Sustainable Computing-Informatics & Systems最新文献

The Internet of Things (IoTs) has transformed the digital landscape by interconnecting billions of devices worldwide, paving the way for smart cities, homes, and industries. With the exponential growth of IoT devices and the vast amount of data they generate, concerns have arisen regarding efficient task-offloading strategies. Traditional cloud and edge computing methods, paired with basic Machine Learning (ML) algorithms, face several challenges in this regard. In this paper, we propose a novel approach to task offloading in a Device-to-Device (D2D)-Edge-Cloud computing using the Rainbow Deep Q-Network (DQN), an advanced Deep Reinforcement Learning (DRL) algorithm. This algorithm utilizes advanced neural networks to optimize task offloading in the three-tier framework. It balances the trade-offs among D2D, Device-to-Edge (D2E), and Device/Edge-to-Cloud (D2C/E2C) communications, benefiting both end users and servers. These networks leverage Deep Learning (DL) to discern patterns, evaluate potential offloading decisions, and adapt in real time to dynamic environments. We compared our proposed algorithm against other state-of-the-art methods. Through rigorous simulations, we achieved remarkable improvements across key metrics: an increase in energy efficiency by 29.8%, a 27.5% reduction in latency, and a 43.1% surge in utility.

Massive multi-input multi-output (MIMO) is realized as the principal technology in the emerging fifth generation communication network system. Hybrid structure uplink communication is considered for the MIMO Non-orthogonal multiple access (MIMO-NOMA) system’s beam forming and power efficiency improvement through the novel three-layer user grouping. In the three-layer user grouping, the K-means algorithm is adopted in the initial layer for grouping users among different clusters and rectifying clustering errors in the third layer. The second layer used the agglomerative nesting (AGNES) algorithm for merging smaller clusters based on the channel correlation and angles of arrival similarity. The beam selection is carried out to minimize the intrusion of defined beam elements and to overcome beam overlapping problems. The non-convex optimization of the power allocating problem is modified as a convex problem by introducing a Quadratic transform (QT) to minimize each user’s data rate requirement. The algorithm of coati optimization is proposed to iteratively optimize the power allocation problem. The simulation results show that our proposed methodology goes beyond the existing schemes in terms of energy efficiency beyond the maximum power and achievable sum rate can be achieved.

Electricity consumption has been intensifying due to population growth, climate change, urbanization, and the growing use of electronic devices, which are increasingly non-linear loads that cause poor power quality conditions. The trend of the Internet of Things has led to the creation of devices that encourage the efficient and effective utilization of electrical power. This in turn facilitates the development of modern power distribution structures such as smart grids. Consequently, this paper presents in detail the design, construction, and validation of a three-phase IoT smart meter intended to form part of the end-user demand side of a smart grid. The compact embedded system, with a manufacturing cost below $80 USD, features a unique electronic design that enables its installation in any load center and employs a straightforward IoT structure that includes WiFi technology for Internet communication. Also, a deployed web application was developed specifically to display the smart meter measurements. Unlike other smart meters, the proposed meter not only provides the amount of active energy consumption, but total and fundamental RMS current and voltage, active, reactive, and apparent power, reactive energy, power factor, and some power quality parameters such as, line frequency, amplitude of 64 current harmonics, and total harmonic distortion. Additionally, this study shows that the prototype achieves an absolute error of less than 1% in all its measurements. Finally, real-life applications of the developed device are demonstrated in residential environments.

The Internet of Things (IoT) is constantly evolving and expanding. However, due to the limited IoT resources, it is intertwined with fog computing to use their resources to compensate for the limitations of IoT resources. On the other hand, fog devices face challenges, such as resource heterogeneity, high distribution, dynamism, and limitations, so an efficient task scheduling approach is needed to deploy fog computing resources effectively and improve the quality of service (QoS). This work mathematically formulates the task scheduling problem to minimize energy consumption and cost and improve QoS by reducing response time and deadline violation times of IoT tasks. Then, it proposes an Energy-efficient and deadline-Aware Task scheduling in Fog Computing (ETFC) method that predicts the traffic of fog nodes by a Support Vector Machine (SVM) and divides them into low-traffic and high-traffic groups. Next, the ETFC method schedules the low-traffic part with an algorithm based on reinforcement learning using the proposed ICLA-SOA, which is an algorithm based on irregular cellular learning automata and schedules the tasks of the high-traffic part with a metaheuristic algorithm using the proposed Non-dominated Sorting Genetic Algorithm (NSGA-III). The simulation results demonstrate that the ETFC method exhibits up to an 84 % enhancement in response time, up to a 33 % reduction in energy consumption, up to a 30 % decrease in costs, and up to a 28 % advancement in meeting task deadlines compared to other methods.

