Search

An electric vehicle charging station (EVCS) infrastructure is the backbone of transportation electrification; however, the EVCS has various vulnerabilities in software, hardware, supply chain, and incumbent legacy technologies such as network, communication, and control. These standalone or networked EVCSs open up large attack surfaces for local or state-funded adversaries. The state-of-the-art approaches are not agile and intelligent enough to defend against and mitigate advanced persistent threats (APT). We propose data-driven model-free digital clones based on multiple independent agents deep reinforcement learning (IADRL) that uses the Twin Delayed Deep Deterministic Policy Gradient (TD3) to efficiently learn the control policy to mitigate the cyberattacks on the controllers of EVCS. Also, the proposed digital clones trained with TD3 are compared against the benchmark Deep Deterministic Policy Gradient (DDPG) agent. The attack model considers the APT designed to malfunction the duty cycles of the EVCS controllers with Type-I low-frequency attacks and Type-II constant attacks. The proposed model restores the EVCS operation under threat incidence in any/all controllers by correcting the control signals generated by the legacy controllers. Our experiments verify the superior control policies and actions of TD3-based clones compared to the DDPG-based clones. Also, the TD3-based controller clones solve the problem of incremental bias, suboptimal policy, and hyperparameter sensitivity of the benchmark DDPG-based digital clones, enforcing the efficient mitigation of the impact of cyberattacks on EVCS controllers.

This work proposes two non-linear and one linear equation-based system for residential load forecasting considering heating degree days, cooling degree days, occupancy, and day type, which are applicable to any residential building with small sets of smart meter data. The coefficients of the proposed nonlinear and linear equations are tuned by particle swarm optimization (PSO) and the multiple linear regression method, respectively. For the purpose of comparison, a subtractive clustering based adaptive neuro fuzzy inference system (ANFIS), random forests, gradient boosting trees, and long-term short memory neural network, conventional and modified support vector regression methods were considered. Simulations have been performed in MATLAB environment, and all the methods were tested with randomly chosen 30 days data of a residential building in Memphis City for energy consumption prediction. The absolute average error, root mean square error, and mean average percentage errors are tabulated and considered as performance indices. The efficacy of the proposed systems for residential load forecasting over the other systems have been validated by both simulation results and performance indices, which indicate that the proposed equation-based systems have the lowest absolute average errors, root mean square errors, and mean average percentage errors compared to the other methods. In addition, the proposed systems can be easily practically implemented.

Virtual power plants (VPPs) are susceptible to cyber anomalies due to their extensive communication layer. FL-trust, an improved federated learning (FL) approach, has been recently introduced as a mitigation system for cyber-attacks. However, current FL-trust enhancements, relying solely on proportional-integral (PI), exhibit drawbacks like sensitivity to controller gain fluctuations and a slow response to sudden disturbances, and conventional FL-trust is not directly applicable to the non-independent and identically distributed (non-IID) datasets common in VPPs. To address these limitations, we introduce an artificial neural network (ANN)-based technique to adapt FL-trust to non-IID datasets. The ANN is designed as an intelligent anomaly mitigation control method, employing a dynamic recurrent neural network with exogenous inputs. We consider the effects of the most common VPP attacks, poisoning attacks, on the distributed cooperative controller at the secondary control level. The ANN is trained offline and tested online in the simulated VPP. Using MATLAB simulations on a HOMER-modeled VPP, the proposed technique demonstrates its superior ability to sustain normal VPP operation amidst cyber anomalies, outperforming a PI-based mitigation system in accuracy and detection speed.

The major problem associated with the grid-connected solar photovoltaic (PV) system is the integration of the generated DC power into the AC grid and maintaining the stability of the system. With advancements in research on these PV inverters, artificial intelligence (AI)-based control models are replacing the existing linear methods. These smart PV systems are prone to a variety of attacks, ranging from physical attacks on the PV plants to data integrity attacks and communication-based attacks. This paper provides an overview of the cybersecurity issues with smart PV inverters, their impacts on the grids, and control methods that exist to detect and identify cyber-attacks on a smart PV grid system. An extensive bibliography is provided on grid-forming and grid-following inverters with a variety of control techniques like Proportional–Integral–Derivative (PID) control, fuzzy-based control, and their performances under different fault situations. Multi-level inverter design approaches with various intelligent control techniques to overcome switching failures and other system faults are reviewed. Moreover, some recommendations for future research on intelligent inverters for grid-connected PV systems are proposed. This work will benefit researchers, scientists, and engineers who are working in the field of intelligent inverters for the grid-connected PV system.

