Resource Efficiency Optimization Research Articles

Principles for Sustainable Integration of BIM and Digital Twin Technologies in Industrial Infrastructure

As industries evolve towards greater digitalization, integrating Building Information Modeling (BIM) and digital twin technologies presents a unique opportunity to enhance sustainability in industrial infrastructure. This paper formulates a comprehensive set of principles aimed at guiding the sustainable integration of these technologies within the context of modern industrial facilities, often referred to as “Factories of the Future”. The principles are designed to address critical sustainability challenges, including minimizing environmental impact, optimizing resource efficiency, and ensuring long-term resilience. Through a detailed examination of lifecycle management, data interoperability, and collaborative stakeholder engagement, this work provides a strategic framework for leveraging digital technologies to achieve sustainability goals. The principles outlined in this paper not only promote greener industrial practices but also pave the way for innovation in the sustainable development of industrial infrastructure. This framework is intended to serve as a foundation for future research and practical application, supporting the global shift towards more sustainable industrial operations.

Merit-Based Sortition in Decentralized Systems

In decentralized systems, it is often necessary to select an 'active' subset of participants from the total participant pool, with the goal of satisfying computational limitations or optimizing resource efficiency. This selection can sometimes be made at random, mirroring the sortition practice invented in classical antiquity aimed at achieving a high degree of statistical representativeness. However, the recent emergence of specialized decentralized networks that solve concrete coordination problems and are characterized by measurable success metrics often requires prioritizing performance optimization over representativeness. We introduce a simple algorithm for 'merit-based sortition', in which the quality of each participant influences its probability of being drafted into the active set, while simultaneously retaining representativeness by allowing inactive participants an infinite number of chances to be drafted into the active set with non-zero probability. Using a suite of numerical experiments, we demonstrate that our algorithm boosts the quality metric describing the performance of the active set by >2 times the intrinsic stochasticity. This implies that merit-based sortition ensures a statistically significant performance boost to the drafted, 'active' set, while retaining the property of classical, random sortition that it enables upward mobility from a much larger 'inactive' set. This way, merit-based sortition fulfils a key requirement for decentralized systems in need of performance optimization.

Leveraging Machine Learning for Advancing Circular Supply Chains: A Systematic Literature Review

Background: Circular supply chains (CSCs) aim to minimize waste, extend product lifecycles, and optimize resource efficiency, aligning with the growing demand for sustainable practices. Machine learning (ML) can potentially enhance CSCs by improving resource management, optimizing processes, and addressing complexities inherent in CSCs. ML can be a powerful tool to support CSC operations by offering data-driven insights and enhancing decision-making capabilities. Methods: This paper conducts a systematic literature review, analyzing 66 relevant studies to examine the role of ML across various stages of CSCs, from supply and manufacturing to waste management. Results: The findings reveal that ML contributes significantly to CSC performance, improving supplier selection, operational optimization, and waste reduction. ML-driven approaches in manufacturing, consumer behavior forecasting, logistics, and waste management enable companies to optimize resources and minimize waste. Integrating ML with emerging technologies such as IoT, blockchain, and computer vision further enhances CSC operations, fostering transparency and automation. Conclusions: ML applications in CSCs align with broader sustainability goals, contributing to environmental, social, and economic sustainability. The review identifies opportunities for future research, such as the development of real-world case studies further to enhance the effects of ML on CSC efficiency.

Transition from Electric Vehicles to Energy Storage: Review on Targeted Lithium-Ion Battery Diagnostics

This paper examines the transition of lithium-ion batteries from electric vehicles (EVs) to energy storage systems (ESSs), with a focus on diagnosing their state of health (SOH) to ensure efficient and safe repurposing. It compares direct methods, model-based diagnostics, and data-driven techniques, evaluating their strengths and limitations for both EV and ESS applications. This study underscores the necessity of accurate SOH diagnostics to maximize battery reuse, promoting sustainability and circular economy objectives. By providing a comprehensive overview of the battery lifecycle—from manufacturing to recycling—this research offers strategies for effective lifecycle management and cost-effective, environmentally sustainable secondary battery applications. Key findings highlight the potential of second-life EV batteries in ESSs. The integration of the considered diagnostic methods was shown to extend battery lifespan by up to 30%, reduce waste, and optimize resource efficiency, which is crucial for achieving circular economy objectives. This paper’s insights are crucial for advancing sustainable energy systems and informing future research on improving diagnostic methods for evolving battery technologies.

