Search Results (288)

Underground mining is a complex dynamic system. Traditional static analytical methods are insufficient to characterize the operational behavior and efficiency variations in such systems under coupled multidimensional constraints. To address this limitation, this study proposes a novel hybrid simulation-modeling method for underground mining processes with multidimensional constraints. The method integrates discrete-event simulation and agent-based simulation. It reconstructs the spatiotemporal constraints of multiple stopes, process constraints, and organizational constraints into an explicit multidimensional constraint system. Using the upward horizontal layered cut-and-fill mining method at the Sanshandao Gold Mine as an engineering case, a simulation model was established for development, cutting, stoping cycles, haulage, and backfilling. Key factors, including stope availability, backfill curing delays, centralized blasting, shift organization, and equipment availability, were embedded as explicit mechanisms. The results show that simulated operating time, production, and efficiency are generally consistent with field statistical data at multiple scales, including cycle operations, individual stopes, individual horizontal layers, and complete mining blocks. This indicates that the model can effectively reproduce the operating characteristics of the underground mining system under multidimensional constraints. Further analysis shows that production rhythm is governed by the combined effects of stope spatiotemporal relationships, process coordination, backfill waiting, and organizational resource constraints, rather than by single-process capacity. Spatiotemporal and process constraints define operation initiation and advancement sequence, while organizational constraints mainly appear as waiting accumulation, process disturbances, and resource-utilization fluctuations. The proposed method provides a reusable tool for capacity evaluation, production organization analysis, and decision optimization in complex underground mines. Full article

Significant challenges will be encountered in next-generation cellular networks to achieve both high spectral efficiency (SE) and diverse quality of service (QoS) requirements simultaneously, particularly under stringent bandwidth and power budgets within highly dynamic and dense topologies. To address these challenges, we formulate an optimization problem in a multi-slice non-orthogonal multiple access (NOMA) system with underlay device-to-device (D2D) communications. This problem aims to maximize SE and satisfy user QoS demands by jointly optimizing power allocation and resource block (RB) assignment. To solve this non-convex and NP-hard problem, we propose a resource allocation mechanism based on joint optimization and cooperative multi-agent deep reinforcement learning (MADRL). Specifically, we construct an optimization framework based on successive convex approximation (SCA) and the Lagrange duality method to derive an analytical iterative solution for the optimal power allocation under a given RB assignment, thereby avoiding the inherent discretization error of the action space in pure learning methods. Furthermore, we propose a cooperative multi-agent algorithm based on dueling double deep Q-Network (CMAD3QN) to address the discrete RB assignment problem. Simulation results demonstrate that, compared with benchmark schemes, the proposed scheme exhibits faster convergence speed and significantly enhances system spectral efficiency while ensuring slice isolation and resource constraints. Full article

The evolving landscape of cybersecurity threats, characterized by increasingly sophisticated and adaptive attackers, poses major challenges to traditional static network defense mechanisms. To address these limitations, this paper proposes an adaptive cyber defense framework that integrates Reinforcement Learning (RL) with Attack Graph (AG) modeling. The interaction between attacker and defender is formulated as a repeated zero-sum stochastic game over a partially observable Attack Graph-guided environment, allowing both agents to adapt their strategies through repeated interaction. Two value-based learning approaches are investigated, namely tabular Q-learning and Deep Q-Networks (DQN), under a unified attacker–defender setting. Experimental results across multiple training scenarios show that defender performance improves substantially as the training budget increases. Under limited training, Q-learning provides a computationally efficient and stable baseline, while DQN requires more training and careful tuning to achieve strong performance. However, with extended training, the DQN-based defender attains the highest win rate, albeit at a significantly greater computational cost. In addition, multi-run statistical comparisons highlight a clear trade-off between defensive effectiveness and runtime efficiency: Q-learning remains far more lightweight, whereas DQN offers stronger asymptotic performance when sufficient resources are available. These findings demonstrate the promise of learning-based adaptive defense over attack graphs while also emphasizing the importance of training budget, computational constraints, and model selection in practical cyber defense deployment. Full article

