The installation of phasor measurement units brings about system-wide synchronized real-time measurements, which makes advanced closed-loop control of wide-area power systems (WAPSs) possible. In addition to uncertainties with the physical system, network imperfections are also critical for control performance and even stability of the system. This paper targets at wide-area damping control of WAPS under both physical and cyber uncertainties. The cyber uncertainties addressed in this paper include both communication delay and package dropout. First, a linearized WAPS model is developed with considerations of random control signal arrivals. Then, a Q-learning-based control algorithm is designed to learn the optimal control under both physical and cyber uncertainties. Finally, to further counteract the communication uncertainties between the control center and actuators, a novel control law is designed based on the statistical analysis to make the long-term control performance approach that under ideal communications. The designed control algorithm is tested with both simplified linear model and detailed nonlinear model of WAPSs. Simulation results demonstrate the effectiveness of the designed algorithm.

In this paper, the real-time non-intrusive load monitoring (NILM) problem with limited measurements, i.e., low sampling rate data, is investigated. NILM is a technique to identify the various types of appliances by analyzing the voltage and current features collected by sensors such as smart outlets. It is one of the most important topics in smart grid management and optimization. Although recent NILM methods developed several general models that can be used for various scenarios, these algorithms either require high-frequency measurement devices or have been limited to use for some specific appliances. A real-time intelligent NILM algorithm that is able to be transferred among different appliances with low-frequency data is still lacking and desperately needed. In this paper, a novel online learning-based intelligent NILM algorithm has been developed that can online infer a variety of appliances using a transferred model with limited measurements. Specifically, the developed algorithm integrates the emerging transfer learning technique along with deep neural networks. Two neural networks are used in two different stages, i.e., 1) The long short-term memory (LSTM) neural network to extract the lower level spatial and temporal features from the grayscale image generated by the measurements, 2) The probabilistic neural network (PNN) to classify the appliance type as well as transfer between appliances. Finally, the algorithm is implemented into practical smart outlet hardware to demonstrate its effectiveness.

Conventional control solutions of the inverter-interfaced microgrids are usually designed based on models with fully decoupled subsystems. The negligence of the strong coupling due to power lines impedance leads to large transient line currents, which might trigger false protection. Besides, the droop-based control methods unnecessarily introduce system frequency and voltage deviations. To overcome these issues, a novel distributed control scheme is proposed for the inverter-interfaced microgrids in this paper. The objective of the primary control is to regulate the bus voltages and frequency while suppressing the transient line currents. The objective of secondary control is to maintain fair load sharing. Both primary control and secondary control are distributed and subsystems or control agents only require measurements from local and neighboring subsystems. The detailed control problem formulation, control design and stability analysis are presented in the paper. The effectiveness of the proposed control solution is evaluated through extensive simulations based on both simplified and detailed models.

Stabilizing the Unmanned Aircraft Systems (UAS) under complex environment including system uncertainties, unknown noise and/or disturbance is so challenging. Therefore, this paper proposes an adaptive neural network based intelligent control method to overcome these challenges. Based on a class of artificial neural network, named Radial Basis Function (RBF) networks an adaptive neural network controller is designed. To handle the unknown dynamics and uncertainties in the system, firstly, we develop a neural network based identifier. Then, a neural network based controller is generated based on both the identified model of the system and the linear or nonlinear controller. To ensure the stability of the system during its online training phase, the linear or nonlinear controller is utilized. The learning capability of the proposed intelligent controller makes it a promising approach to take system uncertainties, noises and/or disturbances into account. The satisfactory performance of the proposed intelligent controller is validated based on the computer based simulation results of a benchmark UAS with system uncertainties and disturbances, such as wind gusts disturbance.

In this paper, a novel discrete-time self-triggered (DTST) distributed controller is developed for DC microgrids with data dropouts and communication delays. To meet the discrete-time (DT) nature of digital systems, a DT distributed controller is first proposed to achieve load current sharing and average voltage regulation simultaneously in DC microgrids. To further relax the communication restrictions, a novel self-triggered mechanism is developed and integrated along with the DT controller, where the local controller proactively estimates the next communication instant ahead of time. Since the controller can only be triggered at DT instants, the Zeno phenomenon is avoided. Moreover, an algorithm is further proposed to compensate for the effect of data dropouts and communication delays. Through Lyapunov synthesis, stability and convergence of the closed-loop system with the proposed design is guaranteed. Finally, detailed simulation studies validate the effectiveness of the proposed DTST controller under communication imperfections.

Underwater acoustic (UWA) communications have been widely used but greatly impaired due to the complicated nature of the underwater environment. In order to improve UWA communications, modeling and understanding the UWA channel is indispensable. However, there exist many challenges due to the high uncertainties of the underwater environment and the lack of real-world measurement data. In this work, the capability of reservoir computing and deep learning has been explored for modeling the UWA communication channel accurately using real underwater data collected from a water tank with disturbance and from Lake Tahoe. We leverage the capability of reservoir computing for modeling dynamical systems and provided a data-driven approach to modeling the UWA channel using Echo State Network (ESN). In addition, the potential application of transfer learning to reservoir computing has been examined. Experimental results show that ESN is able to model chaotic UWA channels with better performance compared to popular deep learning models in terms of mean absolute percentage error (MAPE), specifically, ESN has outperformed deep neural network by 2% and as much as 40% in benign and chaotic UWA respectively.