Integrating risk management in implementing circular economy principles in the healthcare sector: a case study from Indonesia

Purpose The purpose of this study is to explore the integration of risk management and circular economy (CE) principles within the healthcare sector to promote sustainability and resilience. Specifically, the study aims to demonstrate how risk management can support the transition to a circular economy in healthcare supply chains. By integrating risk management practices with CE principles, healthcare organizations can identify potential risks and opportunities associated with circular initiatives. Design/methodology/approach This study adopts a qualitative research approach, using a case study methodology with semi-structured interviews conducted at primary care facilities to understand the application of CE principles in practice. The study uses fuzzy logic methods to assess and mitigate risks associated with strategies promoting CE principles. Additionally, key performance indicators are identified to evaluate the effectiveness and enhance the resilience of these strategies within healthcare supply chains. Findings The study highlights the critical role of robust risk management strategies in facilitating the transition to a circular economy within healthcare organizations. Primary care facilities, which are critical to frontline healthcare delivery, are particularly vulnerable to product shortages due to supply risks. This study focuses on critical protective equipment, specifically latex gloves and assesses operational risks, including supply, demand and environmental risks, using a fuzzy logic-based model. Import delays were found to be a moderate risk, typically occurring once a year. The research highlights critical KPIs for a successful CE transition within healthcare supply chains, such as on-time delivery and service quality, which are directly related to the risk of supply chain disruption. In addition, the study highlights the significant impact of other CE strategies on healthcare supply chains, including localized production and manufacturing, innovation in product development, reverse logistics, closed-loop supply chains and the adoption of lean principles. Practical implications This study provides valuable insights for healthcare organizations to optimize resource efficiency, reduce waste and promote circularity in their operations. By implementing the proposed solutions and focusing on the identified KPIs, organizations can develop strategies to achieve sustainability goals and enhance resilience in healthcare supply chains. Originality/value This study contributes to the literature by demonstrating the application of risk management in facilitating the transition to a circular economy in the healthcare sector. The use of fuzzy logic methodology offers a novel approach to assessing and mitigating risks associated with critical product failures in supply chain activities. The study’s findings provide practical guidance for healthcare organizations seeking to integrate circular economy principles and improve sustainability performance.

Enhanced lightweight encryption algorithm based on chaotic systems

In order to improve security and efficiency, this study presents a novel lightweight encryption technique that makes use of chaotic systems. Our method creatively combines the new chaotic KLEIN_64 algorithm with the Keccak-256 hash function, offering a solid basis for producing initial values essential for causing chaotic maps during the encryption process. After a deep validation with rigorous NIST testing, our chaotic pseudo random generator, LAC, exhibits excellent reliability and cryptographic robustness. Furthermore, the complexity of the cryptographic round function is improved by incorporating a second chaotic pseudo random generator that combines chaotic LFSR and Skew Tent Maps, thereby fortifying security measures.Designed with resource-limited applications in mind, our approach ensures that the cryptosystem remains both lightweight and efficient, meeting the stringent constraints typical of such environments. The practical feasibility and performance of our approach are extensively evaluated through FPGA implementation on the Zybo 7Z010 platform. Our implementation achieves a remarkable throughput of 2.820 Gbps while maintaining optimal resource utilization and efficiency. Extensive experimental results confirm the superior security of our cryptosystem, with correlation tests, entropy measurement, and histogram analysis showcasing robustness against statistical attacks. Moreover, the cryptosystem shows little fluctuation in the Unified Average Changing Intensity (UACI) and Non-Linear Pixel Change Rate (NPCR), confirming its resistance to differential attacks. Overall, our technique advances lightweight cryptography by providing a robust and efficient solution to modern cybersecurity challenges. In particular, our approach is well-suited for applications with limited resources, ensuring that security is maintained without compromising on performance or efficiency, thus fulfilling the needs of modern, constrained environments.

