Reduce Resource Usage Research Articles

Reducing the cost of cold start time in serverless function executions using granularity trees

In serverless computing, cold starts significantly impede performance. This paper presents a granularity tree-based scheduling strategy, dynamically adjusting serverless function deployment by package dependencies to mitigate cold starts and optimize resource usage. This approach notably reduces cold start and response times. Empirical results from evaluating functions across various datasets show the strategy outperforms existing methods. Specifically, it consistently delivers lower response times and decreases resource consumption, demonstrating its effectiveness in managing computational resources while ensuring swift function invocation. In particular scenarios, the proposed scheduler impressively reduced response times from 8134.1 ms to 392.8 ms and idle memory usage from 15.2 GB to 11.2 GB per machine. In other scenarios, it reduced response times from 12,152.7 ms to 504.2 ms while maintaining a 100% function execution percentage. These quantified improvements underscore the significant enhancements in cold start mitigation and overall system performance, highlighting the potential of granularity tree-based scheduling in enhancing serverless computing architectures by effectively balancing rapid response with reduced resource usage.

Optimization of steel plate quality inspection driven by PscSE and SPPFELAN

AbstractBased on the improved YOLOv8n, a steel plate defect detection and recognition method is proposed to address the high labor costs and workload of traditional tasks. SPPFELAN processes inputs in parallel to enhance computational efficiency by executing multiple pooling operations simultaneously. The parallel feature fusion module PscSE, using a mixed‐dimension SE attention mechanism (scSE), captures global and channel‐related information better, improving characterization capability. The EIOU loss function addresses the ambiguous aspect ratio definition of CIOU loss, enhancing detection accuracy and accelerating convergence. Results show the YOLOv8n‐PscSE‐SPPFELAN model achieves 76.9% mAP@0.5 on the Northeastern University steel plate dataset, a 4.6% improvement over the original YOLOv8n, with a computation amount of 7.7 GFLOPs, reducing resource usage and greatly improving detection speed.

Activating sustainability in the design process

Abstract Design decisions have an impact on societies and the environment. Making the impact of design tangible facilitates the mitigation of its negative consequences. The purpose of this paper is to outline what methods and actions a User Experience (UX) practitioner could use in order to support sustainable development. At Ergosign GmbH, an agency creating digital experiences, we conducted a review of existing guidelines and principles to determine the relevance and usefulness of those frameworks in the User Experience Design (UXD) context. The analysis resulted in the creation of six guiding principles to introduce sustainability concerns into the design process. Additionally, we mapped related UX methods and heuristics to each principle. Each of the six principles, as well as an exemplary method, are described in detail in this article. A first practical evaluation of the principles suggests that assessing impact and identifying preventive actions is possible at all stages of the design process. Furthermore, there is no strict correlation of a principle with a particular project phase. While an early analysis generates a more holistic action plan, a later assessment provides more concrete advice. Both approaches can deliver notable improvements in the reduction of resource usage.

Performance of laser metal deposition on hot-rolled stainless steel for hybrid steel structures

The construction sector is increasingly recognising the potential of metal additive manufacturing (AM) for fabricating complex steel details with enhanced performance and reduced resource usage. In the coming years, the application of AM technologies is expected to advance, leading to the development of new structural elements and improved performance of existing ones. This progression involves the integration of conventional construction steel with AM techniques, such as laser metal deposition (LMD), to create hybrid systems that incorporate efficient details. LMD offers the advantage of overcoming size limitations associated with laser powder bed fusion (LPBF) while leveraging its geometric capabilities. In this study, the mechanical behavior of hybrid steel components, fabricated using LMD on AISI316L stainless steel plates, was investigated through an extensive experimental campaign involving 40 samples. Axial tests, fatigue tests, and material characterisation were conducted to evaluate strength criteria and long-term behavior. Results demonstrate that LMD-produced AISI316L exhibits mechanical properties compliant with EN1993's "Design of steel structures" encompassing elastic and plastic behavior. Furthermore, both LMD samples and hybrid specimens exhibit promising fatigue performance, aligning with the highest fatigue detail category (detail category 160) for conventional steel details.

