Search Results (530)

As a distributed approach to Artificial Intelligence (AI) model construction over wireless networks, federated learning (FL) based on multi-device collaborative training can protect data privacy, as well as increase the computing load of local model updates. In contrast, split learning (SL) with proper model splitting can adapt to the computation and transmission capabilities among devices. In this paper, while taking advantage of FL and SL, we concentrate on a semi-decentralized hybrid federated split learning (SD-HFSL) framework, in which we surpass the limitations of a single central server and allow the shared split models to be aggregated among multiple edge servers. To verify the importance of latency optimization for training efficiency, we analyze the convergence performance of SD-HFSL while jointly considering the limited computation and communication resources. Then, aiming at maximizing the long-term training efficiency, we propose an online optimization problem that includes local model splitting and device association. Considering that the training latency is unknown to the system a priori, a context-aware online training algorithm with sublinear regret is proposed based on the framework of contextual multi-armed bandit (CMAB), where the edge servers can observe the context information of device sites for latency estimation, followed by the iterative optimization based on the evaluated information in different contexts. Experiments on several neural network models show that the proposed algorithm reduces training latency and improves test accuracy compared with the selected benchmarks. Full article

Solar-driven interfacial evaporation (SIE) has emerged as a transformative, off-grid technology that confines heat at the air–liquid interface, enabling high-efficiency vapor generation for decentralized water purification. Here, we present a comprehensive and critical review of the field, tracing its evolution from fundamental photothermal principles to integrated multifunctional systems. We first elucidate the thermodynamics of interfacial heat localization and the resultant enhancement in evaporation efficiency. We then systematically analyze material innovation strategies—including broadband-absorbing photothermal agents and tailored evaporator architectures—designed to overcome persistent challenges such as salt crystallization, fouling, and thermal losses. Moving beyond freshwater production, we highlight emerging pathways for extending SIE platforms toward water–energy cogeneration, selective resource recovery, and zero-liquid-discharge wastewater treatment. We further identify and objectively assess the key bottlenecks that currently hinder the transition from laboratory-scale prototypes to real-world deployment, with a focus on long-term material robustness under harsh environments, adaptability to fluctuating water chemistries, and techno-economic viability. Finally, we outline forward-looking research directions, including stimulus-responsive smart evaporators, elucidation of multi-field coupling mechanisms, and the establishment of standardized performance evaluation protocols. This review aims to provide both a tutorial for newcomers and a critical assessment for experienced researchers, offering a balanced perspective on the current state-of-the-art and a roadmap for translating SIE from academic research into sustainable, impactful technologies. Full article

Resource allocation for cognitive Vehicle-to-Everything (V2X) networks is challenging due to dynamic spectrum sharing, strong interference coupling, and stringent latency constraints for safety-critical Vehicle-to-Vehicle (V2V) traffic. Although recent Multi-Agent Reinforcement Learning (MARL) approaches report promising gains, many evaluations are conducted at limited and fixed network scales, which restricts insights into scalability under dense spectrum reuse. This paper investigates cooperative multi-agent learning for interference-aware and deadline-constrained V2X resource management. We propose a Q-value Transformation (QTRAN)-based value decomposition framework under centralized training with decentralized execution (CTDE) for joint resource-block and power allocation among V2V agents. The proposed approach is implemented in a realistic V2V/V2I simulator incorporating Manhattan grid mobility, fast fading, explicit cross-tier and co-channel interference, and per-link payload/deadline dynamics. Beyond communication-level performance, improved timely delivery of V2V safety messages can support cooperative maneuvering, collision avoidance, platooning, and infrastructure-assisted traffic management. Extensive simulations across varying numbers of V2V agents benchmark QTRAN against independent learning baselines including MARL and centralized single-agent learning (SARL). Results show that QTRAN improves performance compared with the selected learning baselines and enhances the throughput–reliability trade-off under interference-coupled spectrum reuse. For instance, at $N_{\mathrm{V}2\mathrm{V}}=20$, QTRAN achieves a V2V rate of $0.194\pm 0.004$ and a V2I rate of $9.117\pm 0.213$, while reaching a V2V success rate of $0.812\pm 0.017$ with a low Deadline Miss Ratio of $0.001\pm 0.000$. At higher density ($N_{\mathrm{V}2\mathrm{V}}=50$), QTRAN sustains strong reliability (V2V success rate of $0.719\pm 0.006$ and Completion Ratio of $0.716\pm 0.006$) while maintaining competitive infrastructure throughput (V2I rate of $9.251\pm 0.114$). These results indicate that QTRAN effectively captures non-linear interference interactions, enabling coordinated decentralized spectrum and power decisions under the adopted density-based evaluation setting, thereby enhancing V2V reliability and throughput in cognitive Internet of Vehicles. Full article

