Increased penetration of grid-connected PV systems in modern electricity networks induces uncertainty factors to be considered from several different viewpoints, including the system’s protection and management. Accurate short-term prediction of a grid-connected PV park’s output is essential for optimal grid control and grid resilience. Out of the numerous types of models employed to this end during the last decade, artificial neural networks, (ANNs) have proven capable of handling the uncertainty issues of solar radiation. Insolation and ambient, or panel temperature, are most commonly employed as the independent variables, and the system’s output power is successfully predicted within 3 to 5% error. In this paper, we apply a common type of ANN for the long-term prediction of a 100 kWp grid-connected PV park’s output, by exploiting experimental data from the last 8 years of operation. Solar radiation and backsheet temperature were utilized for the ANN training stage. The performance metrics of this model, along with a standard linear regression model, are compared against the actual performance data. The capabilities of the ANN model are exploited in the effort to decouple the fluctuating effect of PV panel soiling which interferes with the efficiency degradation process. The proposed methodology aimed to quantify degradation effects and is additionally employed as a fault diagnosis tool in long-term analysis.

https://www.mdpi.com/2076-3417/12/13/6458/pdf?version=1656402766

Prediction of a Grid-Connected Photovoltaic Park’s Output with Artificial Neural Networks Trained by Actual Performance Data

The reliability of energy supply is an important factor for end-users of electricity. Although many advances and efforts have been made by distribution companies to guarantee energy quality, weak feeders and grids are still usually found. As an alternative to minimize such problems, Battery Energy Storage Systems (BESSs) can be used to supply energy to users in the case of power outages or major energy quality problems. This paper presents test results on a real application scenario in a microgrid with different load configurations in the moment of interruption. The tests were compared to each other to analyze the impact found in each scenario. In addition to those, real unpremeditated cases of power quality problems were also discussed, and the performance of the utilized BESS was evaluated.

/pdf/case-study-of-backup-application-with-energy-storage-in-3ntb0869.pdf

Case Study of Backup Application with Energy Storage in Microgrids

Substation (SS) auxiliary systems (SAux) are facilities responsible for hosting the alternating (AC) and direct current (DC) busbar to serve the equipment and systems that perform the substation’s protection, control, and supervision. External and internal power supplies typically ensure the continuity of such a facility. The electricity support will be restricted to diesel emergency generators (DG) if the external power supply is unavailable due to a contingency. The DG present a slower response time and are susceptible to starting failures. Microgrids with Battery Energy Storage Systems (BESS) paired with photovoltaic systems (PV) are presented as an innovative and reliable solution for powering the SAux. In this article, tests were carried out on the microgrid of the Edson Mororó Moura Institute of Technology (ITEMM) in Brazil to support the use of microgrids BESS/PV in the SAux of a transmission SS of the São Francisco Hydroelectric Company (Chesf). Without an external power supply, BESS commands the action of islanded operation, maintaining both voltage and frequency requirements of the microgrid without load shedding. It was possible to observe all operations of the microgrid. The experimental results showed that the solution proposed in the paper implements a dependable self-dispatchable autonomous power supply.

/pdf/characterization-of-the-operation-of-a-bess-with-a-2dzs4r0r.pdf

Characterization of the Operation of a BESS with a Photovoltaic System as a Regular Source for the Auxiliary Systems of a High-Voltage Substation in Brazil

This article addresses the development of the energy compensation method used for the design of hybrid energy storage systems—HBESS. The combination of two battery technologies offers better cost and performance when considering microgrid systems to provide uninterrupted power to sensitive loads (substation auxiliary system) and also provides greater energy security. In the event of a failure, the load needs to continue operating, and batteries such as lithium ions have a fast response, but are expensive for large-scale systems. However, some technologies offer low-cost and good availability of energy for long hours of discharge, such as lead–acid batteries. Consequently, different battery technologies can be used to meet all the needs of the sensitive loads. A specific method for sizing a HBESS was developed for islanded microgrids to support sensitive loads. This method was developed to meet the demand for substations outside the Brazilian standard of power systems that lack an uninterrupted and reliable energy source. The method is validated by designing a microgrid to support the auxiliary systems of a transmission substation in northeastern Brazil. The results showed a system with a capacity of 1215 kWh of lead-carbon and 242 kWh of lithium ions is necessary to maintain an islanded microgrid for at least 10 h. Furthermore, the microgrid comprises a PV plant with an AC output power of 700 kW in connected operation and 100 kW when islanded from the grid.