This study proposes a sustainable, integrated biorefinery approach to valorize mussel shell waste into high-value products, including chitin, chitosan, and calcium formate. Formic acid was employed as an effective demineralizing agent, enabling not only efficient mineral removal but also the direct conversion of the demineralization effluent into value-added calcium formate. The sequential extraction processes, demineralization, deproteinization, and decolorization, successfully yielded purified chitin (PCH), which was subsequently deacetylated to produce chitosan (CTS) with a degree of deacetylation of 85% and a molecular weight of 75 kDa. The physicochemical properties of all products were characterized using Fourier transform infrared spectroscopy (FTIR), X-ray diffraction (XRD), thermogravimetric analysis (TGA), and scanning electron microscopy (SEM). FTIR and XRD analyses confirmed the successful extraction of chitin and chitosan, demonstrating the feasibility of mussel shells as an alternative biopolymer source. In parallel, calcium formate (CCF) was obtained from the demineralization effluent with a yield of 94.19%, and its formation was verified by FTIR and XRD. Elemental analysis by XRF exhibited 98.3% CaO with minimal non-toxic impurities. The TGA/DTG profiles of CCF exhibited a well-defined two-step thermal decomposition, confirming its anhydrous form. Overall, this environmentally benign process enables the simultaneous production of multiple value-added products while significantly improving resource utilization and reducing waste generation. The proposed integrated biorefinery model offers a promising, economically viable pathway for marine biomass valorization, aligned with the Bio-Circular-Green (BCG) economy concept. Full article

To address the challenge of limited communication resources in microgrid economic dispatch, this paper proposes an improved dynamic event-triggered mechanism built upon a distributed event-triggered consensus algorithm. Firstly, a dynamic variable is introduced to adaptively adjust the triggering threshold, which effectively reduces the communication frequency between agents, thereby saving communication bandwidth and energy. Secondly, economic dispatch models are established for two scenarios: without generation constraints and with generation constraints. Corresponding distributed control protocols are designed. Thirdly, rigorous and clear mathematical proofs are provided for the asymptotic stability of the system and the exclusion of Zeno behavior. Simulation results demonstrate that the proposed method converges to the optimal incremental cost and power output. Compared with traditional static event-triggered mechanisms, the frequency of event triggering per unit time is reduced by approximately 51%, thereby effectively validating its effectiveness and superiority under multiple constraints. Full article

In IIoT edge computing, multi-edge server collaborative scheduling faces two core issues due to random task arrivals, heterogeneous resources, and complex topology: traditional model-driven methods cannot make dynamic decisions in dynamic environments, and conventional MARL fails to characterize inter-node topological dependencies and load correlations. To address this, this paper investigates the joint optimization of task offloading, computing resource allocation, and SFC orchestration in IIoT, constructs a cloud-edge-end collaborative architecture, and models the problem as a POMDP to minimize the overall system cost under multiple constraints. A graph-guided value-decomposition MARL method is proposed, which extracts spatial topology and neighborhood-load features of edge nodes via a GNN and combines them with the QMIX framework to realize multi-agent centralized training and distributed execution. Simulations show that the algorithm converges stably under different server scales and task loads, significantly outperforms benchmark algorithms, and can suppress performance degradation in high-load scenarios, demonstrating its robustness and scalability in complex industrial environments. Full article

Understanding the sustainable management of the complex adaptive tourism systems requires an integrated research approach that combines environmental processes with stakeholder behaviors. Agent-based modelling (ABM) has emerged as a pivotal tool for decoding the resilience, adaptability, and sustainability of tourism systems. However, the current application landscape, methodological limitations, and future research directions of ABM remain insufficiently synthesized, thereby constraining its full potential in advancing sustainable tourism management. This study examines 137 publications on the application of ABM in tourism research between 1989 and 2025, aiming to clarify the application characteristics and evolutionary trajectories. The results show the following: (1) ABM applications in tourism have become increasingly comprehensive and refined, evolving from simplistic simulations based on simplex agents and static spatial representations toward integrated models incorporating heterogeneous agents, fine-grained spatial environments, and multiple contextual factors. (2) Behavioral modeling has progressed from basic human–space interactions to complex, co-evolutionary dynamics among human, social, and ecological systems. (3) ABM applications exhibit context specificity: climate-sensitive scenarios emphasize resource dynamics and adaptation strategies; disaster-prone contexts focus on multi-agent responses and emergency management; conservation-oriented systems support sustainable policy development; and management-centric scenarios prioritize technological innovation and macro-level regulation. Future research should prioritize refining agent interactions through dynamic social network integration, incorporating cross-scale and long-distance system linkages, and strengthening the connection between theoretical modeling and real-world applications. This study would provide a comprehensive knowledge base for advancing the innovative application of ABM in sustainable tourism research and contribute to strengthening resilience, adaptive governance, and long-term sustainability within complex tourism systems. Full article