As grid-connected wind farms become more common in the modern power system, the question of how to maximize wind power generation while limiting downtime has been a common issue for researchers around the world. Due to the complexity of wind turbine systems and the difficulty to predict varying wind speeds, artificial intelligence (AI) and machine learning (ML) algorithms have become key components when developing controllers and control schemes. Although, in recent years, several review papers on these topics have been published, there are no comprehensive review papers that pertain to both AI and ML in wind turbine control systems available in the literature, especially with respect to the most recently published control techniques. To overcome the drawbacks of the existing literature, an in-depth overview of ML and AI in wind turbine systems is presented in this paper. This paper analyzes the following reviews: (i) why optimizing wind farm power generation is important; (ii) the challenges associated with designing an efficient control scheme for wind farms; (iii) a breakdown of the different types of AI and ML algorithms used in wind farm controllers and control schemes; (iv) AI and ML for wind speed prediction; (v) AI and ML for wind power prediction; (vi) AI and ML for mechanical component monitoring and fault detection; and (vii) AI and ML for electrical fault prevention and detection. This paper will offer researchers and engineers in the wind energy generation field a comprehensive review of the application of AI and ML in the control methodology of offshore and onshore wind farms so that more efficient and robust control schemes can be designed for future wind turbine controllers.

Since the discovery of Photovoltaic (PV) effect, numerous ways of utilizing the energy that can be generated by the free everlasting solar radiation using solar panels were put forward by many researchers. However, the major disadvantage of solar panel to date is its low efficiency, which is affected by the panel temperature, cell type, panel orientation, irradiance level, etc. Though there are certain multi-junction solar panels that offer higher efficiencies, their application is very minimal due to high manufacturing cost. With the growing demand for the reduction of carbon footprint, there is a need to use and manufacture these panels in the most effective way to harness the maximum power and increase their efficiency. Another major concern is the availability of land/space for the installation of these panels. Several authors have focused on discussing the different technologies that have evolved in the manufacturing of the PV cells along with their architectures. However, there exists a gap that needs to be addressed by combining the latest PV technologies and architectures with a focus on PV applications for increasing the efficiency. Due to the technical limitations on the efficiency of PV panels, applications are to be designed that can extract the maximum power from the PV systems by minimizing the technical difficulties. Considering all these factors, this paper presents an overview of the types of silicon based solar cell architectures with efficiencies of at least 25%, and different integration methods like Building integrated PVs (BIPV), floating PVs, which can increase the efficiency by harnessing more power from a limited space. An extensive bibliography on the PV cell structures and methods of maintaining the efficiencies in real world installations are presented. The challenges with the integration of solar panels and the future work are also discussed. This work benefits the readers and researchers and serves as a basis to understand the solar panel efficiency structure and ways to improve the efficiency and associated challenges to come over in the successful implementation of these systems.

Wind turbines that are consistently exposed to the air displaced by moving trains have a high potential for energy generation. Researchers have developed mathematical models to simulate wind energy generation from turbines on moving trains but there are significant gaps in the developed model theory. Most models do not consider the negative effects that additional aerodynamic drag, increased weight, and modified dimensions can have on the train’s operation. To overcome the drawbacks of existing models, this work proposes a novel approach of modeling the wind turbines on trains by considering wind turbine exposure only when the train is decelerating or stationary. There are no models that consider all of these realistic physical effects as a function of time. Real-time analysis and power-system simulations showed that the proposed model could produce over 3 MJ of net energy for favorable train trips. The simulated load profile met the demand of a 1 KW generator connected to onboard electrical components. Some recommendations on possible future research on wind turbines on trains are explained.

Energy storage devices are collocated with conventional solar photovoltaic (PV) systems to tackle the intermittency of solar irradiance and maintain the power quality of supplied energy. The energy storage system usually has its own conversion devices that may incur an extra capital cost of installation. This paper proposes an integrated and cost-effective photovoltaic-supercapacitor (PVSC) system in which the energy storage functionality of the supercapacitor (SC) is merged into the PV array where the power flow bidirectionally takes place to maintain the system stability under grid disturbances during the daytime, nighttime, and cloudy weather. A nonlinear mathematical model (NMM) was developed to conduct the stability analyses and to design the controller parameters, which facilitates a faster and more accurate numerical analysis compared to existing average models. The effectiveness of the proposed system was evaluated by simulation analysis and compared to that of the basic PV and a conventional SC system in which full energy storage is connected in parallel with the PV. The results demonstrate that the proposed PVSC system is effective in improving the dynamic performance of the connected power grid system. In addition, the proposed PVSC system fulfills the functionality of the conventional SC with merged conversion devices; that is, the performance of the proposed PVSC system is comparable to the conventional SC system.