Application of computing and communications intelligence effectively improves the quality of monitoring and control of smart grids. However, the dependence on information technology also increases vulnerability to malicious attacks. False data injection (FDI), that attack on the integrity of data, is emerging as a severe threat to the supervisory control and data acquisition system. In this paper, we exploit deep learning techniques to recognize the behavior features of FDI attacks with the historical measurement data and employ the captured features to detect the FDI attacks in real-time. By doing so, our proposed detection mechanism effectively relaxes the assumptions on the potential attack scenarios and achieves high accuracy. Furthermore, we propose an optimization model to characterize the behavior of one type of FDI attack that compromises the limited number of state measurements of the power system for electricity theft. We illustrate the performance of the proposed strategy through the simulation by using IEEE 118-bus test system. We also evaluate the scalability of our proposed detection mechanism by using IEEE 300-bus test system.

It is well known that information will play an important role in enhancing emerging smart grid system operation. Therefore, questions naturally arise as to when the increased data-dependence may be considered excessive. Two practical considerations emerge: 1) communications and computational overhead, in which redundant and irrelevant information acquisition and use results in heavy computational burden with limited performance return; and 2) increasing risks of power system disruption due to information delay from communication congestion or cyber attack. One strategy to improve smart grid resilience is to determine the appropriate degree of dependence on cyber information to balance performance with overhead and risk. In this paper, we present a hierarchical cyber-physical multiagent model of smart grid system operation based on flocking theory in the context of the transient stability problem. Through this model, we study strategies that harness a selective degree of cyber technology by leveraging physical couplings. Our formulation enables the identification of large-scale distributed control strategies for robust and resilient power grid operation. We demonstrate the potential performance improvements of our findings on the New England 39-bus power system for case studies involving a variety of system faults and communication delays.

Generator coherency identification is establishing itself as an important task to aid in the resistance of cascading failures within wide-area power systems and as a necessary preprocessing stage in real-time control for transient stability. Inspired by flocking behavior in nature, we propose a novel multiflock-based technique to identify generator coherence rapidly within a short observation window. Our measurement-based approach transforms generator data from the observation space to an information space, whereby the generator frequencies and phases characterize the movement and dynamics of boids within multiple flocks. Analysis of the boids' trajectories enables the discrimination of multiple flocks corresponding to coherent generator clusters. We demonstrate the effectiveness of our technique to identify generator coherency rapidly while exhibiting robustness to environmental noise and cyber attack on the 39-bus New England test system and a modified IEEE 118-Bus test system.

Thanks to the advances in machine learning, data-driven analysis tools have become valuable solutions for various applications. However, there still remain essential challenges to develop effective data-driven methods because of the need to acquire a large amount of data and to have sufficient computing power to handle the data. In many instances these challenges are addressed by relying on a cloud computing vendor. However, although commercial cloud vendors provide valuable platforms for data analytics, they can suffer from a lack of transparency, security, and privacy-preservation. Furthermore, reliance on cloud servers prevents applying big data analytics in environments where the computing power is distributed. To address these challenges, a decentralized, secure, and privacy-preserving computing paradigm is proposed to enable an asynchronized cooperative computing process amongst distributed and untrustworthy computing nodes that may have limited computing power and computing intelligence. This paradigm is designed by exploring blockchain, decentralized learning, and homomorphic encryption techniques. The performance of the proposed paradigm is evaluated via different scenarios in the simulation section.

Wired and wireless communications both play an important role in the blend of communications technologies necessary to enable future smart grid communications. Hybrid networks exploit independent mediums to extend network coverage and improve performance. However, whereas individual technologies have been applied in simulation networks, as far as we know there is only limited attention that has been paid to the development of a suite of hybrid communication simulation models for the communications system design. Hybrid simulation models are needed to capture the mixed communication technologies and IP address mechanisms in one simulation. To close this gap, we have developed a suite of hybrid communication system simulation models to validate the critical system design criteria for a distributed solar Photovoltaic (PV) communications system, including a single trip latency of 300 ms, throughput of 9.6 Kbps, and packet loss rate of 1%. The results show that three low-power wireless personal area network (LoWPAN)-based hybrid architectures can satisfy three performance metrics that are critical for distributed energy resource communications.

This paper proposes an attack-resilient intelligent soft computing based security control for energy management architecture for a hybrid emergency power system of More-Electric Aircrafts (MEAs). Our proposed architecture develops an Adaptive Neuro-Fuzzy Inference System (ANFIS) -based method in conjunction with a specific Recurrent Neural Network architecture called Long Short-Term Memory (LSTM) to evaluate the integrity of the power output of the critical components which have higher vulnerability to the potential cyber-attacks and critical for the effective energy management and emergency control. We evaluate the integrity of the critical measurements that have high vulnerability to the potential cyber-attacks by using LSTM techniques. After identifying the compromised measurements, we continue to activate the closed-loop ANFIS mechanism in which the structure of ANFIS is controlled according to the accuracy of its current estimations by probing the physical couplings in the system. In our simulation, we evaluate the performance of our proposed LSTM-ANFIS -based method to support the integrity of the Energy Management Strategies (EMSs) used in hybrid emergency power system for more-electric aircrafts by using TensorFlow and MATLAB/Simulink co-simulation environment. Our simulation results illustrate the effectiveness of our proposed method in effectively evaluating the integrity of critical data and achieving resilient control.