Rethinking Regional High-Quality Development Pathways from a Carbon Emission Efficiency Perspective

Optimizing resource efficiency and mitigating climate change have become consensuses of human society. However, there is still a gap in assessing the carbon emission efficiency (CEE) and identifying the influence of various factors, especially in rapid urbanizing regions. In this paper, we built a stochastic frontier analysis model to assess CEE and conducted a case study in the Beijing–Tianjin–Hebei Urban Agglomeration (BTHUA), a typical area of collaborative development in China. A comprehensive influencing factor index was constructed to analyze and identify the key influencing factors of CEE. The results revealed that the average CEE among the 13 cities increased in volatility from 2000 to 2019. The average CEE in Langfang was lowest, while that in Tangshan was highest. The input-related factors had a negative effect on CEE, including carbon emissions per capita, employment per ten thousand people, total assets per capita, and energy intensity. GDP per capita, the urbanization level, and the proportion of the tertiary sector’s GDP had positive impacts on CEE. Future policy formulation should focus on the transition from labor- and material-intensive industries to knowledge- and technology-intensive industries. All the results can contribute to achieving high-quality development and dual-carbon target of rapid-urbanizing areas.

Exploring the paradox of densification and greening in China’ s old cities

Urban densification is widely regarded as a key strategy for curbing urban sprawl and optimizing resource efficiency. However, it still threatens urban greenspaces by altering the original land use. The imperative to preserve and restore urban greenspaces has gained increased attention, aligning with the global spotlight on urban resilience. This prompts the crucial question: How will urban densification impact urban greening? Focusing on the old city areas of 159 cities with over one million population in China, we depicted the dynamics of urban greenness using remote sensing data and explored greening trends under urban densification on both horizontal and vertical scales by generalized additive model (GAM). The findings are as follows: (1) As urban horizontal density increased from 68.4 % to 93.1 %, a significant U-shaped trend in urban greenness emerged within the old city areas over the past three decades. Notably, 80 % of these cities experienced turning points before 2010. (2) Almost half of the cities have recovered the urban greenness to 30 years ago, with a growth of 6.58 % on average. While urban densification led to a loss of greenness (-0.0197±0.0182), urban greenspaces countered this with a gain of 0.0049±0.0075, and the original built-up area contributed a gain of 0.0027±0.0284. (3) We decomposed urban densification into horizontal and vertical growth. The horizontal growth coincides with the greenness loss initially, but the rebound occurs when the horizontal density approaches 83 %. Vertical growth, on the other hand, is negatively correlated with urban greenness. Our study depicts the turning point of urban greening in old city areas unveiling the ecological effect of urban densification, which provides a reference for the sustainable development of future urbanization.

Architectural approach to evaluate the design and management of almond cultivars suitable for super high-density orchards.

The almond tree is a major global nut crop, and its production has surged dramatically in recent years. Super high-density (SHD) planting systems, designed to optimize resource efficiency and enhance precocity, have gained prominence in almond cultivation. A shift in cropping systems toward sustainable intensification (SI) pathways is imperative, and so maximizing branching density within the canopies of SHD trees is crucial to establish and maintain productive potential, especially for hedge-pruned trees. This study investigates the influence of different almond cultivars grafted onto a novel growth-controlling rootstock on tree architectural and growth parameters in a SHD orchard. This open field research provided valuable insights for the development and application of new tools and methods to increase productivity and sustainability in almond growing. Three cultivars (Lauranne® Avijour, Guara Tuono, and Filippo Cea) were evaluated in Gravina in Puglia (BA) over a two-year period. Canopy growth parameters, such as canopy volume and trunk cross-sectional area, and architectural traits, like branching density, branching angle, number and length of subterminal shoots, and number of brachyblasts, were measured through qualitative and quantitative measurements. Results revealed significant differences in tree height, canopy thickness, width, volume, and vigor among the cultivars. Architectural traits, including branch parameters, brachyblast parameters, and subterminal shoots, varied among the cultivars. Lauranne displayed a more compact well-distributed canopy and exhibited the lowest vigor. Filippo Cea showed the highest vigor and the greatest canopy volume. Tuono had a higher number of buds and bud density. The best ideotype for SHD orchards is a smaller tree, with high branching density and smaller trunk diameters, i.e. the vigor. Cv. Lauranne seemed to be the best cultivar, mostly with the lowest tree vigor of all the cultivars involved. These findings provide valuable insights for almond growers and breeders seeking to optimize orchard design and management for enhanced SHD orchards productivity and sustainability. Future research will explore the relationship between canopy architecture and yield parameters, considering different scion/rootstock combinations in different environmental conditions.