Model-data-driven adversarial active learning for brain tumor segmentation

Active learning (AL) attempts to select informative samples in a dataset to minimize the number of required labels while maximizing the performance of the model. Current AL in segmentation tasks is limited to the expansion of popular classification-based methods including entropy, MC-dropout, etc. Meanwhile, most applications in the medical field are simply migrations that fail to consider the nature of medical images, such as high class imbalance, high domain difference, and data scarcity. In this study, we address these challenges and propose a novel AL framework for medical image segmentation task. Our approach introduces a pseudo-label-based filter addressing excessive blank patches in medical abnormalities segmentation tasks, e.g., lesions, and tumors, used before the AL selection. This filter helps reduce resource usage and allows the model to focus on selecting more informative samples. For the sample selection, we propose a novel query strategy that combines both model impact and data stability by employing adversarial attack. Furthermore, we harness the adversarial samples generated during the query process to enhance the robustness of the model. The experimental results verify our framework’s effectiveness over various state-of-the-art methods. Our proposed method only needs less than 14% annotated patches in 3D brain MRI multiple sclerosis (MS) segmentation tasks and 20% for Low-Grade Glioma (LGG) tumor segmentation to achieve competitive results with full supervision. These promising outcomes not only improve performance but alleviate the time burden associated with expert annotation, thereby facilitating further advancements in the field of medical image segmentation. Our code is available at https://github.com/HelenMa9998/adversarial_active_learning.

An efficient intrusion detection model based on convolutional spiking neural network

Many intrusion detection techniques have been developed to ensure that the target system can function properly under the established rules. With the booming Internet of Things (IoT) applications, the resource-constrained nature of its devices makes it urgent to explore lightweight and high-performance intrusion detection models. Recent years have seen a particularly active application of deep learning (DL) techniques. The spiking neural network (SNN), a type of artificial intelligence that is associated with sparse computations and inherent temporal dynamics, has been viewed as a potential candidate for the next generation of DL. It should be noted, however, that current research into SNNs has largely focused on scenarios where limited computational resources and insufficient power sources are not considered. Consequently, even state-of-the-art SNN solutions tend to be inefficient. In this paper, a lightweight and effective detection model is proposed. With the help of rational algorithm design, the model integrates the advantages of SNNs as well as convolutional neural networks (CNNs). In addition to reducing resource usage, it maintains a high level of classification accuracy. The proposed model was evaluated against some current state-of-the-art models using a comprehensive set of metrics. Based on the experimental results, the model demonstrated improved adaptability to environments with limited computational resources and energy sources.

Advancements in variable rate spraying for precise spray requirements in precision agriculture using Unmanned aerial spraying Systems: A review

Pesticides suppress pest populations and maintain agricultural yield; however, their overuse causes ecological damage. To mitigate the ecological damage caused by the overuse of pesticides, this paper explores the application of a precise and adaptable technique known as unmanned aerial spraying system (UASS)-based variable rate spraying (VRS). Herein, the current state of precision agriculture is examined, and the application of UASS in variable rate spraying is discussed. Then, the role of advanced sensors, including multispectral and hyperspectral technologies, in optimizing UASS-based VRS missions is studied, followed by the challenges in UASS-based spraying, ranging from technical intricacies to regulatory considerations, and related solutions. In addition to delving into pesticides, the paper explores alternative solutions such as herbicides, encompassing an integrated approach that aligns with sustainable farming practices for more effective pest management. VRS has advantages, including increased yields, reduced resource usage, and environmental sustainability. This paper concludes by delineating current challenges and envisioning future innovations, spotlighting ongoing studies on sensor technology and AI-driven flow rate optimization. This review provides insights into UASS-based VRS for precision agriculture.

