Day-Ahead Forecasting of Hourly Photovoltaic Power Based on Robust Multilayer Perception

Evidential Extreme Learning Machine Algorithm-Based Day-Ahead Photovoltaic Power Forecasting

The gradually increased penetration of photovoltaic (PV) power into electric power systems brings an urgent requirement for accurate and stable PV power forecasting methods. The existing forecasting methods are built to explore the function between weather data and power generation, which ignore the uncertainty of historical PV power. To manage the uncertainty in the forecasting process, a novel ensemble method, named the evidential extreme learning machine (EELM) algorithm, for deterministic and probabilistic PV power forecasting based on the extreme learning machine (ELM) and evidential regression, is proposed in this paper. The proposed EELM algorithm builds ELM models for each neighbor in the k-nearest neighbors initially, and subsequently integrates multiple models through an evidential discounting and combination process. The results can be accessed through forecasting outcomes from corresponding models of nearest neighbors and the mass function determined by the distance between the predicted point and neighbors. The proposed EELM algorithm is verified with the real data series of a rooftop PV plant in Macau. The deterministic forecasting results demonstrate that the proposed EELM algorithm exhibits 15.45% lower nRMSE than ELM. In addition, the forecasting prediction intervals obtain better performance in PICP and CWC than normal distribution.

Weather Data Mixing Models for Day-Ahead PV Forecasting in Small-Scale PV Plants

As a large number of small-scale PV plants have been deployed in distribution systems, generation forecasting of such plants has recently been gaining interest. Because the PV power mainly depends on weather conditions, it is important to accurately collect weather data for relevant PV sites to enhance PV forecasting accuracy. However, small-scale PV plants do not often have their own measuring apparatus to get historical weather data, so they have used weather datasets from relatively nearby weather data centers (WDCs). Therefore, these small-scale PV plants have difficulty delivering robust and reliable forecasting accuracy because of inappropriate predicted weather data from a distance. In this paper, two weather data mixing models are proposed: (a) inverse distance weighting (IDW), and (b) inverse correlation weighting (ICW). These models acquire adequate mixed weather data for the day-ahead generation forecasting for small-scale PV plants. Furthermore, the mixed weather data are collected using the geographic distance between the PV site and WDCs, or correlation between the PV generation and weather variables from nearby WDCs. Interestingly, the proposed ICW model outperforms when WDCs are located distant from the PV plants, whereas IDW performs well with the closer WDCs. The forecasting performance of the proposed mixing models was compared with those of the existing weather data collection methods.

Day-Ahead Forecasting for Small-Scale Photovoltaic Power Based on Similar Day Detection with Selective Weather Variables

As photovoltaic (PV) power plants are an essential component of modern smart grids, the PV generation forecasting of such plants has recently been gaining interest. The forecasting results of PV power often suffer from large errors because of unusual weather conditions. In a learning-based forecasting model, the forecasting accuracy can be enhanced by using carefully selected data for training rather than all the data without any screening. That is, using a training set that only contains information obtained from similar days can help enhance the accuracy of learning-based PV forecasting. This paper proposes a forecasting method for small-scale PV generation. This method is based on long short-term memory; further, it detects similar days considering the different impacts of weather variables on PV power according to the day. This method can address issues caused by unnecessary learning from non-similar historical days. The simulation results demonstrate that the proposed method exhibits better performance than do existing similar day detection methods.

Islanding Fault Detection in Microgrids—A Survey

This paper provides an overview of islanding fault detection in microgrids. Islanding fault is a condition in which the microgrid gets disconnected from the microgrid unintentionally due to any fault in the utility grid. This paper surveys the extensive literature concerning the development of islanding fault detection techniques which can be classified into remote and local techniques, where the local techniques can be further classified as passive, active, and hybrid. Various detection methods in each class are studied, and advantages and disadvantages of each method are discussed. A comprehensive list of references is used to conduct this survey, and opportunities and directions for future research are highlighted.

Solar irradiance measurement instrumentation and power solar generation forecasting based on Artificial Neural Networks (ANN): A review of five years research trend

The increased demand for solar renewable energy sources has created recent interest in the economic and technical issues related to the integration of Photovoltaic (PV) into the grid. Solar photovoltaic power generation forecasting is a crucial aspect of ensuring optimum grid control and power solar plant design. Accurate forecasting provides significant information to grid operators and power system designers in generating an optimal solar photovoltaic plant and to manage the power of demand and supply. This paper presents an extensive review on the implementation of Artificial Neural Networks (ANN) on solar power generation forecasting. The instrument used to measure the solar irradiance is analysed and discussed, specifically on studies that were published from February 1st, 2014 to February 1st, 2019. The selected papers were obtained from five major databases, namely, Direct Science, IEEE Xplore, Google Scholar, MDPI, and Scopus. The results of the review demonstrate the increased application of ANN on solar power generation forecasting. The hybrid system of ANN produces accurate results compared to individual models. The review also revealed that improvement forecasting accuracy can be achieved through proper handling and calibration of the solar irradiance instrument. This finding indicates that improvements in solar forecasting accuracy can be increased by reducing instrument errors that measure the weather parameter.

Robust 24 Hours ahead Forecast in a Microgrid: A Real Case Study

Forecasting the power production from renewable energy sources (RESs) has become fundamental in microgrid applications to optimize scheduling and dispatching of the available assets. In this article, a methodology to provide the 24 h ahead Photovoltaic (PV) power forecast based on a Physical Hybrid Artificial Neural Network (PHANN) for microgrids is presented. The goal of this paper is to provide a robust methodology to forecast 24 h in advance the PV power production in a microgrid, addressing the specific criticalities of this environment. The proposed approach has to validate measured data properly, through an effective algorithm and further refine the power forecast when newer data are available. The procedure is fully implemented in a facility of the Multi-Good Microgrid Laboratory (MG L a b 2 ) of the Politecnico di Milano, Milan, Italy, where new Energy Management Systems (EMSs) are studied. Reported results validate the proposed approach as a robust and accurate procedure for microgrid applications.

Forecasting Solar Power Using Hybrid Firefly and Particle Swarm Optimization (HFPSO) for Optimizing the Parameters in a Wavelet Transform-Adaptive Neuro Fuzzy Inference System (WT-ANFIS)

Solar power generation deals with uncertainty and intermittency issues that lead to some difficulties in controlling the whole grid system due to imbalanced power production and power demand. The forecasting of solar power is an effort in securing the integration of renewable energy into the grid. This work proposes a forecasting model called WT-ANFIS-HFPSO which combines the wavelet transform (WT), adaptive neuro-fuzzy inference system (ANFIS) and hybrid firefly and particle swarm optimization algorithm (HFPSO). In the proposed work, the WT model is used to eliminate the noise in the meteorological data and solar power data whereby the ANFIS is functioning as the forecasting model of the hourly solar power data. The HFPSO is the hybridization of the firefly (FF) and particle swarm optimization (PSO) algorithm, which is employed in optimizing the premise parameters of the ANFIS to increase the accuracy of the model. The results obtained from WT-ANFIS-HFPSO are then compared with several other forecasting strategies. From the comparative analysis, the WT-ANFIS-HFPSO showed superior performance in terms of statistical error analysis, confirming its reliability as an excellent forecaster of hourly solar power data.