The popularity of intelligent vehicles with cutting-edge vehicular applications has fueled the rapid expansion of Vehicular Ad hoc Networks (VANETs) in recent years. VANETs are a network of vehicles designed to exchange and explore real-time data using a well-developed and effectively organized data transport technology. However, the major issue of dynamic topology and cluster stability always has an impact on choosing an optimal path between the cars. At this point, an intelligent clustering technique in VANETs that handles dynamic topology and cluster stability is critical for efficient route selection between vehicular nodes. This is an NP-hard issue that can be effectively solved using an intelligent nature-inspired algorithm that can discover near-optimal solutions in the search space. An Intelligent Hybrid Fennec Fox and Sand Cat Optimization Algorithm (HFFSCOA) -Based Clustering Scheme is proposed in this paper as a novel route clustering optimization strategy that takes grid size, orientation, velocity node density, and communication range into account while achieving its goal. This HFFSCOA contributed to the route clustering process, which determines dependable and optimal routes between vehicular nodes for the purpose of building and evaluating ideal Cluster Heads (CHs) in the network. HFFSCOA's findings clearly demonstrated its usefulness and efficacy in terms of the number of vehicles, network size, changeable communication ranges, and number of clusters built in the network. The statistical results of HFFSCOA also confirmed an enhanced cluster Optimization rate of 56.21% and an increased cluster stability of 92.34.

Rapid urbanization has given rise to escalating land surface temperatures, climate change, and the emergence of surface urban heat islands (SUHIs) and urban hot spots (UHSs), posing significant environmental challenges. This study, situated in the dynamic urban landscape of southern Iran, leverages Landsat satellite imagery to scrutinize the repercussions of temperature escalation on the environment. Our approach harnesses a novel Urban Thermal Field Variance Index (UTFVI) in conjunction with thermal and spectral indices to gain insights into these challenges. We employ a multifaceted methodology that integrates linear regression, cellular automata (CA)-Markov chains, and advanced neural network techniques to predict land surface temperature (LST) values and associated indicators. Over the span of 2000–2019, our findings reveal a 5% augmentation in urban heat islands (UHIs), signifying an alarming temperature increase. A striking 46% of the region, as uncovered by UTFVI, falls into the most severe categories of ecological discomfort. Our analysis underscores the robust correlations between LST and critical indices, notably the Normalized Difference Built Index (NDBI) (0.96), Normalized Difference Vegetation Index (NDVI) (-0.71), UTFVI (0.98), and SUHI (0.82). Notably, our original contributions lie in the application of Artificial Neural Networks (ANNs), wherein the Multilayer Perceptron (MLP) method excels in predicting UTFVI (R²=0.96) and NDBI (R²=0.96), while the Radial Basis Function (RBF) method demonstrates remarkable accuracy in forecasting the SUHI index (R²=0.96). These achievements signify a groundbreaking advancement in comprehending the intricate dynamics of urban environmental conditions. The repercussions of increased urbanization, the proliferation of barren land, and dwindling vegetation in 2019 manifest in a marked decline in ecological quality, with a concomitant surge in temperatures within the study area. These findings underscore the pressing need for informed urban planning and sustainable practices to mitigate the detrimental effects of urban heat islands and their impact on local climates.

