{"title":"A certain examination on heterogeneous systolic array (HSA) design for deep learning accelerations with low power computations","authors":"","doi":"10.1016/j.suscom.2024.101042","DOIUrl":"10.1016/j.suscom.2024.101042","url":null,"abstract":"<div><div>Acceleration techniques play a crucial role in enhancing the performance of modern high-speed computations, especially in Deep Learning (DL) applications where the speed is of utmost importance. One essential component in this context is the Systolic Array (SA), which effectively handles computational tasks and data processing in a rhythmic manner. Google's Tensor Processing Unit (TPU) leverages the power of SA for neural networks. The core SA's functionality and performance lies in the Computation Element (CE), which facilitates parallel data flow. In our article, we introduce a novel approach called Proposed Systolic Array (PSA), which is implemented on the CE and further enhanced with a modified Hybrid Kogge Stone adder (MHA). This design incorporates principles to expedite computations by rounding and extracting data model in SA as PSA-MHA. The PSA, utilizing a data flow model with MHA, significantly accelerates data shifts and control passes in execution cycles. We validated our approach through simulations on the Cadence Virtuoso platform using 65 nm process technology, comparing it to the General Matrix Multiplication (GMMN) benchmark. The results showed remarkable improvements in the CE, with a 30.29 % reduction in delay, a 23.07 % reduction in area, and an 11.87 % reduction in power consumption. The PSA outperformed these improvements, achieving a 46.38 % reduction in delay, a 7.58 % reduction in area, and an impressive 48.23 % decrease in Area Delay Product (ADP). To further substantiate our findings, we applied the PSA-based approach to pre-trained hybrid Convolutional and Recurrent (CNN-RNN) neural models. The PSA-based hybrid model incorporates 189 million Multiply-Accumulate (MAC) units, resulting in a weighted mean architecture value of 784.80 for the RNN component. We also explored variations in bit width, which led to delay reductions ranging from 20.17 % to 30.29 %, area variations between 13.08 % and 32.16 %, and power consumption changes spanning from 11.88 % to 20.42 %.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142438052","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 bidirectional gated recurrent unit based novel stacking ensemble regressor for foretelling the global horizontal irradiance","authors":"","doi":"10.1016/j.suscom.2024.101041","DOIUrl":"10.1016/j.suscom.2024.101041","url":null,"abstract":"<div><div>The rapid expansion of solar power generation has led to new challenges in solar intermittency, requiring precise forecasts of Global Horizontal Irradiance (GHI). Accurate GHI predictions are crucial for integrating sustainable energy sources into traditional electrical grid management. The article proposes an innovative solution, the novel Enhanced Stack Ensemble with a Bi-directional Gated Recurrent Unit (ESE-Bi-GRU), which uses machine learning (ML) boosting regressors such as Ada Boost, Cat Boost, Extreme Gradient Boost, and Gradient Boost, and Light Gradient Boost Machine acts as a base learner and the deep learning (DL) algorithms such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) for both directions are taken as a meta-learner. The predictive performance of the proposed ESE-Bi-GRU model is evaluated against individual models, showing significant reductions in mean absolute error (MAE) by 86.03 % and root mean squared error (RMSE) by 66.43 %. The model's ability to minimize prediction errors, such as MAE and RMSE holds promise for more effective planning and utilization of sporadic solar resources. By improving GHI forecast accuracy, the ESE-Bi-GRU model contributes to optimizing the integration of sustainable energy sources within the broader energy grid, fostering a more sustainable and environmentally conscious approach to energy management.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142432143","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":"Occupancy prediction: A comparative study of static and MOTIF time series features using WiFi Syslog data","authors":"","doi":"10.1016/j.suscom.2024.101040","DOIUrl":"10.1016/j.suscom.2024.101040","url":null,"abstract":"<div><div>Occupancy prediction has been the subject of ongoing research, employing various methods and data sources to improve occupancy prediction accuracy and energy efficiency in buildings. Precise occupancy prediction is crucial for optimizing energy usage, ensuring occupant comfort, and enhancing building management. With the increasing demand for intelligent building management systems, robust and accurate occupancy prediction models are becoming more critical. This study aims to predict building occupancy using WiFi Syslog files from three different datasets: an open-source dataset from the University of Massachusetts Dartmouth, a new locally collected dataset from the dental school at the University of Detroit Mercy, and finally, a dataset from an office building in Berkeley, California. Two types of features, static features, and MOTIF time series features, were extracted from the datasets to process and compare their performance in occupancy prediction.</div><div>The first step of the proposed framework consisted of selecting the most suitable time range to compare occupancy prediction models between different datasets. It was concluded that this analysis was best conducted semester by semester. Multiple regression algorithms, such as random forest and LightGBM, were applied in the following step, along with advanced ensemble techniques, including stacking and blending, to assess the model. The stacking regression showed the best results for static features across all datasets. It achieved a Coefficient of Determination (<span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span>) of 0.9540 in the first dataset, 0.9482 in the second, and 0.9977 in the third. For MOTIF features, however, the best algorithm depended on the dataset. All algorithms performed similarly in the first dataset, with <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.956. In contrast, LightGBM and the Stacking Regressor had better results than the others in the second dataset, with a low <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.531 due to dataset-specific differences. The stacking regression once again delivered the best results in the last dataset with an <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 0.9967.