Power system faults are significant problems in power transmission and distribution. Methods based on relay protection actions and electrical component actions have been put forward in recent years. However, they have deficiencies dealing with power system fault. In this paper, a method for data-based line trip fault prediction in power systems using long short-term memory (LSTM) networks and support vector machine (SVM) is proposed. The temporal features of multisourced data are captured with LSTM networks, which perform well in extracting the features of time series for a long time span. The strong learning and mining ability of LSTM networks is suitable for a large quantity of time series in power transmission and distribution. SVM, with a strong generalization ability and robustness, is introduced for classification to get the final prediction results. Considering the overfitting problem in fault prediction, layer of dropout and batch normalization are added into the network. The complete network architecture is shown in the paper in detail. The parameters are adjusted to fit the specific situation of the actual power system. The data for experiments is obtained from the Wanjiang substation in the China Southern Power Grid. The real experiments prove the proposed method’s improvements compared with current data mining methods. Concrete analyses of results are elaborated in the paper. A discussion of practical applications is presented to demonstrate the feasibility in real scenarios.

The recent spades of cyber attacks have compromised end users' data security and privacy in Medical Cyber-Physical Systems (MCPS) in the era of Health 4.0. Traditional standard encryption algorithms for data protection are designed based on a viewpoint of system architecture rather than a viewpoint of end users. As such encryption algorithms are transferring the protection on the data to the protection on the keys, data safety and privacy will be compromised once the key is exposed. In this paper, we propose a secure data storage and sharing method consisted by a selective encryption algorithm combined with fragmentation and dispersion to protect the data safety and privacy even when both transmission media (e.g. cloud servers) and keys are compromised. This method is based on a user-centric design that protects the data on a trusted device such as end user's smartphone and lets the end user to control the access for data sharing. We also evaluate the performance of the algorithm on a smartphone platform to prove the efficiency.

Short-term load forecasting is an important task for the planning and reliable operation of power grids. High-accuracy forecasting for individual customers helps to make arrangements for generation and reduce electricity costs. Artificial intelligent methods have been applied to short-term load forecasting in past research, but most did not consider electricity use characteristics, efficiency, and more influential factors. In this paper, a method for short-term load forecasting with multi-source data using gated recurrent unit neural networks is proposed. The load data of customers are preprocessed by clustering to reduce the interference of electricity use characteristics. The environmental factors including date, weather and temperature are quantified to extend the input of the whole network so that multi-source information is considered. Gated recurrent unit neural networks are used for extracting temporal features with simpler architecture and less convergence time in the hidden layers. The detailed results of the real-world experiments are shown by the forecasting curve and mean absolute percentage error to prove the availability and superiority of the proposed method compared to the current forecasting methods.

The distributed control of DC microgrid is becoming increasingly important in modern power systems. One important control objective is to ensure DC bus voltage stability and proper current sharing with a reduced communication burden. This paper presents a new event-triggered distributed secondary control strategy for single-bus DC microgrid. Through this strategy, both current sharing and bus voltage regulation can be guaranteed. Moreover, through the event-triggering mechanism, each converter can decide locally when to transmit signals to its neighbours. In this way, the communication burden among converters is significantly reduced. Compared to existing results, the proposed strategy also enables various types of loads, including both linear and nonlinear loads, to be connected to the DC microgrid. Simulation and experiment results illustrate the effectiveness of the proposed strategy.

This article investigates the cooperative estimation problem to recover the parametric flow field through sensor measurements from an autonomous underwater vehicle (AUV) team. We establish the parametric flow model that incorporates the concept of incompressibility to provide a physical property. Then, considering the influence of unknown flow field on AUVs’ trajectories while submerged, we define: 1) the deviation between actual and predicted relative positions between each vehicle and its neighbors as an relative motion-integration error , which is available using local measurement and 2) the deviation between the actual and predicted position of each vehicle as an absolute motion-integration error , which is available from global positioning system (GPS) when the AUVs are on the sea surface. Based on relative and absolute motion-integration errors, we formulate a set of nonlinear equations to present the deterministic and continuous relationship between the above errors and the parametric flow model. To reconstruct the flow field, an iterative algorithm is proposed to estimate the model parameters by solving an inverse problem for these nonlinear equations. Moreover, a detailed convergence analysis of the proposed algorithm is given. Finally, simulations are conducted to illustrate the effectiveness of the proposed algorithm in a simulated and real dataset of the flow field.

The paper studies the asynchronous observer-based sliding mode control (SMC) for Markov jump systems (MJSs) with actuator failures. Considering the phenomena of unmeasurable states and the case that the controller/observer to be devised have different modes from the original systems, a hidden Markov model (HMM) is used to construct an asynchronous observer and the corresponding sliding surface is designed. Then, the asynchronous SMC strategy is developed to guarantee the reachability of the predetermined sliding surface in a limited time. A sufficient condition is established for the mean-square stability of the overall closed-loop systems and the desired controller is designed. Moreover, when the conditional probabilities describing the mode asynchronism are only partially known for the HMM in the systems, the related results are also given. Finally, simulation results show the usefulness of the developed techniques.