Reliability modeling in the context of the Internet of Things (IoT) has received considerable attention from researchers to ensure the safety and stable operation of the relevant systems. However, current methods of reliability modeling are incapable of adequately characterizing the autonomy and cooperativity of the Dynamic Spatiotemporal IoT (DSIoT). To solve this problem, this study proposes an agent-based method of reliability modeling. The authors discuss the autonomy and cooperativity of the DSIoT in case of failure and summarize 11 typical failure states of its functional components. We then develop a multiagent-based framework for the reliability modeling of the DSIoT. Methods of failure modeling are analyzed to describe the propagation of failure within a node and among multiple nodes. Two kinds of criteria of failure are proposed for IoT systems with dynamic spatiotemporal characteristics, and a Monte Carlo simulation-based approach is given to evaluate the reliability of the DSIoT. We also illustrate the uses and effectiveness of the proposed method by using a case study involving a swarm of 16 intelligent unmanned aerial vehicles.

Multiple unmanned aerial vehicle (multi-UAV) system is a type of dynamic spatiotemporal Internet of Things and susceptible to destruction from the external environment. Meanwhile, resilience theory has been introduced to describe the ability of unmanned aerial vehicles (UAVs) faced with disturbances. However, the existing methods do not fully reflect the dynamic spatiotemporal characteristics of multi-UAV systems. Therefore, we proposed a novel resilience metric that integrates mission coverage area and communication status to describe the dynamic spatiotemporal characteristics of multi-UAV systems. On the basis, a combination of importance measures for vulnerability, recoverability, and resilience is presented to support the analysis and identification of weaknesses for the system in whole process. Furthermore, a structure design method is given to improve system resilience by considering both importance measures and trajectory optimization methods simultaneously. Finally, a typical formation topology with six UAVs is simulated as a case study to verify the proposed approach.

Timetabling and scheduling of electric buses (EBs) are crucial for a sustainable city transportation system. Most studies mainly focus on the scheduling and timetabling for one EB line based on the assumption that energy consumption of a battery is linear with distance. In this study, timetabling and scheduling for multiple EB lines are investigated by considering nonlinear energy consumption due to the dynamic load of buses. The optimization objectives are to minimize the number of vehicles and total operation costs, in which the constraints include the limitations of operation range and nonlinear energy consumption of the battery and the capacity of buses can be simultaneously charged at charging stations. Further, an improved particle swarm optimization algorithm is developed to obtain the optimal solution set. Compared with the existing schedule, the proposed schedule can not only reduce the number of vehicles and total charging costs but also distribute the charging periods during off-peak hours to reduce the impact on the urban electricity grid.

The scarcity of time-series data constrains the accuracy of online reliability assessment. Data expansion is the most intuitive way to address this problem. However, conventional small-sample reliability evaluation methods either depend on prior knowledge or are inadequate for time series. This article proposes a novel autoaugmentation network, the worm Wasserstein generative adversarial network, which generates synthetic time-series data that carry realistic intrinsic patterns with the original data and expands a small sample without prior knowledge or hypotheses for reliability evaluation. After verifying the augmentation ability and demonstrating the quality of the generated data by manual datasets, the proposed method is demonstrated with an experimental case: the online reliability assessment of lithium battery cells. Compared with conventional methods, the proposed method accomplished a breakthrough in the online reliability assessment for an extremely small sample of time-series data and provided credible results.

Effective recovery after disruptions is essential to improve system resilience. For many distributed systems such as offshore wind farms and communication networks, spatial location characteristics and limited maintenance resources lead to discontinuous changes in performance during system recovery. However, the stepwise performance is frequently ignored. The coupling relationship between the system and maintenance teams makes it difficult to improve the system resilience from the recovery perspective. In this article, a new method that combines the resilience importance measure and enhanced pigeon-inspired optimization (PIO) is presented to optimize the system resilience under stepwise recovery conditions. First, this study proposes a resilience-oriented importance measure that evaluates the recovery priority for each component. Second, an optimization model is established to minimize the system resilience loss by joint optimization of recovery sequence and task assignment under the conditions of multiple maintenance teams. Third, the resilience importance measure is combined with roulette wheel selection to form a high-quality intitle swarm of PIO. Fourth, an importance measure-based PIO with a Gaussian mutation and adaptive crossover operator is designed to find an optimization solution for system resilience. Finally, the recovery of a network system consisting of 32 nodes and 71 edges is studied. Compared with the stochastic method and traditional PIO, the proposed method in this study reduces the system resilience loss by 48.87 and 15.54%, respectively.

Fault prognosis based on single model is generally inaccurate due to the varying working conditions. A multistage fault prognosis methodology combining stage identification with Bayesian networks (BNs) and time series approach with particular emphasis on the autoregressive moving average (ARMA) model is proposed to solve this problem. In the first stage, degradation data are identified, and outliers are marked by the Euclidean distance. Degenerate attributes of outliers are finely identified by BNs and matched to the corresponding model. In the second stage, the ARMA model is used for prognosis according to the results of the fine identification. Subsequently, the double-precision identification and ARMA submodel prognosis are carried out alternately throughout the prognosis process. Three degradation types of permanent magnet synchronous motor are simulated to verify the applicability of the method. Result shows that it can track the changes in the degradation in time and obtains better results.

Preventive maintenance (PM) activities in battery energy storage systems (BESSs) aim to achieve a better status in long-term operation. In this article, we develop a reinforcement learning-based PM method for the optimal PM management of BESSs equipped with prognostics and health management capabilities. A multilevel PM framework is established to generate a PM action strategy considering costs, capacity, and reliability simultaneously. Finite costs are the constraints, and reliability is the objective according to capacity degradation, respectively. The proposed PM agent with an integrated Monte Carlo tree search and a deep neural network (DNN) utilizes the state-of-health information of large-scale batteries in the BESS and selects optimal maintenance actions. The DNN is used as the state-action value function to extend the ability to address PM problems with large state-action spaces. The case of a BESS with 9 × 12 × 4 batteries in a fleet is simulated via Python. The results show that the PM agent can achieve efficient and steady decision-making proficiency in BESS PM management.