Nowadays, the advancement of non-intrusive load monitoring (NILM) is hastened by the everincreasing requirements for smart power utilization and demand side management. Thus, an intelligent event-driven non-intrusive load monitoring method based on convolutional neural network (CNN) is proposed in this paper to profile residential consumer behavior, which focused on limited applicability and low recognition accuracy of existing NILM techniques. The deep convolutional neural architecture improves the performance of load monitoring procedure, and extends its application range to monitoring process in terms of various and combined characteristics. Meanwhile, the event-driven procedure is conducted to find the start-stop time and state change of the appliance accurately, including zero-cross detection, current similarity detection, threshold evaluation, and event current acquisition. Subsequently, the current-to-image conversion is carried out to represent the characteristics of residential appliance as the input of CNN. And the convolutional neural architecture is proposed to identify the power consumption load and its working condition. Selected experimental results are performed that the average recognition accuracy is over 93%, which demonstrates the effectiveness and superiority of the proposed methodology for home energy management.

This paper is concerned with the networked synchronization control problem of coupled dynamic networks (CDNs) with time-varying delay. First, both the data packet dropouts and network-induced delays are taken into account in the synchronization controller design. A Markovian jump process is induced to describe the packet dropouts. The network-induced delays are interval time varying and depend on the Markovian jump modes. A new closed-loop coupled dynamic error system (CDES) with Markovian jump parameters and interval time-varying delays is constructed. Second, using the Kronecker product technique and the stochastic Lyapunov method, a delay-dependent sufficient criterion of stochastic stability is obtained for the closed-loop CDES, which also guarantees that the CDNs are stochastically synchronized. Finally, a simulation example is given to demonstrate the effectiveness of the proposed result.

This article proposed a novel event-triggered integral sliding-mode control (ISMC) strategy for nonlinear system with disturbances via robust adaptive dynamic programming (ADP) considering control constrains. A mixed event-triggered ISMC scheme with two different trigger parts is developed and the optimal performance of sliding-mode dynamics with input constrains is ensured. By guaranteeing that the system trajectory converges to the sliding-mode surface with removing the input disturbances, a discontinuous part triggering rule is presented together with the existence analysis of a lower trigger interval time bound. Then, the optimal event-triggered control of sliding-mode dynamics is converted into a discounted factor-based H _∞ constrained control problem under continuous part triggering condition. To solve the event-triggered HJI equation, a critic-only neural network (NN)-based ADP scheme is developed by applying a concurrent learning. The NN weight is updated by analyzing the uniformly ultimately bounded (UUB) stability of sliding-mode dynamics considering the event-triggered condition via the Lyapunov technique. Finally, the validity of our control strategy is verified by simulation.

The optimal tracking problem for continuous-time boiler turbine systems (BTSs) with asymmetric input constraints is considered in this paper. Considering that continuous updating of control input will reduce the service life of engineering oriented system, a novel dynamic event-based triggering mechanism is proposed to reduce the number of controller updates, where a positive internal dynamic variable is introduced to expand the threshold. The objective is to find the optimal event-triggered control strategy for a given performance index function so that the system can track the ideal signal while minimizing the cost function. Firstly, by introducing tracking error variable, the optimal tracking problem is transformed into the optimal stability problem with symmetric input constraints. Then, three neural networks are designed to approximate the system model, cost function and control strategy respectively, and the feasibility of the proposed optimization algorithm is strictly proved by Lyapunov method, and the system will not exhibit Zeno behavior. Finally, simulation results effectively indicate the feasibility of the developed method in the industrial oriented system. Note to Practitioners —With the development of the national economy, China’s demand for electricity is also increasing. The BTSs in thermal power generation unit should not only realize load tracking, but also consider minimizing fuel consumption, minimizing pollutant emissions, maximizing the service life of BTSs. In this paper, adaptive dynamic programming (ADP) method and dynamic event-based mechanism are used to solve the optimal tracking problem of BTSs. The dynamic event-based mechanism not only affects the real performance of the BTSs, but also reduces the number of controller updates and saves resources of the BTSs.