The proliferation of large language model (LLM) agents has enabled increasingly complex multi-step automation; however, composing multiple agents into coherent systems introduces significant orchestration challenges that remain poorly documented. This survey examines LLM-based multi-agent orchestration from 2023 through early 2026 (literature cutoff: March 2026), with explicit attention to the evidence hierarchy used to interpret deployment claims. We propose a three-topology, one-adaptivity taxonomy—centralized, decentralized, and hierarchical coordination topologies, each optionally augmented with a dynamic–adaptive control axis—grounded in classical multi-agent systems theory and recent empirical evidence. We compare six leading frameworks (LangGraph, CrewAI, AutoGen/Microsoft Agent Framework, OpenAI Agents SDK, MetaGPT, and DSPy) along axes directly relevant to practitioners: state-management granularity, token-cost structure, failure-recovery options, and design philosophy. The emerging protocol stack is examined in terms of why MCP (agent-to-tool) and A2A (agent-to-agent) occupy complementary layers, how the ACP–A2A merger signals protocol convergence, and where ANP’s decentralized-discovery design fits. Production design considerations—state management, task planning, error handling, scalability, and security—are evaluated with reference to published benchmarks. Vendor-reported figures are marked † throughout and held to a documented evidence hierarchy, which separates them from peer-reviewed and government-evaluator measurements. We close by identifying eight open challenges and proposing a six-dimension evaluation framework for multi-agent coordination quality. This paper offers practitioners a decision framework covering taxonomy, framework selection, protocol adoption, and early operational pilots. Full article

Acid phosphatase (ACP) is a clinically important enzyme whose early-stage detection is hindered by its extremely low abundance, nonspecific tissue distribution, and rapid loss of activity under conventional analytical conditions. Herein, we present a target-driven in situ nanozyme synthesis strategy that enables rapid and ultrasensitive point-of-care testing (POCT) of ACP. In this approach, ACP catalyzes the hydrolysis of L-ascorbic acid 2-phosphate sesquimagnesium (AAPS), producing ascorbic acid (AA). The generated AA partially reduces Fe³⁺ ions to Fe²⁺, thereby initiating alkaline co-precipitation and in situ formation of Fe₃O₄ nanoparticles. Polyvinylpyrrolidone (PVP) stabilizes the nanoparticles and preserves catalytic accessibility, while their intrinsic magnetism allows for efficient magnetic separation to eliminate matrix interference. The resulting Fe₃O₄@PVP nanozymes display pronounced peroxidase-like activity, catalyzing hydrogen-peroxide-mediated oxidation of 3,3′,5,5′-tetramethylbenzidine (TMB). Quantitative readout can be achieved using either spectrophotometric analysis or smartphone imaging. The sensing platform achieves a detection limit of 0.021 U/L within 40 min and demonstrates excellent sensitivity, selectivity, and operational robustness. Successful validation in human serum confirms its clinical feasibility, while smartphone-based imaging enables portable and low-cost quantification suitable for decentralized diagnostics. Collectively, this work establishes a generalizable paradigm for target-triggered nanozyme generation aimed at detecting low-abundance and labile biomarkers. Full article

As robotic systems evolve toward large-scale distributed architectures and cloud-edge collaboration, communication middleware has become a critical infrastructure that impacts system real-time performance and scalability. The traditional Robot Operating System 1 (ROS 1) communication architecture, which relies on a centralized master node, has limitations in dynamic network environments. Robot Operating System 2 (ROS 2) achieves decentralized communication through the introduction of DDS. However, the single Data Distribution Service (DDS) mechanism remains inadequate for cross-network communication and high-performance local data exchange. Addressing the current issue in ROS communication research: the coexistence of multiple mechanisms without a unified analytical framework or guidance for selection. This paper systematically traces the evolution of the ROS communication architecture from centralized to distributed systems. It constructs a unified analytical framework covering two dimensions: communication models and data transmission paths. Crucially, to overcome the unreliability of cross-protocol comparisons based on heterogeneous literature, this paper designs and executes a set of unified benchmark experiments on a controlled testbed. These experiments systematically evaluate the performance of two mainstream DDS implementations (CycloneDDS and FastDDS) across five key metrics: latency, throughput, jitter, scalability, and packet loss rate under load. Additionally, a comprehensive comparative analysis of the performance of three transmission modes is conducted. Based on this comprehensive evaluation, this paper summarizes the performance characteristics of different mechanisms and further proposes an optimization-based middleware selection method for quantitative communication mechanism selection under different workload and application requirements. This paper provides a systematic reference for the design and optimization of ROS communication systems and offers guidance for promoting the application of multi-middleware collaborative architectures in robotic systems. Full article