The Complex Approach to Environmental and Technological Project Management to Enhance the Sustainability of Industrial Systems

To achieve sustainability, industrial systems need to be modernized to improve resource efficiency while optimizing environmental and social performance. The implementation of environmental and technological projects is a complex management process and requires sufficient innovative potential and serious investments, which not every company can provide. Network integration of companies, providing synergy of resources and potentials, is an effective tool for the development and implementation of innovative technologies that allow achieving optimal resource efficiency indicators. An integrated complex approach to the formation of a cross- industrial system on the principles of network integration and partnerships ensures technological interaction between companies, optimizes the methods and forms of their economic activities, allows integration participants to achieve strategic goals and ensure environmental and social effects for the territory of presence. The sustainability of such a system is expressed in its ability to withstand internal threats and external challenges. Approaches to balancing environmental and technological effects while simultaneously analysing social efficiency have not received sufficient development in scientific research. This article discusses an approach to the selection of environmental-technological projects based on criteria for assessing the sustainability and resilience of industrial systems. The authors’ approach has been tested using two industrial symbioses of advanced socio-economic development territories in the city of Novotroitsk (Orenburg region, Russian Federation). The authors presented calculated indicators of resource efficiency before and after the formation of a cross-sectoral industrial system in order to identify social and environmental effects in Novotroitsk. This approach to the assessment of environmental and technological projects allows to concentrate government support measures on the general priorities of the implementation of regional economic and industrial policies.

Mapping the Sustainability of Waste-to-Energy Processes for Food Loss and Waste in Mexico—Part 1: Energy Feasibility Study

Mexico generated 8.9 Mt of food loss and waste (FLW) at food distribution and retail centers in the year 2022. Traditional management methods in Latin America primarily involve final disposal sites, contributing to national greenhouse gas emissions of 0.22 Mt CO2 eq y−1. This creates an urgent need for sustainable valorization strategies for FLW to mitigate environmental impacts. This comprehensive study analyzes the geographical distribution of FLW generation and proposes a valorization approach using WtE-AD plants. Geographic information systems were employed for geographical analysis, life cycle assessment was used for environmental evaluation, and circular economy business models were applied for sustainability assessment. The primary objective of this first part of the contribution is to evaluate the technical feasibility of implementing waste-to-energy anaerobic digestion (WtE-AD) plants for FLW management in Mexico considering their geographical locations. The results demonstrate that WtE-AD plants with treatment capacities exceeding 8 t d−1 can achieve positive energy balances and significantly reduce greenhouse gas emissions. Specific findings indicate that these plants are viable for large-scale implementation, with larger plants showing resilience to increased transport distances while maintaining energy efficiency. The results highlight the critical influence of methane yields and transport distances on plant energy performance. This study underscores the importance of strategically placing and scaling WtE-AD plants to optimize resource efficiency and environmental sustainability. These findings provide essential insights for policymakers and stakeholders advocating for the transition of Mexico’s food supply chain toward a circular economy. Future parts of this study will explore detailed economic analyses and the policy frameworks necessary for the large-scale implementation of WtE-AD plants in Mexico. Further research should continue to develop innovative strategies to enhance the techno-economic and environmental performance of WtE-AD processes, ensuring sustainable FLW management and energy recovery.