Carbon Emissions Reduction of a Circular Architectural Practice: A Study on a Reversible Design Pavilion Using Recycled Materials

The construction industry, as a major consumer of resources and energy, accounts for about 40% of global carbon emissions. The concept of a circular economy (CE) is one effective means to address this issue. The entire lifecycle of a building includes: material production, construction, operation, and demolition. The production of building materials emits the largest proportion of carbon dioxide, followed by the operational phase, while construction (including demolition) has the smallest proportion. However, it is crucial to note the waste phase after demolition, where building materials are typically disposed of through incineration or landfill, leading to significant carbon emissions and environmental degradation. Therefore, carbon emissions generated during both the production and waste phases of the construction industry cannot be overlooked. This article employs a combined approach of practice and research, using the Circular Pavilion as a case study. From the design stage, reducing resource usage and carbon emissions are considered crucial factors. Reversible design, modularity, and the use of recycled materials are employed to reduce the emissions of “embodied carbon” and enhance material reuse. To validate the effectiveness of recycled materials in reducing greenhouse gas (GHG) emissions, this study calculates the material usage and carbon emissions during the production, transportation, and waste phases of the Circular Pavilion, Concrete Pavilion, and Steel Pavilion. The Circular Pavilion accounts for 34% and 3.5% of the total carbon emissions of the Concrete Pavilion and Steel Pavilion, respectively. In conclusion, the practical implementation of reversible design and recycled materials based on the concept of a circular economy is key to transitioning the construction industry from environmentally harmful impacts to eco-friendly practices. This establishes an effective method for resource reuse and carbon dioxide reduction in the construction sector, allowing waste resources to re-enter production and manufacturing processes, thereby reducing natural extraction, waste disposal, and energy consumption. Future applications of this method in the construction field involve establishing multidimensional composite design models and conducting feasibility assessments with upstream and downstream supply chains to support the realization of circular cities.

Optimizing locations of emergency medical stations for rural areas: A case study in Iran

Given the dearth of emergency medical services in rural areas, offering these services is among the most important things that should be done right to save the lives of people who have suffered severe injuries. Rapid access to EMSs, which includes a shorter response time and the availability of all intensive care services, including the ICU, CCU, NICU, and PICU, is crucial in this regard. In this regard, a GIS-based ACO-QAP model is proposed for rural areas to optimize locations for EMS stations. This model takes into account the standards of EMS in rural areas, and the standards of out-of-city roads, reducing the response times from EMS stations to the scene of damage and from the damage scene to the closest hospital that offers the required intensive care services. Additionally, to increase the availability of intensive care services and to optimal use of available resources, the model determines which types of intensive care services should be provided in the EMS stations. As a result of the integration for setting up the out-of-city EMS, 614 optimized locations were identified. The identified EMS stations should provide single or multiple intensive care services. There were identified as 544 (88.6%) multiservice stations and 70 (11.4%) single service stations. Among the multiservice stations, 113 (20.8%) stations were identified as two-service, 150 (27.5%) as three-service, and 281 (51.7%), as four-service stations. This model generates a chain of EMS stations that improves spatial accessibility and emergency medical availability while reducing resource usage.

FPGA-based ML adaptive accelerator: A partial reconfiguration approach for optimized ML accelerator utilization

The relentless increase in data volume and complexity necessitates advancements in machine learning methodologies that are more adaptable. In response to this challenge, we present a novel architecture enabling dynamic classifier selection on FPGA platforms. This unique architecture combines hardware accelerators of three distinct classifiers—Support Vector Machines, K-Nearest Neighbors, and Deep Neural Networks—without requiring the combined area footprint of those implementations. It further introduces a hardware-based Accelerator Selector that dynamically selects the most fitting classifier for incoming data based on the K-Nearest Centroid approach. When tested on four different datasets, Our architecture demonstrated improved classification performance, with an accuracy enhancement of up to 8% compared to the software implementations. Besides this enhanced accuracy, it achieved a significant reduction in resource usage, with a decrease of up to 45% compared to a static implementation making it highly efficient in terms of resource utilization and energy consumption on FPGA platforms, paving the way for scalable ML applications. To the best of our knowledge, this work is the first to harness FPGA platforms for dynamic classifier selection.