Plant fungal diseases, such as apple tree canker caused by Valsa mali, have caused severe losses in agricultural production. Traditional chemical fungicides induce drug resistance in pathogens and cause environmental pollution. Therefore, it is of substantial importance to screen efficient and environmentally friendly bacterial strains as potential biocontrol agents. The tea rhizosphere harbors abundant microbial resources, and previous research has identified microorganisms with antifungal activity existing in this environment. Therefore, in this study, we isolated antagonistic bacteria with broad-spectrum biocontrol potential from tea rhizosphere soil. In this study, a strain with strong antagonistic activity against V. mali was isolated from tea rhizosphere soil. Based on morphological characteristics, 16S rRNA gene sequencing, and whole-genome analysis, the isolated strain was identified as Bacillus velezensis and designated as LW-66. This strain demonstrated broad-spectrum antifungal activity against various plant pathogenic fungi, including Valsa mali, Fusarium graminearum, Bipolaris sorokinianum, Alternaria solani, and Exserohilum turcicum. The active extract of B. velezensis maintained strong stability across a wide range of temperatures (25–90 °C) and pH values (2–8), with stability decreasing only when the temperature reached 100 °C or pH ≥ 10. In a preventive assay using detached apple branches inoculated with V. mali, the control efficacy of LW-66 against apple tree canker reached more than 90%. Additionally, in a therapeutic assay using V. mali-infected potted apple seedlings, the LW-66 bone-glue bacterial agent achieved a survival rate of up to 90%. Whole-genome analysis revealed that the genome of LW-66 contains 13 predicted secondary metabolite biosynthetic gene clusters, seven of which showed high homology (≥92% similarity) with known antimicrobial gene clusters, including surfactin, bacillaene, macrolactin H, fengycin, difficidin, bacillibactin, and bacilysin. These gene clusters may be connected to the broad-spectrum antifungal activity of B. velezensis, as well as its ability to disrupt hyphal morphology. The volatile organic compounds produced by LW-66 inhibited V. mali growth by 91.70%. Collectively, these findings demonstrate that B. velezensis LW-66 has a wide antimicrobial range and strong antagonistic effects against multiple plant pathogenic fungi. Therefore, B. velezensis shows promise as a biocontrol agent for managing fungal diseases in plants, providing a basis for developing LW-66-derived biocontrol products aimed at controlling diseases such as apple tree canker. Full article

Building users are key participants in demand response (DR) markets, providing significant flexible resources. Due to uncertainty in market clearing prices, various risk-based decision models have been developed to describe their bidding behavior, typically assuming constant risk preferences. However, empirical evidence indicates that users’ risk attitudes vary with the magnitude of load adjustments. To capture this feature, this paper introduces mental accounting theory to model the risk-aware bidding behavior of building users. Total response capacity is divided into three independent mental accounts based on air-conditioning setpoint adjustment magnitude, representing risk-averse, risk-neutral, and risk-seeking behaviors. This framework allows multiple risk preferences to be represented within a unified bidding model. For each account, response quantity and cost models are developed. Bidding strategies under uncertain market clearing prices are formulated by incorporating loss aversion. A multi-agent simulation framework, including building users, a load aggregator, and a grid operator, is established to simulate the market clearing process. A simulation study is conducted using 19 building clusters located in Zhuhai, China. The proposed model is compared with a single-bid model and a step-wise bidding model with constant risk preferences. The results show that it better captures building users’ multiple risk preferences under market clearing price uncertainty. Users tend to secure stable returns through responses with minimal comfort loss, while pursuing excess profits via higher bids for responses involving greater comfort sacrifices. Full article