This study examines experiential and financial factors associated with Metaverse readiness in Lebanon. Drawing on a socio-technical readiness perspective informed by selected concepts from technology adoption literature, the study explores how interest in immersive technologies, remote work experience, and perceived financial security in decentralized digital assets relate to individual readiness and perceived organizational expectations. Using an exploratory cross-sectional survey of 231 respondents, multiple regression analyses were conducted to examine these associations. The findings indicate that interest in VR/AR technologies and positive remote work experience are positively associated with individual willingness to use the Metaverse for work, education, or professional activities. Perceived financial security in decentralized digital assets is also positively associated with perceived organizational benefit expectations. The results suggest that Metaverse readiness is linked not only to technological interest but also to prior digital collaboration experience and financial trust. By focusing on Lebanon as a developing and crisis-affected economy, the study contributes a context-sensitive and perception-based understanding of readiness for immersive digital ecosystems. Practical implications are discussed for organizations and policymakers seeking to support responsible digital transformation. Full article

The hydrological prediction in transboundary river basins is difficult because of their heterogeneous data distribution, restrictions of data sovereignty, and the irregular nature of the discharge pattern. In this paper, Federated Learning (FL) with an LSTM neural network is proposed for next-day predictions of discharge in the Chu–Talas transboundary basin. The basin area belongs to both Kazakhstan and Kyrgyzstan. In an FL scenario, two hydrological stations from the basin were selected as client nodes, representing two different discharge regimes. Station 15125—the Chu main channel is characterized by the highest discharge regime among stations located in the basin, while Station 15233—Merke tributary represents a small catchment with an irregular regime. The federated LSTM model is compared against a centralized LSTM and a local-only LSTM baseline model. The training process is based on nearly three decades of daily discharge measurements. The preprocessing step includes synchronization, lag calculation, and windowing operation. The models are trained using three metrics: root mean square error, mean absolute error, and Nash–Sutcliffe Efficiency, as well as using Monte Carlo Dropout for estimation of the probabilistic uncertainty. The results demonstrate that the federated model demonstrates comparable performance with the centralized one for the Chu main channel. It also improves prediction accuracy for the smaller Merke tributary compared with both centralized and local-only models. These findings show that FL can work effectively with non-IID and heterogeneous hydrological data. The study makes three main contributions: (i) it implements the FedAvg algorithm on transboundary, heterogeneous hydrological data, proving that decentralized optimization can effectively capture autoregressive temporal hydrology without data centralization; (ii) it systematically compares federated, centralized, and local-only models, demonstrating that the federated approach eliminates the scale bias that traditionally neglects smaller, high-variance catchments; and (iii) it utilizes Monte Carlo Dropout to translate deterministic AI outputs into risk-aware probabilistic bounds. Ultimately, the results of this study demonstrate the practical and scientific usefulness of FL in operational water management, as the method presents a privacy-saving means of increasing predictive capacity and enabling risk-based decision-making in transboundary river basins. Full article

This study investigates how the hydrogen supply chain should be designed under alternative carbon tax scenarios to decarbonize heavy-duty freight transportation. A bi-objective, multi-period optimization model is developed to minimize the total daily system cost while constraining CO₂ emissions using the Augmented ε-constraint approach, thereby revealing the trade-off between economic and environmental objectives. The model was applied to Türkiye’s heavy-duty transportation sector and solved under zero, moderate, and aggressive carbon tax scenarios. The results show that the levelized cost of hydrogen (LCOH) ranges from 2.06 to 14.06 $/kg H₂. High carbon pricing increases the LCOH by 29.06% in hybrid designs, while raising the renewable energy share from 2.04% to 46.97% in centralized supply chains. Sensitivity analysis reveals that a ±20% variation in electrolyzer-based production costs does not alter the network topology but shifts the LCOH between 13.10 and 15.02 $/kg H₂ in emission-focused solutions. The findings indicate that in renewable-energy-based decentralized structures, higher carbon tax policies primarily increase the LCOH. Still, the overall technology mix and network topology remain largely unchanged compared to the no-tax case. However, in centralized supply chains, carbon pricing affects both the energy sources and selected technologies. By integrating Türkiye’s 2030–2053 policy milestones into a multi-period framework, this study distinguishes itself by providing a comprehensive, multi-period planning framework tailored to the economic and logistical realities of developing countries. Unlike existing models, our approach quantifies how evolving carbon tax trajectories decisively drive infrastructure investment by analyzing the direct impact of different tax levels on the operational and strategic decisions of heavy-duty transport. This research represents the first joint assessment of carbon tax policy instruments and the evolution of long-term hydrogen supply chains, offering a decision-making framework for policy-driven energy transitions in similar emerging economies. Full article