IMPACT ASSESSMENT OF MACHINE LEARNING ALGORITHMS ON RESOURCE EFFICIENCY AND MANAGEMENT IN URBAN DEVELOPMENTS

Urban centers face the mounting challenge of balancing resource demands with sustainable practices in the face of population growth and environmental concerns. Machine learning (ML) has emerged as a transformative technology with the potential to optimize resource efficiency and management within urban environments. This article investigates the multifaceted impact of ML algorithms on enhancing resource management and the associated challenges and considerations. It delves into successful ML applications in vital urban sectors, including smart grids, water conservation, and intelligent transportation systems. Through the analysis of case studies, the article quantifies improvements in resource efficiency and highlights the contributions of ML to data-driven decision-making. Crucially, it emphasizes the need for a holistic approach, addressing computational costs, data bias, privacy concerns, and ethical considerations to ensure the responsible and equitable deployment of ML. The article concludes by underscoring the ongoing evolution of ML and its pivotal role in shaping sustainable and resilient urban futures.

Towards achieving the sustainable development goals: a collaborative action plan leveraging the circular economy potentials

This contribution to the journal “Gruppe. Interaktion. Organisation. (GIO)” delves into the critical role of Sustainable Development Goal 17 (SDG 17), “Partnership for the Goals,” in fostering interdisciplinary collaboration to further circular economy objectives. Aiming to address the existing research focus on isolated technical aspects within the circular economy, this study uses an expertise- and interaction-based foresight process to integrate perspectives from business, engineering, social sciences, and work and organizational psychology to unearth broader, interconnected challenges and solutions for the implementation of circular economy practices. Based on the pooled experience of experts within the foresight process, this contribution elucidates major challenges, ongoing issues, and prospective hurdles to be tackled by 2030 in circular economy, presenting an action plan centered on interdisciplinary cooperation and stakeholder engagement to advance labor conditions and continuous learning, sustainable and regenerative systems, minimize waste, and optimize resource efficiency. The collaborative action plan serves as a pivotal resource for the transformation task for researchers and practitioners, offers insights and strategic directions for implementing circular economy practices, and emphasizes collective responsibility and action in achieving global sustainability, all while aligning with the principles of SDG 17. The presented collaborative approach propels the discourse on sustainability forward, highlighting the potential of the circular economy in realizing a more sustainable world by 2030.

Effects of the Plastic Mulching System and Fertilizer Application on the Yield of Tartary Buckwheat (Fagopyrum tataricum) and Water Consumption Characteristics in a Semi-arid Area

Although plastic film mulching is commonly utilized to enhance crop water use efficiency (WUE) in semi-arid areas, the combined effect of plastic film mulching and fertilizer application on Tartary buckwheat yield is still unknown. To address this gap, a four-year field experiment was conducted from 2018 to 2021 to investigate the effect of plastic film mulching and fertilizers on the soil water storage, plant growth, yield, and WUE of Tartary buckwheat in semi-arid environments. The treatments comprised traditional planting without fertilizer (TNF), traditional planting with fertilizer application (N–P2O5–K2O: 40–30–20 kg ha−1) (TF), plastic film mulching with fertilizer application (N–P2O5–K2O: 40–30–20 kg ha−1) (MF), and plastic film mulching without fertilizer (MNF). The results indicated that MF treatment significantly increased leaf area index and SPAD values compared to the other treatments. The yield of Tartary buckwheat under the film mulching increased by 23.3% in comparison to no-mulching treatments, and under fertilizer application it increased by 18.2% compared to no fertilizer. WUE under film mulching exhibited an increase of 3.1% in 2018, 34.9% in 2019, 45.5% in 2020, and 34.6% in 2021, respectively, compared to no mulching. The impact of film mulching on WUE was more significant in years with lower precipitation compared to those with normal or higher precipitation levels. Overall, MF significantly enhanced both the yield and WUE of Tartary buckwheat. This approach proved to be an effective strategy for bolstering drought-resistant yield and optimizing resource efficiency in Tartary buckwheat cultivation in semi-arid regions. Moreover, the positive effects of plastic mulching and fertilizer application on grain yield and water use efficiency were more pronounced in drier years.

