Search

The working environment of complex systems is complex and variable, and their performance is often affected by various shock events during the service phase. In this paper, first, considering that the system performance will be affected by shocks again in the process of maintenance, the reliability changes and fault process of complex systems are discussed. Second, the performance change processes of complex systems are analyzed under multiple shocks and maintenance. Then, based on performance loss and recovery, this paper analyzes the reliability and resilience of complex systems under the intersecting process of multiple shocks and maintenance. Considering the direct and indirect losses caused by shocks, as well as maintenance costs, the changes in total costs are analyzed. Finally, the practicability of the proposed model is checked by using a specific welding robot system.

Federated Learning (FL) is a promising distributed machine learning framework that emphasizes privacy protection. However, inconsistencies between local optimization objectives and the global objective, commonly referred to as client drift, primarily arise due to non-independently and identically distributed (Non-IID) data, multiple local training steps, and partial client participation in training. The majority of current research tackling this challenge is mainly based on the empirical risk minimization (ERM) principle, while giving little consideration to the connection between the global loss landscape and generalization capability. This study proposes FedGAM, an innovative FL algorithm that incorporates Gradient Norm-Aware Minimization (GAM) to efficiently search for a local flat landscape. FedGAM specifically modifies the client model training objective to simultaneously minimize the loss value and first-order flatness, thereby seeking flat minima. To directly smooth the global flatness, we propose the more significant FedGAM-CV, which employs control variables to correct local updates, guiding each client to train models in a globally flat direction. Experiments on three datasets (CIFAR-10, MNIST, and FashionMNIST) demonstrate that our proposed algorithms outperform existing FL baselines, effectively finding flat minima and addressing the client drift problem.

In Mobile Crowdsensing (MCS), sensing tasks have different impacts and contributions to the whole system or specific targets, so the importance of the tasks is different. Since resources for performing tasks are usually limited, prioritizing the allocation of resources to more important tasks can ensure that key data or information can be collected promptly and accurately, thus improving overall efficiency and performance. Therefore, it is very important to consider the importance of tasks in the task selection and allocation of MCS. In this paper, a task queue is established, the importance of tasks, the ability of participants to perform tasks, and the stability of the task queue are considered, and a novel task selection and allocation scheme (TSAS) in the MCS system is designed. This scheme introduces the Lyapunov optimization method, which can be used to dynamically keep the task queue stable, balance the execution ability of participants and the system load, and perform more important tasks in different system states, even when the participants are limited. In addition, the Double Deep Q-Network (DDQN) method is introduced to improve on the traditional solution of the Lyapunov optimization problem, so this scheme has a certain predictive ability and foresight on the impact of future system states. This paper also proposes action-masking and iterative training methods for the MCS system, which can accelerate the training process of the neural network in the DDQN and improve the training effect. Experiments show that the TSAS based on the Lyapunov optimization method and DDQN performs better than other algorithms, considering the long-term stability of the queue, the number and importance of tasks to be executed, and the congestion degree of tasks.

Lake water surface albedo (LWSA) is a critical parameter for describing energy flux balance at the air–water interface. It is used to measure the capacity of lake water surface reflectance in the shortwave radiation band, which controls the energy partitioning between atmosphere and lake. LWSA and its driving factors, including solar radiation angle, water quality and meteorology, in lakes of Northeast China was analyzed in this research. Solar altitude angle emerged as the most important controlling factor of LWSA. The results showed a strong reduction in LWSA values with increase in solar altitude angle. The study also documented a strong effect of suspended matter on the radiative properties of lakes surface, leading to increased LWSA with increased in suspended matter concentration, especially at high solar altitude angles (R2: 0.76). While no significant association (R2: 0.11) was found between LWSA and chlorophyll-a concentration, LWSA was positively correlated with wind speed (R2 of 0.62 and 0.50 at high and low solar altitude angles, respectively), likely a consequence of wind-driven sediment resuspension in lake waters. Although chromophoric dissolved organic matter (CDOM) and organic particulate matter can affect energy partitioning and spectral distribution of incident solar radiation in lake waters, there was insufficient evidence of measurable effects on LWSA. Variations in LWSA recorded in this study were primarily dependent on similar solar altitude angles and backscattering properties of inorganic particulate matter suspended in the water column. Higher surface albedo was found in the turbid lakes.