Optimizing Resource Management for Shared Microservices: A Scalable System Design

A common approach to improving resource utilization in data centers is to adaptively provision resources based on the actual workload. One fundamental challenge of doing this in microservice management frameworks, however, is that different components of a service can exhibit significant differences in their impact on end-to-end performance. To make resource management more challenging, a single microservice can be shared by multiple online services that have diverse workload patterns and SLA requirements. We present an efficient resource management system, namely Erms, for guaranteeing SLAs with high probability in shared microservice environments. Erms profiles microservice latency as a piece-wise linear function of the workload, resource usage, and interference. Based on this profiling, Erms builds resource scaling models to optimally determine latency targets for microservices with complex dependencies. Erms also designs new scheduling policies at shared microservices to further enhance resource efficiency. Experiments across microservice benchmarks as well as trace-driven simulations demonstrate that Erms can reduce SLA violation probability by 5× and more importantly, lead to a reduction in resource usage by 1.6×, compared to state-of-the-art approaches.

Efficient quantum simulation of nonlinear interactions using SNAP and Rabi gates

Quantum simulations provide means to probe challenging problems within controllable quantum systems. However, implementing or simulating deep-strong nonlinear couplings between bosonic oscillators on physical platforms remains a challenge. We present a deterministic simulation technique that efficiently and accurately models nonlinear bosonic dynamics. This technique alternates between tunable Rabi and SNAP gates, both of which are available on experimental platforms such as trapped ions and superconducting circuits. Our proposed simulation method facilitates high-fidelity modeling of phenomena that emerge from higher-order bosonic interactions, with an exponential reduction in resource usage compared to other techniques. We demonstrate the potential of our technique by accurately reproducing key phenomena and other distinctive characteristics of ideal nonlinear optomechanical systems. Our technique serves as a valuable tool for simulating complex quantum interactions, simultaneously paving the way for new capabilities in quantum computing through the use of hybrid qubit-oscillator systems.

Reinforcement learning-based dynamic pruning for distributed inference via explainable AI in healthcare IoT systems

Deep Neural Networks (DNNs) have become the key technique to revolutionize the healthcare sector. However, conducting online remote inference is often impractical due to privacy constraints and latency requirements. To enable local computation, researchers have attempted network pruning with minimal accuracy loss or DNN distribution without affecting the performance. Yet, distributed inference can be inefficient due to the energy overhead and fluctuation of communication channels between participants. On the other hand, given that realistic healthcare systems use pre-trained models, local pruning and retraining relying only on the available scarce data is not possible. Even pre-pruned DNNs are limited in their ability to customize to the local load of data and device dynamics. The online pruning of DNN inferences without retraining is viable; however, it was not considered in the literature as most well-known techniques do not perform well without adjustment. In this paper, we propose a novel pruning strategy using Explainable AI (XAI) to enhance the performance of pruned DNNs without retraining, a necessity due to the scarcity and bias of local healthcare data. We combine distribution and pruning techniques to perform online distributed inference assisted by dynamic pruning when needed for highest accuracy. We use Non-Linear Integer Programming (NLP) to formulate our approach as a trade-off between resources and accuracy, and Reinforcement Learning (RL) to relax the problem and adapt to dynamic requirements. Our pruning criterion shows high performance compared to other reference techniques and ability to assist distribution by reducing resource usage while keeping high accuracy.

A lightweight mixup-based short texts clustering for contrastive learning.

Traditional text clustering based on distance struggles to distinguish between overlapping representations in medical data. By incorporating contrastive learning, the feature space can be optimized and applies mixup implicitly during the data augmentation phase to reduce computational burden. Medical case text is prevalent in everyday life, and clustering is a fundamental method of identifying major categories of conditions within vast amounts of unlabeled text. Learning meaningful clustering scores in data relating to rare diseases is difficult due to their unique sparsity. To address this issue, we propose a contrastive clustering method based on mixup, which involves selecting a small batch of data to simulate the experimental environment of rare diseases. The contrastive learning module optimizes the feature space based on the fact that positive pairs share negative samples, and clustering is employed to group data with comparable semantic features. The module mitigates the issue of overlap in data, whilst mixup generates cost-effective virtual features, resulting in superior experiment scores even when using small batch data and reducing resource usage and time overhead. Our suggested technique has acquired cutting-edge outcomes and embodies a favorable strategy for unmonitored text clustering.