Autonomous UAV landing on dynamic unmanned surface vessel platforms is affected by deck motion and degraded visual observations, which may lead to unsafe final descent decisions. This paper proposes a fully decentralized reliability-enhanced predictive landing method that combines probabilistic perception, visual quality assessment, and model predictive control. Target posterior probability, perception uncertainty, and task-oriented image quality are fused into an online observation reliability index, which is used to adapt observation noise, constrain phase switching, and penalize unreliable descent opportunities. FFT-based dominant-mode identification and Kalman correction are also used to predict deck roll and pitch for landing-window selection. Simulation results show that the proposed method achieves a 90% small-angle landing success rate and keeps the touchdown attitude angle within 5°. Compared with standard MPC, landings within a 15° deck inclination increase from 24% to 82%, and the 80th-percentile touchdown inclination decreases by 9°. Compared with SHMPC, the average solution time decreases from 913 ms to approximately 104 ms per iteration. These results indicate that the proposed reliability-aware framework can reduce unsafe descent decisions and improve landing robustness while maintaining real-time feasibility under degraded maritime visual conditions. Full article

The rapid integration of photovoltaic (PV) generation into active distribution networks (ADNs) creates a fundamental tension between maintaining tight voltage regulation and accommodating high distributed energy resource (DER) penetration levels. Conventional voltage control methods such as the droop control operate locally without coordination, while centralized optimal power flow requires full network observability and reliable real-time communication. Multi-agent deep reinforcement learning (MADRL) methods provide adaptive coordination but suffer from long training times and algorithmic complexity that prevent direct deployment on embedded inverter hardware. This paper proposes the Optimal Historical Selection and Forecasting (OHSF) scheme: a physics-informed long short-term memory (LSTM) network combined with an online sensitivity-based correction loop for medium-voltage ADNs. A composite loss function incorporating data-driven regression, an inter-PV voltage sensitivity penalty, and an inverter capability constraint produces reactive power setpoints that are inherently aware of physical limits, while the correction loop refines the predictions using real-time AC power flow feedback. The OHSF scheme supports a centralized full-network mode and a decentralized fallback mode in which the trained weights run locally on each inverter. Simulations under worst-case PV placement and network reconfiguration on the modified IEEE 33-bus and 69-bus test systems achieve an average voltage deviation across all PV buses of $0.701\%$ and $0.601\%$ at $172\%$ DER penetration on the 33-bus system, and $0.804\%$ and $0.806\%$ at $242\%$ DER penetration on the 69-bus system, while training 32 to 49 times faster than state-of-the-art MADRL methods. Full article

Efficient coordination under limited communication is a central challenge in multi-agent reinforcement learning (MARL). Existing approaches often focus on message exchange without explicitly modeling how communication affects policy learning, leading to redundant interactions and limited coordination gains. In this paper, we propose a threshold-gated sparse communication framework built upon QMIX, a monotonic value-decomposition method that mixes individual agent action values into a global team action value. In the proposed framework, communication is integrated into the agent utility function to directly influence policy learning. Each agent encodes local observations into structured representations and activates communication through a learned trigger mechanism. Messages are aggregated via neighbor-constrained attention and incorporated into utility estimation for decentralized decision-making. Experimental results on the StarCraft Multi-Agent Challenge (SMAC) benchmark show that the proposed method improves coordination quality and training stability while significantly reducing communication frequency. On MMM, the Marine–Marauder–Medivac heterogeneous scenario, the communication rate is reduced to approximately 30–38% while achieving up to 96.6% win rate, compared to 92.1% for QMIX. On 10m_vs_11m, a homogeneous scenario where ten allied Marines fight against eleven enemy Marines, communication remains within 28–37% while reaching 88.4% win rate, compared to 85.6% for QMIX. Moreover, on the same task, varying communication thresholds induce clearly differentiated policy behaviors, indicating that sparse communication not only reduces overhead but also plays a critical role in shaping coordination policies. These results demonstrate that selective communication enables efficient coordination while explicitly regulating policy formation. Full article