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142424728","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 scenario-customizable and visual-rendering simulator for on-vehicle vibration energy harvesting","authors":"","doi":"10.1016/j.suscom.2024.101039","DOIUrl":"10.1016/j.suscom.2024.101039","url":null,"abstract":"<div><div>The rising demand for renewable energy supply in standalone computing devices has led to the emergence of vibration energy harvesting (VEH) to overcome technical and environmental challenges. For instance, VEH is desirable in IoT scenarios where maintaining a battery supply is non-sustainable or impractical due to many devices or remote circumstances. VEH can be environmentally friendly given that it reduces the reliance on traditional battery production and usage, thus reducing the carbon footprint and chemical waste in disposable batteries. However, a significant hurdle in VEH adoption is the lack of effective simulation tools for generating various application scenarios to describe, validate, or predict the efficacy of the VEH-based devices. It is necessary for designing and implementing a VEH simulator for a variety of realistic application scenarios. Being the first of its kind, this study presents a scenario-customizable and visual-rendering VEH simulation system based on the Unity3D Engine. The proposed simulator features a modular design that consists of several key functional components including vibration scenarios’ creation and manipulation, VEH model specification, Unity-Python Co-computing mechanism, and 3D visualization. This paper also presents two AI-based case studies leveraging the functionality and data provided by the simulator to demonstrate its potential for data-driven research and applications.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Incorporation of computational routines in a microservice architecture in AgDataBox platform","authors":"","doi":"10.1016/j.suscom.2024.101038","DOIUrl":"10.1016/j.suscom.2024.101038","url":null,"abstract":"<div><div>Agriculture has been undergoing a digital process that aims to apply digital technologies to make the sector more productive, profitable, and environmentally responsible. This trend has been adopted since applying precision agriculture (PA) techniques and, more recently, with digital agriculture (DA). DA aims to use all available information and knowledge to enable the automation of sustainable processes in agriculture, applying data analysis methods and techniques by specific software and platforms to collect and transform data into meaningful information for agriculture. Platform AgDataBox (ADB) offers tools to allow agriculture specialists to obtain, process, and visualize data for the correct decision-making. However, its structure needed to be readjusted to new software architecture to allow the aggregation of new functionalities and expand the ADB platform. This study aimed to develop a web microservices architecture (ADB-MSA) to incorporate the required functionalities to create thematic maps (TMs) and delineate management zones (MZs). ADB-MSA provided eight microservices, six of which (statistics, spatial, interpolation, clustering, rectification, and lime/nutrient recommendation) execute procedures based on JavaScript, R, and Python programming languages. At the same time, the other two are used to store data. In the case study, the procedures to create TMs and delineate MZs were performed with data from one commercial area. Thus, the services provided in the architecture meet the steps of creating TMs and delineating MZs, as MZs for fertilizer application were generated and evaluated according to phosphorus and potassium requirements. ADB-MSA allows the development of several new client applications (web, mobile, desktop, and embedded systems) to promote solutions in agriculture, streamlining processes, as it abstracts the implementation and execution complexity of available algorithms.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323089","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":"Optimization of reservoir operation by sine cosine algorithm: A case of study in Algeria","authors":"","doi":"10.1016/j.suscom.2024.101035","DOIUrl":"10.1016/j.suscom.2024.101035","url":null,"abstract":"<div><div>The optimal operation of the reservoir has vital importance in water engineering. In the presented article, a new optimization method, named sine cosine algorithm (SCA) was employed to obtain operating policy for an irrigation system. The SCA was utilized for the monthly operation of the Boukerdane Dam placed in the north of Algeria. The fitness function was the minimization of the total shortage for the studied period. Three scenarios considering three different seasons of inflow (dry, normal and wet) are used to optimize the reservoir system’s operation. The SCA outputs were compared with particle swarm optimization (PSO) and kidney algorithm (KA). The outcomes indicated that the SCA surpassed the PSO and KA in convergence rate. The general results indicated the low speed of KA and PSO in achieving convergence. The results indicated that the highest RES (resiliency index), SUS (sustainability index) and REL (reliability index) achieved by the SCA were 65, 86 and 92 %, respectively. Comparing the third scenario with the first and second scenarios, it was observed that the third scenario (wet seasons) improved the results.