Revolutionizing agriculture: Exploring the potential of digital technologies and controlled environmental agriculture

The agricultural sector has experienced remarkable transformations fueled by technological advancements over the past 50 years, which have enhanced productivity and sustainability. Presently, agriculture is transitioning into a new era, driven by connectivity and data, known as Agriculture 4.0. This transition holds promise for further enhancing yield, optimizing resource utilization, and promoting sustainability and resilience. However, challenges such as population growth, resource scarcity, environmental degradation, and food waste persist and necessitate innovative solutions. Controlled Environment Agriculture (CEA) has emerged as a pivotal domain in urban agriculture, offering solutions to address these challenges. Several Controlled Environment Agriculture (CEA) facilities, such as greenhouses, plant factories, and rooftop gardens, employ sophisticated methods to enhance plant growth and quality while reducing resource usage. Achieving optimal growth conditions within CEA facilities remains a challenge, necessitating the effective management of microclimates and root zone environments. Recent research has emphasized the role of intelligent systems, particularly artificial intelligence and deep learning, in addressing these challenges. Moreover, optimizing indoor growing environments requires careful consideration of factors, such as temperature, humidity, chemical balance, and photosynthetic photon flux. Despite these advancements, the global food supply chain faces significant inefficiencies and wastage, exacerbated by factors such as the COVID-19 pandemic and climate change. Climate-smart agriculture, which leverages technologies such as AI and genomic tools, offers promising avenues for enhancing crop resilience and productivity in the face of changing climatic conditions. The integration of information technologies has further revolutionized agriculture and offers potential solutions to mitigate the impact of climate.

HYBRID APPROACH FOR DATA FILTERING AND MACHINE LEARNING INSIDE CONTENT MANAGEMENT SYSTEM

The object of research is the processes of data filtering and machine learning in content management systems. The subject of research is developing a hybrid approach to data filtering based on a combination of supervised and unsupervised machine learning. The article explores machine learning approaches to content management and how they can change the way we organize, categorize, and derive value from vast amounts of data. The main goal is to develop and use a hybrid approach for data filtering and training that will help optimize resource consumption and perform supervised training for better categorization in the future. This approach includes elements of supervised and unsupervised learning using the BERT architecture that uses this kind of flow that help reduce resource usage and adjust the algorithm to perform better in a specific area. As a result, thanks to this approach, the intelligent system was able to independently optimize for a specific field of use and help to reduce the costs of using resources. Conclusion. After applying a hybrid approach of data filtering and machine learning to existing data streams, we obtain a performance increase of up to 5%, and this percentage increases depending on the running time of the application.

Practical Evaluation of Federated Learning in Edge AI for IoT

AI running locally on IoT Edge devices is called Edge AI. Federated Learning (FL) is a Machine Learning (ML) technique that builds upon the concept of distributed computing and preserves data privacy while still supporting trainable AI models. This paper evaluates the FL regarding practical CPU usage and training time. Additionally, the paper presents how biased IoT Edge clients affect the performance of an AI model. Existing literature on the performance of FL indicates that it is sensitive to imbalanced data distributions and does not easily converge in the presence of heterogeneous data. Furthermore, model training uses significant on-device resources, and low-power IoT devices cannot train complex ML models. This paper investigates optimal training parameters to make FL more performant and researches the use of model compression to make FL more accessible to IoT Edge devices. First, a flexible test environment is created that can emulate clients with biased data samples. Each compressed version of the ML model is used for FL. Evaluation is done regarding resources used and the overall ML model performance. Our current study shows an accuracy improvement of 1.16% from modifying training parameters, but a balance is needed to prevent overfitting. Model compression can reduce resource usage by 5.42% but tends to accelerate overfitting and increase model loss by 9.35%.