Federated Learning (FL) is a machine learning technique that preserves data privacy and security by training models directly on decentralized edge network devices. This generates substantial communication overhead due to the repeated exchange of model updates across numerous edge network devices. Quantization has tackled this challenge by reducing communication overhead and computational costs by quantizing model updates. Although selecting the most suitable quantization level to balance communication efficiency and model accuracy is challenging, failing to achieve this balance results in excessive compression, leading to accuracy degradation due to the lossy nature of the quantization technique. This challenge was tackled in this paper via a Quantile-based lossless compression method named Pcodec, which implements lossless compression in the FL context. Pcodec is a Quantile-based lossless compression algorithm designed for numerical data that utilizes mode identification with delta encoding and binning, where binning groups similar values into entropy-coded bins and stores the exact offset within each bin, thus achieving high compression ratios and efficient processing speed. Using MNIST and CIFAR-10 datasets and models such as CNN and ResNet18, we demonstrate that Pcodec achieves up to 58.19% size reduction with no accuracy loss compared to standard quantization methods. The experiments showed that the proposed Quantile-based compression approach in FL reduces up to 2.81× the communication overhead between each server and edge network device while maintaining the accuracy. In comparison to quantization, the Quantile approach reduced the communication overhead by 2.74×, tackling the main challenge of FL context by reducing communication overhead with a remarkably high compression ratio while maintaining the model’s accuracy. Full article

This study develops a bottom-up cost optimization model (DC-DECOM) to evaluate decarbonization pathways for Japan’s data center industry, targeting carbon neutrality of the information and communications technology (ICT) sector by 2040. The model represents Power Usage Effectiveness (PUE) as a dynamic function of ambient temperature and cooling technology, and integrates technology selection, regional energy supply, and carbon pricing within a single cost-minimization framework. Three scenarios are compared: a reference case (REF), a centralized carbon-neutral scenario (C-CN) that restricts new capacity to metropolitan areas, and a regional decentralization scenario (R-CN) that allows for nationwide siting. Input parameters are calibrated against data from the International Energy Agency (IEA), the Uptime Institute, Japan’s Ministry of Internal Affairs and Communications (MIC) White Papers, and the Japan Science and Technology Agency (JST). The R-CN scenario achieves the 2040 net-zero target at 18–23% lower total system cost than C-CN. The cost gap decomposes into four channels (cooling-energy reduction ∼35%, lower regional renewable procurement cost ∼30%, lower carbon cost ∼25%, and lower siting-related cost ∼10%). Sensitivity analysis identifies the carbon-price trajectory and the hardware-efficiency improvement rate as the most influential parameters; the R-CN advantage remains positive across all $\pm 1\sigma$ parameter variations and across two combined-scenario stress tests. Full article

Damage to urban water supply infrastructure can rapidly compromise access to safe water and force households to rely on alternative sources of uncertain quality. This study presents a case-based assessment of water quality and emergency household-level treatment options in Mykolaiv, Ukraine, following conflict-induced disruption of the centralized water supply system. Water samples collected from selected groundwater and distribution-network points were analyzed for physicochemical, organoleptic, and microbiological indicators, including total dissolved solids, hardness, sulfates, chlorides, iron, permanganate oxidizability, total microbial count, and E. coli. The results showed elevated mineralization, increased sulfate and chloride concentrations, high hardness, organic load indicators, and episodic microbiological contamination in several samples. A low-cost four-stage household treatment procedure combining chemical oxidation, thermal treatment, sorption, and short-term preservation was evaluated as a preliminary emergency approach. The procedure improved odor, taste, hardness, iron content, permanganate oxidizability, and microbiological safety; however, it did not fully reduce total dissolved solids, sulfates, or chlorides to drinking-water standards. Therefore, the treated water should be considered non-potable and suitable mainly for limited domestic and hygienic uses unless additional desalination or blending is applied. The study highlights both the potential and the limitations of simple household-level interventions under emergency water supply disruption and emphasizes the need for decentralized treatment support, monitoring, and long-term infrastructure recovery. Full article