Incorporating solar energy into a grid necessitates an accurate power production forecast for photovoltaic (PV) facilities. In this research, output PV power was predicted at an hour ahead on yearly basis for three different PV plants based on polycrystalline (p-si), monocrystalline (m-si), and thin-film (a-si) technologies over a four-year period. Wind speed, module temperature, ambiance, and solar irradiation were among the input characteristics taken into account. Each PV plant power output was the output parameter. A deep learning method (RNN-LSTM) was developed and evaluated against existing techniques to forecast the PV output power of the selected PV plant. The proposed technique was compared with regression (GPR, GPR (PCA)), hybrid ANFIS (grid partitioning, subtractive clustering and FCM) and machine learning (ANN, SVR, SVR (PCA)) methods. Furthermore, different LSTM structures were also investigated, with recurrent neural networks (RNN) based on 2019 data to determine the best structure. The following parameters of prediction accuracy measure were considered: RMSE, MSE, MAE, correlation (r) and determination (R²) coefficients. In comparison to all other approaches, RNN-LSTM had higher prediction accuracy on the basis of minimum (RMSE and MSE) and maximum (r and R²). The p-si, m-si and a-si PV plants showed the lowest RMSE values of 26.85 W/m², 19.78 W/m² and 39.2 W/m² respectively. Moreover, the proposed method was found to be robust and flexible in forecasting the output power of the three considered different photovoltaic plants.

The incessantly growing demand for electricity in today’s world claims an efficient and reliable system of energy supply. Distributed energy resources such as diesel generators, wind energy and solar energy can be combined within a microgrid to provide energy to the consumers in a sustainable manner. In order to ensure more reliable and economical energy supply, battery storage system is integrated within the microgrid. In this article, operating cost of isolated microgrid is reduced by economic scheduling considering the optimal size of the battery. However, deep discharge shortens the lifetime of battery operation. Therefore, the real time battery operation cost is modeled considering the depth of discharge at each time interval. Moreover, the proposed economic scheduling with battery sizing is optimized using firefly algorithm (FA). The efficacy of FA is compared with other metaheuristic techniques in terms of performance measurement indices, which are cost of electricity and loss of power supply probability. The results show that the proposed technique reduces the cost of microgrid and attain optimal size of the battery.

Technology advancement in the last few decades allows large penetration of renewable energy resources in the distribution network (DN). The integration of such resources has shown a substantial impact on DN through power loss reduction and improved network reliability. Besides this, the existing protection system has encountered coordination challenges due to the bidirectional power flow, different types and capacity of generation sources, and changes in fault levels due to network operating modes (grid-connected or islanded). Such conditions may cause the relays to malfunction and imperil the effectiveness of the existing protection scheme. Therefore, an efficient and robust protection coordination scheme is imperative to avoid network reliability and stability issues to the grid. This review paper presents a comparative analysis of various protection techniques implemented to alleviate the impact of integrated resources into DN. Moreover, a comparison of classical and modified protection approaches in terms of advantages, shortcomings, and implementation costs is presented. The prime objective of this study is to highlight the prominence of utilizing user-defined programmable relays for modern DNs. Moreover, recommendations are presented by considering the application of user-defined relay characteristics that can be proved as a robust protection scheme to cope with the protection challenges in existing and future power systems developments.