Smart Aquaponics with Integration of AI and IoT for Yield Enhancement through Real-Time Monitoring and Decision Support

Technological advancements have become the key factor for major changes and upgradations in numerous industries and domain. Agriculture is no exception, technology stacks like IoT and AI are being integrated into agriculture up to a large extent starting from best crop prediction to crop health analysis, nutrient analysis to yield prediction. The intervention of technology is even more prominent in various smart agriculture methods including aquaponics, hydroponics, etc. Aquaponics is a sustainable method of agriculture, that combines aquaculture (fish farming) with hydroponics. This innovative system allows for the cultivation of fish and plants simultaneously, enabling a symbiotic relationship that enhances nutrient recycling. To lead the way for smart aquaponics, as technology continues to advance, the integration of artificial intelligence (AI) and the Internet of Things (IoT) holds immense potential for transforming traditional aquaponics into smart aquaponics. By harnessing real-time monitoring and decision support, AI and IoT can revolutionize various aspects of aquaponics that includes a major paradigm shift in agriculture, promising increased productivity, reduced resource usage, and improved environmental conservation. This article explores the transformative potential of leveraging AI and IoT technologies in aquaponics systems for yield enhancement, sustainability, and overall efficiency.

Sustainability metrics of environmental sustainability in Iranian manufacturing sector: achieving through human resources.

The paper investigates the impact of green human resource management (GHRM) on operatives' green actions in Iranian businesses. GHRM is a human resource management approach that prioritizes environmental and social responsibility. The study uses a random sample of 385 managers and employees from Iran's industrialized businesses in all regions. The research uses partial least square structure equations modeling to evaluate the suggested framework. The results show that GHRM practices affect corporate social responsibility, green attitudes inside the workplace, and green activities taken by workers. In addition, a green mentality and a commitment to corporate social responsibility encourage environmental activities in the workplace. The green psychosocial environment and corporate social responsibilities are intermediaries between green human resources development and individual green behaviour in Iranian businesses. The study suggests that incorporating sustainability metrics into the human resource management system is vital for achieving a sustainable future in industrial development. The research has important implications for businesses around the world, particularly those in the manufacturing sector, by encouraging them to adopt more environmentally responsive methods, including reducing resource usage.

Enabling containerized Central Unit live migration in 5G radio access network: An experimental study

5G mobile networks have gained considerable attention and traction by offering numerous benefits such as high data rates, low latency, reliability, and application specific connectivity. To effectively achieve these milestones mobile network functions must be virtualized using Virtual Machine (VM) and/or Containers. The latter has gained momentum in recent years due to its reduced resource usage and virtualization overhead, improving efficiency and flexibility while sharing compute and network resources. While containerization offers numerous benefits, it still faces specific challenges, one of them being the ability to provide robustness and resiliency of the containerized network functions under challenging network conditions, e.g., varying load conditions and application types. The currently available open-source container platform(s) do not achieve a full-fledged containerized mobile network protocol stack as they fail to support successful live migration of containers that execute specific 5G software functionalities.The contribution of this study is to present a proof-of-concept implementation that completes the live migration of a containerized 5G Central Unit (CU) module between two servers without causing permanent service disruption to the mobile user. The authors’ implementation makes use of an open-source migration software (CRIU) that has been modified to support the protocol (SCTP) used by the CU to exchange signaling messages with other 5G modules. The authors’ implementation is experimentally tested in a federated testbed environment by applying four container migration techniques, namely Cold, Pre-Copy, Post-Copy, and Hybrid-Copy migration. A performance comparison reveals that the end-user service recovery time due to the CU live migration can be reduced by up to 36% when applying the hybrid migration technique compared to the conventional cold migration technique. Additionally, experimental results reveal that compared to state-of-the-art VM migration the container-based migration approach reduces both migration time and service downtime by 96.7% and 75.2%, respectively.