Submental Island Flaps for Lateral Reconstruction: Technical Refinements for Optimal Outcomes and Resource Efficiency.

To describe our modifications to the submental island flap (SMIF) in a case series that demonstrates improved reproducibility, shortened length of stay (LOS),and reduced utilization of hospital resources. This retrospective case series with chart review included adult patients who underwent resection of malignant or benign tumors resulting in lateral facial, parotid, or temporal bone defects, which were reconstructed with SMIF. A tertiary-care academic referral center. Retrospective case series included all adult patients who underwent SMIF reconstruction between March 2020 and August 2021. Patient demographic and clinical data were collected. Primary outcomes were measures of hospital utilization including duration of surgery, LOS, and postoperative outcomes. Twenty-eight patients were included with a mean age of 71.7 years. Eighty percent were male. All patients underwent parotidectomy, and the mean operative time was 347minutes. The median LOS was 2.5 days (range 0-16 days). Seventy-five percent of the flaps drained into the internal jugular vein, and 25% drained into the external jugular vein. No patients required reoperation or readmission. All flaps survived. SMIFs are a safe and effective option for reconstruction of lateral facial, parotid, and temporal bone defects. Compared to free flap reconstruction, SMIFs offer reduced length of surgery, decreased use of health care resources, and lower rate of reoperation. As health care resource allocation is increasingly important, the SMIF offers an excellent alternative to free flap reconstruction of lateral defects.

Revolutionizing Cloud-Based Task Scheduling: A Novel Hybrid Algorithm for Optimal Resource Allocation and Efficiency in Contemporary Networked Systems

Revolutionizing Cloud-Based Task Scheduling: A Novel Hybrid Algorithm for Optimal Resource Allocation and Efficiency in Contemporary Networked Systems

Drip irrigation on productivity, water use efficiency and profitability of turmeric (Curcuma longa) grown under mulched and non-mulched conditions

Turmeric cultivation primarily thrives in India, with significant presence in Bangladesh, Thailand, Cambodia, China, Indonesia, Philippines, and Malaysia. India leads globally in both area (0.19 Mha) and production (0.844 MT) of turmeric. Despite this, there's a recognized gap in research regarding the combined effects of mulching and drip fertigation on turmeric growth in Tamil Nadu conditions. Therefore, this study aims to assess how mulching and drip fertigation impact water usage, turmeric growth, productivity, and post-harvest soil health via field experiments. The treatments comprise of different mulching techniques (M1-25 μm Plastic Mulching, M2-50 μm Plastic Mulching, M3- Organic Mulching, M4-No Mulching) as the main plot, coupled with various irrigation regimes as the sub plot (S1-100% of pan evaporation, S2- 80% of pan evaporation, S3- 60% of pan evaporation), in a split plot design. Findings show that 50-μm Plastic Mulching (M2) notably enhances turmeric growth parameters, including plant height, biomass, leaf count, and yield attributes such as tillers and rhizomes, compared to no mulch. Significantly, when 80% of pan evaporation is utilized in drip irrigation, it showcases the most pronounced plant growth and yield characteristics, with plastic mulch at this level significantly improving water and nutrient use efficiency while increasing beneficial compounds like Curcumin and oleoresin. The highest fresh rhizome yield is observed with 50-μm plastic mulch and 80% pan evaporation (M2S2), displaying a 39.79% increase compared to the control. Additionally, the study notes effects on microbial populations and mulch degradation. Economically, M2S2 exhibits the highest profitability with a benefit-cost ratio of 3.23 compared to other treatments. Implementing these practices not only enhances yields but also conserves water (estimated at 9.15 mm3) while emphasizing the importance of drip irrigation, fertilizer application, and mulching in boosting turmeric productivity, optimizing resource efficiency, and ensuring economic and environmental sustainability.

