achieve high quality of service, throughput, scalability, low response time, and optimal bilateral transposed conv filtering. Moreover, during VM migration existing techniques result in service level agreement violations owing to inefficient VM placement among PMs. To overcome these issues, a Double Deep Q proximal model with a feedback controller has been proposed. The double weight set in the offline and online updating process in the decision model maintains a smooth service level agreement with the cloud. Also, centralized and decentralized controller algorithm fails with a single point of failure and coordination issue in complicated situations with instruction mixing of processes. Finally, the conditional GAN feedback controller has been used to eliminate a single point of failure with high fault tolerance, low energy consumption and migration time.

UWSN refers to a collection of numerous underwater wireless sensor-nodes dispersed throughout the marine environment. Proposed work develops node-localization and optimal relay node selection based routing approach for UWSN. Target nodes initially listen to the beacon for a certain amount of time whenever they are within range of an anchor node before retrieving an anchor-node with RSS data. Next, the Euclidean distance between a target node and an anchor node is determined. After that, another two anchor nodes were placed within the transmission range. The suggested approach then uses modified COOT-optimization to determine the target sensor node's coordinates in an effort to reduce localization-error. After that, the process of uneven clustering and selecting the cluster heads was done. For identifying the ideal relay node, the proposed technique employs a parameter-based approach to CH discovery, particularly RSO. Finally, using an information fusion technique, the sensing information is sent through relay nodes. Proposed localization and routing algorithm is validated using some of the parameter which achieves better performance like 94% localization accuracy, 6% localization error, 2.4% throughput value and 81% packet delivery ratio. It performs better when compared to other existing approaches such as DEEC, SEP, ELEACH and LEACH whose localization accuracy are 93%, 84%, 80% and 78%. Thus the techniques utilized in this proposed approach are the best choice for node localization and routing in UWSN.

The Black Widow Optimization (BWO) algorithm has garnered significant attention within the realm of metaheuristic algorithms due to its potential to address diverse problems across various domains. However, a noteworthy weakness of BWO is its utilization of a random selection technique, which can lead to reduced diversity, expedited convergence, and potential entrapment in local optima. This research introduces a novel approach to augment the BWO algorithm by integrating alternative selection schemes, thereby surpassing the limitations of the current selection methodology. To assess the effectiveness of these proposed variants, we employ the CEC 2019 benchmark functions as the standard evaluation metric. Subsequently, we utilize the best-performing BWO version, PIBWO, to address cloud scheduling challenges. In a series of comparative experiments, PIBWO demonstrates superior performance compared to existing algorithms, showcasing remarkable enhancements in makespan reduction, energy consumption minimization, and cost efficiency. These findings underscore PIBWO’s potential as a robust solution for addressing cloud task scheduling challenges, offering promising avenues for developing more sustainable and cost-effective cloud computing systems.

Agriculture industry faces the challenge of increasing productivity by 50% from 2012 to 2050 while reducing water usage, given that it currently consumes 69% of the world’s freshwater. To achieve this goal, smart technologies such as Artificial Intelligence (AI), Digital Twins (DT), and Internet of Things (IoT) are being increasingly utilized. However, the use of DT in agriculture is still in its early stages. This study proposes a smart irrigation framework inspired by digital twins in an application domain. The irrigation framework’s sensors and actuators are linked to their virtual counterparts to create a digital twin. The IoT platform collects, aggregates, and processes data to determine daily irrigation requirements, and the behavior of the irrigation system is simulated. The proposed framework has two main advantages: evaluating the behavior of the digital twin and IoT platform in the context of agriculture before integrating them into the field and comparing various irrigation methods with current farming methods. By providing farmers with information about soil, weather, and crops, the system has the potential to improve farm operations and reduce water consumption.