Patient Blood Management (PBM) has evolved from a transfusion-centered practice to a structured, patient-focused perioperative strategy aimed at improving surgical outcomes while preserving blood resources. In the operating room, where bleeding risk is anticipated and modifiable, PBM requires proactive intervention rather than reactive transfusion. This review synthesizes current evidence on perioperative blood conservation strategies specifically relevant to surgeons and anesthesiologists. Preoperative optimization begins with systematic identification and correction of anemia, most commonly iron deficiency, using appropriately timed oral or intravenous iron therapy and, in selected cases, erythropoiesis-stimulating agents. Careful management of anticoagulant and antiplatelet therapies, early recognition of acquired or inherited coagulopathies, and protocol-driven reversal strategies further reduce perioperative hemorrhagic risk. Intraoperatively, blood conservation depends on meticulous surgical technique, respect for anatomical planes, minimally invasive approaches, and the judicious use of advanced energy devices and topical hemostatic agents. Pharmacologic interventions—particularly tranexamic acid administered with appropriate timing and dosing—have demonstrated consistent reductions in blood loss and transfusion requirements across multiple surgical disciplines. Goal-directed coagulation management guided by viscoelastic testing allows targeted correction of specific hemostatic deficits while minimizing unnecessary blood product exposure. Acute normovolemic hemodilution and intraoperative cell salvage provide additional benefit in selected high-blood-loss procedures. Collectively, these multimodal strategies shift perioperative care from product-driven transfusion toward physiology-based blood conservation. When embedded within institutional protocols and supported by multidisciplinary collaboration, perioperative PBM reduces transfusion exposure, decreases morbidity, shortens hospital stay, and promotes sustainable stewardship of blood resources without compromising patient safety. Full article

The low-carbon transition of industrial parks is driving an increasing demand for advanced energy systems. Integrated energy supply systems (IESSs), which couple multiple energy forms, offer a critical pathway to alleviate the high-carbon intensity of energy structures and supply–demand imbalances in industrial parks by enhancing energy efficiency and reducing carbon emissions. The rapid advancement of energy storage technologies, multi-energy system modeling, and advanced energy management strategies has further propelled the research and application of IESSs. This review comprehensively delineates the distinctions between IESSs and traditional energy systems, highlighting the architecture and operational characteristics of IESSs to elucidate the impacts of multi-energy coupling and source–grid–load–storage interactions. We examine existing equipment and system modeling approaches and load modeling methods, and discuss modeling techniques for variable operating conditions. We analyze operational optimization methods for IESSs under deterministic, multi-time-scale, and uncertain conditions, and investigate the utilization mechanisms of flexibility resources across source–grid–load–storage links to illustrate how system flexibility supports dynamic supply–demand coordination. The review also identifies emerging trends in AI-driven IESS operation, highlighting the integration of physics-informed modeling, large language models, and multi-agent systems. This review establishes a unified analytical perspective for flexible supply–demand matching within IESSs, offering theoretical support for the development of future low-carbon industrial energy systems. Full article

To address the challenges posed by multiple uncertainties in modern power systems to the market bidding of Virtual Power Plants (VPPs), this paper proposes an adaptive bidding strategy based on Deep Reinforcement Learning (DRL). First, a heterogeneous VPP aggregation model integrating dedicated energy storage, Vehicle-to-Grid (V2G), and flexible loads is constructed, incorporating complex physical and operational constraints. Second, to overcome the “myopic” local optimality problem of traditional DRL in temporal arbitrage tasks, a potential-based reward shaping mechanism linked to future price trends is designed to guide the agent toward long-term optimal strategies. Finally, multi-dimensional comparative experiments and mechanism analyses are conducted in a simulated day-ahead electricity market. Simulation results demonstrate the following: (1) The proposed algorithm exhibits robust convergence stability and effectively handles stochastic noise in market prices and renewable generation. (2) Economically, the strategy significantly outperforms the rule-based strategy and remains highly competitive with the deterministic-optimization benchmark under perfect-information assumptions. (3) Mechanism analysis further reveals that the DRL agent breaks through the rigid logic of fixed thresholds, learning a non-linear dynamic game mechanism based on “Price-SOC” states, thereby achieving full-depth utilization of energy storage resources. This work provides an interpretable data-driven paradigm for intelligent VPP decision-making in uncertain environments. Full article

With the rapid development of applications such as smart cities and the industrial internet, the computation-intensive tasks generated by massive sensing devices pose significant challenges to traditional cloud computing paradigms. Unmanned aerial vehicle (UAV)-assisted edge computing systems, leveraging their high mobility and wide-area coverage capabilities, offer an innovative architecture for low-latency and highly reliable edge services. However, the practical deployment of such systems faces a highly complex multi-objective optimization problem featured by the tight coupling of task offloading decisions, UAV trajectory planning, and edge server resource allocation. Conventional optimization methods are difficult to adapt to the dynamic and high-dimensional characteristics of this problem, leading to suboptimal system performance. To address this critical challenge, this paper constructs an intelligent collaborative optimization framework for UAV-assisted edge computing systems and formulates the system quality of service (QoS) optimization problem as a mixed-integer non-convex programming problem with the dual objectives of minimizing task processing latency and reducing overall system energy consumption. A multi-agent joint task association and trajectory optimization (MA-JTATO) algorithm based on hybrid reinforcement learning is proposed to solve this intractable problem, which innovatively decouples the original coupled optimization problem into three interrelated subproblems and realizes their collaborative and efficient solution. Specifically, the Advantage Actor-Critic (A2C) algorithm is adopted to realize dynamic and optimal task association between UAVs and edge servers for discrete decision-making requirements; the multi-agent deep deterministic policy gradient (MADDPG) method is employed to achieve cooperative and energy-efficient trajectory planning for multiple UAVs to meet the needs of continuous control in dynamic environments; and convex optimization theory is applied to obtain a closed-form optimal solution for the efficient allocation of computational resources on edge servers. Simulation results demonstrate that the proposed MA-JTATO algorithm significantly outperforms traditional baseline algorithms in enhancing overall QoS, effectively validating the framework’s superior performance and robustness in dynamic and complex scenarios. Full article