A Comprehensive Farm Efficiency Analysis of Apple Growers in Newley Merged District South Waziristan

In the apple-producing land of South Waziristan’s three tehsils, Wana, Bermal, and Tiarza, this research paper is designed to analyze farmers' efficiencies, e.g., production, allocative and technical dimensions. Through a Data Envelopment Analysis (DEA) framework, the study evaluates the performance trajectories of 304 apple growers. A multistage sampling technique was used for the farmer’s interview. To the researcher’s knowledge, there is no detailed efficiency analysis of South Waziristan’s apple growers in existing literature, so there is a need to investigate the factors affecting efficiencies in the targeted area. The researcher is therefore encouraged to conduct a study of the farm efficiency of apple growers in South Waziristan. Apple growers' efficiencies were categorized as technical, allocative, and economic efficiency using the DEA approach. Results of the study show that there were tremendous inefficiencies of apple growers, which need to be reduced. This study sheds light on optimal resource allocation, productivity dynamics, and efficiency frontiers within apple cultivation in South Waziristan. The research offers an understanding of agricultural practices, resource utilization patterns, and efficiency benchmarks. The empirical insights derived from this comprehensive analysis facilitate informed decision-making among farmers and provide policymakers, agricultural stakeholders, and development practitioners with actionable recommendations to enhance agricultural productivity, sustainability, and socio-economic well-being in the region. Through empirical evidence and contextual relevance, this paper contributes significantly to the evolving discourse on agricultural efficiency analysis and underscores the imperative of tailored interventions for optimizing apple cultivation practices in South Waziristan.

Resource-aware multi-criteria vehicle participation for federated learning in Internet of vehicles

Federated learning (FL), as a safe distributed training mode, provides strong support for the edge intelligence of the Internet of Vehicles (IoV) to realize efficient collaborative control and safe data sharing. However, due to the resource limitation and the instability of training environment in the complex IoV, ideal performance of FL cannot be achieved. Since considering the actual resource constraints and federated task requirements, the diversified device selection criteria make the resource-aware vehicle selection problem become a multi-criteria selection problem. To effectively support FL for IoV, the resource-aware multi-criteria vehicle selection problem was described as a many-objective optimization problem, and a resource-aware many-objective vehicle selection model (RA-MaOVSM) is proposed to optimize resource efficiency. The RA-MaOVSM considering heterogeneous resources (like computation resources, communication resources, energy resources and data resources) of on-board devices in IoV, and realizes the joint optimization of learning efficiency, energy cost and global performance. Additionally, a novel probability distribution combination game strategy is applied to many-objective evolutionary algorithm (MaOEA) for improving the model solving performance. Simulation results demonstrate that RA-MaOVSM can effectively optimize the IoV resources and FL model performance, and the designed algorithm exhibits good convergence and distribution, achieving a good balance among multiple device selection criteria.

Unified ensemble federated learning with cloud computing for online anomaly detection in energy-efficient wireless sensor networks

Anomaly detection in Wireless Sensor Networks (WSNs) is critical for their reliable and secure operation. Optimizing resource efficiency is crucial for reducing energy consumption. Two new algorithms developed for anomaly detection in WSNs—Ensemble Federated Learning (EFL) with Cloud Integration and Online Anomaly Detection with Energy-Efficient Techniques (OAD-EE) with Cloud-based Model Aggregation. EFL with Cloud Integration uses ensemble methods and federated learning to enhance detection accuracy and data privacy. OAD-EE with Cloud-based Model Aggregation uses online learning and energy-efficient techniques to conserve energy on resource-constrained sensor nodes. By combining EFL and OAD-EE, a comprehensive and efficient framework for anomaly detection in WSNs can be created. Experimental results show that EFL with Cloud Integration achieves the highest detection accuracy, while OAD-EE with Cloud-based Model Aggregation has the lowest energy consumption and fastest detection time among all algorithms, making it suitable for real-time applications. The unified algorithm contributes to the system's overall efficiency, scalability, and real-time response. By integrating cloud computing, this algorithm opens new avenues for advanced WSN applications. These promising approaches for anomaly detection in resource constrained and large-scale WSNs are beneficial for industrial applications.