Over the past decade, the high penetration of renewable-based distributed generation (DG) units has witnessed a considerable rise in electrical networks. In this context, direct current (DC) microgrids based on DGs are being preferred due to having less complexity for the establishment and control. At the same time, they offer higher efficiency and reliability compared to their alternating current (AC) counterparts. This paper proposes a new model predictive control (MPC)-trained artificial neural network (ANN) control strategy being an ANN-MPC instead of conventional cascaded-proportional-integral (PI)-trained ANN control for dynamic damping of photovoltaic (PV)-battery-based grid-connected DC microgrids. Unlike traditional controllers, the proposed control approach more rapidly attains generation-load power balancing under variable climate input (meteorological sensor data) and output (load demand), hence achieving quick DC-bus voltage damping. The proposed ANN-MPC scheme is examined under different operating conditions, and the results are compared with the ANN-based conventional PI controller. The results show the proposed control strategy's efficacy to lessen the instability issues and achieve effective attenuation of oscillations in DC microgrids.

Turkey is among the countries largely dependent on energy import. This dependency has increased interest in new and alternative energy sources. Installation of rooftop solar photovoltaic systems (RSPSs) in Turkey is increasing continuously regarding geographical and meteorological conditions. This paper presents an insight into the potential situation for Turkey and a simulation study for the RSPS designing and calculation for the faculty building at Marmara University in Istanbul. This simulation study demonstrates that 84.75-kWp grid-connected RSPS can produce remarkable power. The system is performed in detail with the PV*SOL software (Premium 2017 R8-Test Version, Valentin Software GmbH, Berlin, Germany). Detailed financial and performance analysis of the grid-connected RSPS for faculty building with various parameters is also carried out in this study. According to the simulation results, the system supplies 13.2% of the faculty buildings’ annual electrical energy consumption. The annual savings value of faculty buildings’ electrical consumption is approximately 90,298 kWh energy which costs roughly $7296. A photovoltaic (PV) system installation for the faculty building, which has considerable potential for solar energy and sunshine duration, is indispensable for clean energy requirements and was supported by the simulation results. This paper can be considered to be a basic feasibility study prior to moving on to the implementation project.

Nowadays, DC microgrids are preferred in the field of renewable energy. The autonomous DC microgrids aim to provide smooth power flow from renewables to loads. While satisfying certain load profiles and sustaining the power as the desired level, the control of power converters is considerable. To ascend the resilience of DC microgrids, battery storage systems (BSSs) are also used as a backup unit for supplying uninterrupted power. The main task of BSSs is to compensate for the lack of power when the load is higher than supplied power or store the surplus of power in case that the load demand is less than the extracted power. In other words, by draining and storing the power, BSSs help to increase the flexibility of the system and keep the main DC bus voltage within acceptable bounds. This study introduces artificial intelligence (AI)-based method to diminish the number of implemented sensors and control power converters without reducing efficiency. In this paper, artificial neural networks (ANNs) as a subset of AI are exploited. Diminishing the number of sensors in the control layer makes the system more reliable. To validate the effectiveness of the proposed system, offline and online time-domain simulations are performed in MATLAB/Simulink.

In this work, a sensorless voltage estimation approach for total harmonic distortion (THD) calculation is proposed to reduce number of voltage sensors in the microgrids. The intelligent proposed method provides a cost-effective and reliable voltage estimation and THD calculation of the desired bus in the multi-bus microgrid based on the artificial neural networks (ANNs). In the proposed method, the output voltage and current of distributed generation units along with the voltage of the desired bus are used to train the ANN offline. The trained ANN is then used to estimate the voltage and calculate both harmonic components, and THD online at the desired bus. The Simulation results show that the proposed approach can effectively estimate the voltage and calculate THD of buses in the multi-bus islanded microgrids.

To enable more wide-scale exploitation of renewable energy sources (RESs), distributed generations (DGs) as in microgrids have gained prominence recently. This study describes the design, modeling, implementation, and operation of a microgrid, in which a standalone hybrid power system has been installed for an education and research laboratory. The unstable nature of RESs results in power compatibility issues on DGs. Therefore, providing a decent power flow from renewables to loads is the scope of this paper. To satisfy defined load profiles and sustain the power with the desired level, the design and operation of power converters are a remarkable part of performing microgrids as well. For a robust microgrid structure, the presented control algorithm includes an energy management system (EMS) between renewables, batteries, and loads. Primarily, modeling of the system has been developed in MATLAB/Simulink environment. Additionally, case studies have been exemplified to further demonstrate the simulated system. Within this scope, certain load profiles not only have been fed but also power flow has been managed and analyzed to ensure effective and flexible operation with two different EMS cases. The real-time operation has been also provided to validate the system under various input and output conditions during a lab course.

In a microgrid, photovoltaic (PV) systems are broadly preferred with energy storage systems (ESSs) that form small-sized direct current (DC) microgrids. They are also termed local grids i.e., DC nanogrids, which feed the local consumers to some extent in the next decades. Therefore, ESSs enable the DC nanogrids more flexible and stable by preserving the intermittent nature of renewables. Yet still, feeding local consumers smoothly with PV-battery-based systems is exceedingly a considerable theme. In this context, proper control of power electronics converters as the main carrier of the system is essential. Besides, the rise of PV applications challenges possible issues upon integrating the conventional grid. Emerging possible issues and the ways of dealing with them have been developing day by day. Thus, it is inevitable that innovative methods will be put into practice. To achieve this goal, the deep learning aided-sensorless control approach is adopted. To validate the proposed control method, the training phase is presented elaborately with the help of the experimental setup of a DC nanogrid. From the obtained results, it is concluded that the deep learning-based approach reaches very small error values, captures the system dynamics with a high accuracy rate successfully, and allows the possibility to apply practically.