Understanding an irrigation ditch plays an important role in intelligent agriculture environmental monitoring, especially in field environments where large chunks of ditches are particularly covered by various types of natural unstructured soil, vegetation and weeds. However, due to the diverse and unstructured muddy ditches, understanding them remains a challenge. Traditional approaches of understanding a scene from three-dimensional (3D) point clouds or multi-sensor fusion are energy intensive and computationally complex, making them quite laborious in application on a resource-constrained system. In this study, we propose a methodology to understand irrigation ditches and reconstruct them in a 3D scene, using only a resource-constrained monocular camera, without prior training. Spatial similar textures projections are extracted and clustered. Through geometric constraints of distribution and orientation, similar texture projections are refined and their corresponding surfaces are shaped. By contours and evidence lines, the ditch bottom surfaces are represented. Thus an irrigation ditch can be understood and reconstructed in a 3D environment, which can be used in agricultural automatic control system, agricultural robots, and precise agriculture. Unlike machine learning-based algorithms, the proposed method requires no prior training nor knowledge of the camera’s internal parameters such as focal length, field angle, and aperture. Additionally, pure geometric features make the presented method robust to varying illumination and colour. The percentage of incorrectly classified pixels was compared to the ground truth. Experimental results demonstrated that the approach can successfully elucidate irrigation ditches, meeting requirements in safety monitoring in an agriculture environment.

The integration of renewable energy sources, relatable as Solar Photovoltaic (PV) and Wind Power, into the radial distribution system has gained significant attention due to their eco-friendly and sustainable attributes. This article presents a narrative advent for achieving the finest share of Solar PV and Wind force power through a radial distribution system using the innovative Spider Monkey Optimization (SMO) algorithm. Multi-objective function for the minimization of distribution loss and voltage deviation with the constraints of power balance equation and boundary limits of voltage and power is considered. The Spider Monkey Optimization algorithm, stimulated via the community activities of spider monkeys, be employed to effectively search for the finest allotment of Solar PV and Wind Energy Power within the distribution network. The SMO algorithm exhibits robustness in handling non-linear and multi-dimensional optimization problems, making it suitable for this complex task. To authorize the usefulness and efficiency of the planned approach, it is functional to standard 33-bus radial division coordination. Comparative analyses of optimization techniques are reported and SMO reduces the losses to 104 KW and the voltage deviation is minimized to 0.0458 pu. The valuable perception is that incorporating Solar PV and Wind Energy sources into radial distribution systems improves the quality.

Cloud computing is one of the powerful engines driving global industrial upgrading and the booming digital economy. However, the explosive growth of cloud data centers (DCs) has resulted in inevitable energy consumption and carbon emission problems. Therefore, constructing energy-efficient and sustainable DCs will be essential for green cloud computing. This review makes several efforts to thoroughly investigate and track the research progress and routes to sustainable DCs. Firstly, we construct a new conceptual model of sustainable DCs to cover cutting-edge research results and indicate future evolutionary directions. Secondly, this review provides a comprehensive survey of five topics from a technical perspective: workload management, virtual resource management, energy management, thermal management, and waste heat recovery. Subsequently, some real-world datasets relevant to the topics, including workload traces, renewable energy data, and electricity price traces, have been specifically collected to support researchers in conducting further research. Finally, based on observations of existing works, we highlight some salient technical challenges and promising solutions to provide sensible energy and carbon reduction suggestions in sustainable DCs.

In a cloud computing environment, job scheduling allows the service provider to schedule resources based on demand. Job scheduling must also ensure QoS, end-user satisfaction, and the efficient usage of resources. Cloud computing vendors assign virtualized computing resources to end-users based on job requirements that are dynamically scalable and pay-per-use. The assignment of jobs requires proper investigation and mapping of available resources. In this paper, we have proposed a novel job scheduling scheme based on Rock Hyrax. Our Rock Hyrax approach uses objective functions to map jobs to available resources. The objective function considers a variety of QoS parameters like makespan, response time and energy efficiency. Our method employs two key QoS parameters: makespan and energy consumption. The node behavior and characteristics, such as processing power, storage, and network connectivity to cluster similar resources, have also been considered for scheduling. An experimental setup is created for a thorough study of the proposal using CloudSim simulator. For both the jobs and virtual machines, static and dynamic scenarios for performance evaluation have been developed. To compare our work with existing scheduling algorithms like ACO, PSO, BFO, and ABC has been considered and we have found that the proposal reduces makespan by 2–9% as increased in jobs. Furthermore, the proposed method reduces total energy consumption in data centers by 7–23% as jobs request increases. The findings support the claim that the proposed method surpasses the existing methods and significantly shortens the time needed to determine the resource required for the job.