Systems are damaged due to various disturbances, and the reliability of the systems is reduced. Measures to improve system resilience need to be studied since many systems still need to operate normally after suffering damage. In this paper, the whole process of the disturbance and recovery of the system is considered, and a resilience optimization model of a multi-component system is proposed. Firstly, a system resilience assessment method is proposed based on system reliability, and the system resilience loss is used as the resilience assessment index. Secondly, two component importance indexes, loss importance and recovery importance, are proposed for the system disturbance phase and recovery phase, respectively. The two importance indexes are weighted to obtain the weighted importance so as to measure the change law of system resilience and determine the influence degrees of components on system reliability. Then, under the constraint of maintenance time, an optimization model is established to determine a redundancy strategy to maximize system resilience. Finally, through an example analysis of a wind turbine system with its main components, it is verified that the redundancy strategy proposed with this method can reduce the loss of system resilience and effectively improve system reliability.

Federated learning (FL) has emerged for solving the problem of data fragmentation and isolation in machine learning based on privacy protection. Each client node uploads the trained model parameter information to the central server based on the local training data, and the central server aggregates the parameter information to achieve the purpose of common training. In the real environment, the distribution of data among nodes is often inconsistent. By analyzing the influence of independent identically distributed data (non-IID) on the accuracy of FL, it is shown that the accuracy of the model obtained by the traditional FL method is low. Therefore, we proposed the diversified sampling strategies to simulate the non-IID data situation and came up with the OPTICS (ordering points to identify the clustering structure)-based clustering optimization federated learning method (OCFL), which solves the problem that the learning accuracy is reduced when the data of different nodes are non-IID in FL. Experiments indicate that OCFL greatly improves the model accuracy and training speed compared with the traditional FL algorithm.

Mobile crowdsensing is a crowdsourcing-based paradigm, where the platform executes the sensing requests with the help of many common peoples' handheld devices (typically smartphones). In this paper, we mainly address the dynamic sensing request admission and smartphone scheduling problem to maximize the long-term profit, taking into account the competitive interaction procedure between the platform and smartphones, the queue backlog, and the location of sensing requests and smartphones. First, formulate this problem as a discrete time model and the interaction procedure between the platform and smartphones as a Stackelberg game. Then, we introduce the Lyapunov optimization technique and design a Stackelberg game based dynamic Admission and Scheduling algorithm(SAS). In SAS, all control decisions are made only based on the currently available information and none of the stakeholders, including the platform and smartphones, can improve his utility by unilaterally changing its current strategy. Next, we design an online Cooperative dynamic Admission and Scheduling algorithm(CAS) for the situation where the platform and smartphones work in a cooperative way. Theoretical analysis shows that under any control parameter V > 0, both SAS and CAS algorithm can achieve O(1/V)-optimal average profit while the sensing request backlog is bounded by O(V). The extensive numerical results based on both synthetic and real trace demonstrate the Stackelberg equilibrium of the SAS. The CAS always outperforms SAS, and in some certain situations, the profit of SAS is very close to that of the CAS.

Federated learning (FL) can tackle the problem of data silos of asymmetric information and privacy leakage; however, it still has shortcomings, such as data heterogeneity, high communication cost and uneven distribution of performance. To overcome these issues and achieve parameter optimization of FL on non-Independent Identically Distributed (non-IID) data, a multi-objective FL parameter optimization method based on hierarchical clustering and the third-generation non-dominated sorted genetic algorithm III (NSGA-III) algorithm is proposed, which aims to simultaneously minimize the global model error rate, global model accuracy distribution variance and communication cost. The introduction of a hierarchical clustering algorithm on non-IID data can accelerate convergence so that FL can employ an evolutionary algorithm with a low FL client participation ratio, reducing the overall communication cost of the NSGA-III algorithm. Meanwhile, the NSGA-III algorithm, with fast greedy initialization and a strategy of discarding low-quality individuals (named NSGA-III-FD), is proposed to improve the convergence efficiency and the quality of Pareto-optimal solutions. Under two non-IID data settings, the CNN experiments on both MNIST and CIFAR-10 datasets show that our approach can obtain better Pareto-optimal solutions than classical evolutionary algorithms, and the selected solutions with an optimized model can achieve better multi-objective equilibrium than the standard federated averaging (FedAvg) algorithm and the Clustering-based FedAvg algorithm.

In this paper, we propose a particle swarm optimization variant based on a novel evaluation of diversity (PSO-ED). By a novel encoding of the sub-space of the search space and the hash table technique, the diversity of the swarm can be evaluated efficiently without any information compression. This paper proposes a notion of exploration degree based on the diversity of the swarm in the exploration, exploitation, and convergence states to characterize the degree of demand for the dispersion of the swarm. Further, a disturbance update mode is proposed to help the particles jump to the promising regions while reducing the cost of function evaluations for poor particles. The effectiveness of PSO-ED is validated on the CEC2015 test suite by comparison with seven popular PSO variants out of 12 benchmark functions; PSO-ED achieves six best results for both 10-D and 30-D.