/pdf/development-of-a-method-for-sizing-a-hybrid-battery-energy-2cs1rbcb.pdf

Development of a Method for Sizing a Hybrid Battery Energy Storage System for Application in AC Microgrid

The insertion of renewable sources to diversify the energy matrix is one of the alternatives for the energy transition. In this sense, Brazil is one of the largest producers of renewable energy in the world, mainly in wind generation. However, the impact of integrating intermittent sources into the system depends on their penetration level, causing problems in the electrical network. To evaluate this scenario, the present article aims to investigate the power quality problems generated by wind turbines in connection with the electrical system and how battery energy storage systems (BESS) solve or mitigate these disturbances in the network. Knowing the impacts of high generation power variability, the focus of the work is the application of power smoothing. However, results are presented for five applications (factor correction, voltage control, power factor smoothing, frequency control and time shift) that can be carried out at the studied wind farm. This article presents a real BESS, which has a capacity of 1 MW/1.29 MWh, connected in parallel to a group of wind turbines that provides a power of approximately 50.4 MW located in Brazil. In addition to presenting the system simulation in HOMER Pro software, this study validates the effectiveness of this BESS by presenting real operation data for each application.

/pdf/operational-data-analysis-of-a-battery-energy-storage-system-3ewazt5i.pdf

Operational Data Analysis of a Battery Energy Storage System to Support Wind Energy Generation

Solar irradiance forecasting has been an essential topic in renewable energy generation. Forecasting is an important task because it can improve the planning and operation of photovoltaic systems, resulting in economic advantages. Traditionally, single models are employed in this task. However, issues regarding the selection of an inappropriate model, misspecification, or the presence of random fluctuations in the solar irradiance series can result in this approach underperforming. This paper proposes a heterogeneous ensemble dynamic selection model, named HetDS, to forecast solar irradiance. For each unseen test pattern, HetDS chooses the most suitable forecasting model based on a pool of seven well-known literature methods: ARIMA, support vector regression (SVR), multilayer perceptron neural network (MLP), extreme learning machine (ELM), deep belief network (DBN), random forest (RF), and gradient boosting (GB). The experimental evaluation was performed with four data sets of hourly solar irradiance measurements in Brazil. The proposed model attained an overall accuracy that is superior to the single models in terms of five well-known error metrics.

/pdf/solar-irradiance-forecasting-using-dynamic-ensemble-2yc5p7iq.pdf

Solar Irradiance Forecasting Using Dynamic Ensemble Selection

Harmony can be defined in a musical way as art that combines several musical notes reproduced simultaneously to create sounds that are coherent to human ears and serve as accompaniment and filling. However, working out harmony is not a simple task. It requires knowledge, experience, and an intense study of music theory, which takes time to reach good skills. Thus, systems capable of automatically harmonizing melodies are beneficial for experienced and novice musicians. In this paper, a comparative study between distinct architectures and ensembles of Artificial Neural Networks was proposed to solve the problem of musical harmonization, seeking consistent results with rules of music theory: Multilayer Perceptron (MLP), Radial Basis Function network (RBF), Echo State Network (ESN), Extreme Learning Machines (ELM), and Long Short-Term Memory (LSTM). For this, a processed and defined melody with symbolic musical data serves as input to the system, having been trained from a musical database that contains melody and harmony. The output is the chord sequence to be applied to the melody. The results were analyzed with quantitative measures and the ability to melody adaptation. The performances were favorable to the MLP, which could generate harmonies according to the objectives. 

Tathiana M. Barchi

Papers

Solar Irradiance Forecasting Using Dynamic Ensemble Selection

Neural Networks And Ensemble Based Architectures To Automatic Musical Harmonization: A Performance Comparison