Multi-agent systems (MASs), with unmanned aerial vehicles (UAVs) as a representative embodiment, have become increasingly vital in time-sensitive disaster response scenarios, where multiple agents must collaborate to execute “observe-and-intervene” emergency tasks and jointly cope with dynamic environmental uncertainties. Existing research on task allocation mostly eliminates uncertainty through deterministic models; the few studies that directly consider uncertainty focus primarily on time uncertainty, overlooking the critical importance of demand uncertainty. To this end, this study accounts for the impact of harsh environmental conditions and incident complexity factors on intervention resource demands. We establish an uncertainty set for these demands and construct a two-stage robust optimization model to solve the coupled multi-agent task allocation problem. Compared with deterministic models, this framework enhances risk resistance while simultaneously reducing the conservatism of decisions. Furthermore, to overcome the computational challenges of large-scale instances, a Learning-Enhanced Column and Constraint Generation (LE-C&CG) algorithm is proposed. Experimental results demonstrate that LE-C&CG converges over an order of magnitude faster than standard Benders and C&CG algorithms, consistently achieving a 0% optimality gap within fractions of a second, making it highly suitable for time-critical emergency applications. Full article

Federated learning (FL) enables collaborative model training across distributed devices and robotic systems while preserving data privacy, making it well-suited for swarm robotics and edge-device-powered intelligence. However, FL remains vulnerable to adversarial behaviors such as data and model poisoning, particularly in real-world deployments where detection methods must operate under strict computational and communication constraints. This paper presents a practical, real-world federated learning framework that enhances robustness to adversarial agents in a ROS2-based edge-device swarm environment. The proposed system integrates the Federated Averaging (FedAvg) algorithm with a lightweight average cosine similarity-based filtering method to detect and suppress harmful model updates during aggregation. Unlike prior work that primarily evaluates poisoning defenses in simulated environments, this framework is implemented and evaluated on physical hardware, consisting of a laptop-based aggregator and multiple Raspberry Pi worker nodes. A convolutional neural network (CNN) based on the MobileNetV3-Small architecture is trained on the MNIST dataset, with one worker executing a sign-flipping model poisoning attack. Experimental results show that FedAvg alone fails to maintain meaningful model accuracy under adversarial conditions, resulting in near-random classification performance with a final global model accuracy of 11% and a loss of 2.3. In contrast, the integration of cosine similarity filtering demonstrates effective detection of sign-flipping model poisoning in the evaluated ROS2 swarm experiment, allowing the global model to maintain model accuracy of around 90% and loss around 0.37, which is close to baseline accuracy of 93% of the FedAvg algorithm only under no attack with a very minimal increase in loss, despite the presence of an attacker. The proposed method also maintains a false positive rate (FPR) of around 0.01 and a false negative rate (FNR) of around 0.10 of the global model in the presence of an attacker, which is a minimal difference from the baseline FedAvg-only results of around 0.008 for FPR and 0.07 for FNR. Additionally, the proposed method of FedAvg + cosine similarity filtering maintains computational statistics similar to baseline FedAvg with no attacker. Baseline results show an average runtime of about 34 min, while our proposed method shows an average runtime of about 35 min. Also, the average size of the global model being shared among workers remains consistent at around 7.15 megabytes, showing little to no increase in message payload sizes between baseline results and our proposed method. These results demonstrate that computationally lightweight cosine similarity-based detection methods can be effectively deployed in real-world, resource-constrained robotic swarm environments, providing a practical path toward improving robustness in real-world federated learning deployments beyond simulation-based evaluation. Full article