</div></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142327285","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":"Optimized dynamic service placement for enhanced scheduling in fog-edge computing environments","authors":"","doi":"10.1016/j.suscom.2024.101037","DOIUrl":"10.1016/j.suscom.2024.101037","url":null,"abstract":"<div><p>The traditional cloud computing model struggles to efficiently handle the vast number of Internet of Things (IoT) services due to its centralized nature and physical distance from end-users. In contrast, edge and fog computing have emerged as promising solutions for supporting latency-sensitive IoT applications by distributing computational resources closer to the data source. However, these technologies are limited by their size and computational capacities, making optimal service placement a critical challenge. This paper addresses this challenge by introducing a dynamic and distributed service placement policy tailored for edge and fog environments. By leveraging the inherent advantages of proximity in fog and edge nodes, the proposed policy seeks to enhance service delivery efficiency, reduce latency, and improve resource utilization. The proposed method focuses on optimizing the placement of high-demand services closer to the data generation sources to enhance scheduling efficiency in fog computing environments. Our method is divided into three interconnected modules. The first module is the service type estimator, which is responsible for distributing services to appropriate nodes. Here, we use the Political Optimizer (PO) as a new metaheuristic algorithm for deploying IoT services. The second module is service dependency estimator, which manages service dependencies. Here, we load dependent services near the data using a path matrix based on the Warshall algorithm. Finally, the third module is resource demand scheduling, which estimates resource demand to facilitate optimal scheduling. Here, we use a popularity-based policy to manage resource demand and service execution scheduling. Implementation results demonstrate significant improvements over existing state-of-the-art policies, highlighting the efficacy of the proposed policy in enhancing service delivery within fog-edge computing frameworks.</p></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142228676","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 succinct state-of-the-art survey on green cloud computing: Challenges, strategies, and future directions","authors":"","doi":"10.1016/j.suscom.2024.101036","DOIUrl":"10.1016/j.suscom.2024.101036","url":null,"abstract":"<div><p>Cloud computing is a method of providing various computing services, including software, hardware, databases, data storage, and infrastructure, to the public through the Internet. The rapid expansion of cloud computing services has raised significant concerns over their environmental impact. Cloud computing services should be designed in a green manner, efficient in energy consumption, virtualized, consolidated, and eco-friendly. Green Cloud Computing (GCC) is a significant field of study that focuses on minimizing the environmental impact and energy usage of cloud infrastructures. This survey provides a comprehensive overview of the current state of GCC, focusing on the challenges, strategies, and future directions. The review study begins by identifying important challenges in GCC from practical implementations, identifying GCC-introduced environmental protection and prevention initiatives, and expressing the demand for long-term technical progression. It then addresses GCC’s primary concerns, such as energy efficiency, resource management, operational costs, and carbon emissions, and categorizes implementations according to algorithms, architectures, frameworks, general issues, and models and methodologies. Furthermore, enhancements in virtualization, multi-tenancy, and consolidation have been identified, analyzed, and accurately portrayed to address the advancements in GCC. Finally, the survey outlines future research directions and opportunities for advancing the field of GCC, including the development of novel algorithms, technologies for energy harvesting, and energy-efficient and eco-friendly solutions. By providing a comprehensive overview of GCC, this survey aims to serve as documentation for further evolving new emerging technological approaches in the GCC environment.</p></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142173277","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 new hybrid fixed and adaptive gains control algorithm to reduce power losses on LLCL filter-based renewable energy conversion systems with systematic parametrization using Grey Wolf optimizer","authors":"","doi":"10.1016/j.suscom.2024.101034","DOIUrl":"10.1016/j.suscom.2024.101034","url":null,"abstract":"<div><p>Currently, there is a transition in the energy matrix around the world, where traditional sources of energy generation are continually being replaced by energy generation systems based on renewable sources to mitigate the climate crisis. In this bias, this work presents the mathematical modeling of an LLCL filter, used to connect power generation systems based on renewable energy sources to the electrical grid, and presents a novel hybrid fixed-and adaptive gains control strategy for current injection into the grid using this system. The developed hybrid controller is composed of a proportional–integral controller and a direct robust adaptive controller. The first term of the controller guarantees the reference current, while the second term of the controller is used for disturbance rejection. Furthermore, a systematic procedure for the controller’s parametrization based on Grey Wolf Optimizer is also provided. The control of the current injected into the grid is carried out considering the LLCL filter without passive damping resistors in the filter structure to avoid power losses due to the passive filter elements. Additionally, the LLCL filter model considers minimal parasitic resistances to evaluate the controller’s performance and optimize it for the application of interest, aiming to maximize the system performance by ensuring a short transient regime due to the fast closed-loop system response. Simulation results indicate high performance of this optimized control strategy with small tracking error even considering grid impedance variations.</p></div>","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142088597","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":"Retraction notice to ‘Deep learning-based energy inefficiency detection in the smart buildings' [Sustainable Computing: Informatics and Systems 40 (2023) 100921]","authors":"","doi":"10.1016/j.suscom.2024.101022","DOIUrl":"10.1016/j.suscom.2024.101022","url":null,"abstract":"","PeriodicalId":48686,"journal":{"name":"Sustainable Computing-Informatics & Systems","volume":null,"pages":null},"PeriodicalIF":3.8,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2210537924000672/pdfft?md5=6ab54742df5e59c27c2e8123f9f00aba&pid=1-s2.0-S2210537924000672-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141935798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}