![ Named Intellectual Methods, selected for problem solving.
Several models are available in the literature based on their structure, operation, and
utilization. Broadly, these models can be classified into three categorizations named
statistical [34], physical [35] and hybrid models [36,37]. These models were designed with
various techniques including intelligent techniques for forecasting are follows:
Artificial Neural Network (ANN):
Regression
support vector machines (SVM)
Markov chain
Numerical Weather Prediction (NWP).
Deep Learning
(Article-2)](https://image.slidesharecdn.com/presentation1-241120194805-7322e9e0/85/PV-power-forecasting-based-on-data-driven-Models-8-320.jpg)
![ The method used by the authors to highlight the advantages of their
solution is given: what data was used for testing, what alternative
algorithms were compared with, how much better the results were than
those obtained by alternative methods.
LSTM: An LSTM network is a popular RNN architecture that solves this problem of
vanishing gradient.
LSTM deal with the vanishing gradient problem by not imposing any bias toward
recent observations, but it keeps constant error flowing back through time [29].
This is possible by the introduction of gates (input, forget, and output) into the
internal structure of LSTM based neurons (also called memory cells). This structure
allows better control of the gradient flow and enables better preservation of long-
term dependencies.
Only LSTM-based models have the ability to support time sequence in the data.
This is one reason that these models and their variations have emerged as
particularly attractive algorithms to design a PV power forecasting model recently.
(Article-3)](https://image.slidesharecdn.com/presentation1-241120194805-7322e9e0/85/PV-power-forecasting-based-on-data-driven-Models-13-320.jpg)
PV power forecasting based on data-driven Models
- 1. Professor- Dr. Artūras Serackis Submitted by -Harshita, Gehlot Intelligent system Task Report
- 2. For the report, you need to choose 4 scientific articles that address issues close to the topic of your Master's research paper. The tasks in the selected articles should be solved using intelligent methods (artificial neural networks, fuzzy logic, genetic algorithms, knowledge systems, etc.). Prepare presentation slides (there is no need to write a separate report, only the presentation slides must be prepared). The slides must contain for each article: - The solved problem and tasks are named. - Named intellectual methods, selected for problem solving. - The method used by the authors to highlight the advantages of their solution is given: what data was used for testing, what alternative algorithms were compared with, how much better the results were than those obtained by alternative methods. - Short conclusions provided by the authors of the article (if the authors of the article wrote a long paragraph of the text of the conclusions, you should try to single out the main statements on your own). Task:
- 3. The solved problem and Tasks are named. The ML techniques (sub-branch of artificial intelligence) are extensively used due to their ability to solve nonlinear and complex data structures. In case of unavailability of historical PV power for a new PV plant and in case of failure of real-time data acquisition, indirect PV power forecasting can be a viable alternative. Although the performance ranking of various ML models is complicated and no model is universal, So, the recent studies suggest that methodologies like deep neural networks and ensemble or hybrid models outperform conventional methods for short-term PV forecasting. R PV Power Forecasting Based on Data-driven Models: A Review (Article-1)
- 4. Named Intellectual Methods, selected for problem solving. Machine learning utilizes historical data points to establish a relation between the input and output, even if the relationship between them is complex. So it is recommended to use proper data or prepare them to solve the problem effectively. Some of them are described as follows: Artificial Neural Network (ANN): Supervised Learning: Wavelet Transform (WT) Self-Organising Map (SOM) Support Vector Machine (SVM) K-means Cluster Deep Learning (Article-1)
- 5. The method used by the authors to highlight the advantages of their solution is given: what data was used for testing, what alternative algorithms were compared with, how much better the results were than those obtained by alternative methods. DEEP LEARNING: Deep learning is a sub-class of machine learning and can be supervised or unsupervised. Due to the ability of artificial neural networks to deal with the non-linearity of the problem, researchers are focusing on the further development of ANN methods. Deep learning is a more advanced form of neural network with a memory unit and can apply in many fields, including forecasting. Some models based on supervised deep learning like recurrent neural networks (Guan, Zhang, and Yan 2019), deep belief networks, convolutional neural networks have started to produce excellent results in the field of solar energy forecasting. Compared to other forecasting methods like NWP physical model, persistence and other statistical methods, DL-based models can effectively extract deep features and information from the time series forecasting. (Article-1)
- 6. Short Conclusion Analysis of the development of literature on PV power forecasting based on some factors like chronological growth of literature, methods deployed, the evolution of techniques, forecast horizon and input parameters has also been presented. Some key points from the literature are as follows:- As shown in the paper, many data-driven techniques are available for forecasting. Some are beginning to be used more frequently (bagging, boosting, decision trees, etc.), some are often used (ANN, SVM, ARIMA, MLR), and some have not been used so frequently (deep learning). Ensemble learning-based forecasting models outperform the single-stage forecasting models (ANN, SVM, k-NN, etc.) in most of the cases. Deep Learning is becoming a more powerful tool in time series forecasting problems due to its ability to discover the complex non-linearity of the time series data. The ability of deep learning models to overcome the limitations of traditional time series models (ARMA, ARIMA) makes them the best option for time series forecasting. LINK: https://doi.org/10.1080/19397038.2021.1986590 (Article-1)
- 7. The solved problem and Tasks are named. The literature studied showed that ANN-based models outperform the others due to their nonlinear complex problem solving capabilities. Their accuracy can be further improved by hybridization of the two models or by performing pre-processing on the input data. Therefore, a highly precise and reliable solar irradiance prediction is required in order to perform smooth operations of the power system. However, accurate forecasting of solar irradiance is one of the challenging. Solar forecasting techniques 215 tasks to perform where many desperate models have already been designed in the literature. A Comprehensive Review and Analysis of Solar Forecasting Techniques (Article-2)
- 8. Named Intellectual Methods, selected for problem solving. Several models are available in the literature based on their structure, operation, and utilization. Broadly, these models can be classified into three categorizations named statistical [34], physical [35] and hybrid models [36,37]. These models were designed with various techniques including intelligent techniques for forecasting are follows: Artificial Neural Network (ANN): Regression support vector machines (SVM) Markov chain Numerical Weather Prediction (NWP). Deep Learning (Article-2)
- 9. The method used by the authors to highlight the advantages of their solution is given: what data was used for testing, what alternative algorithms were compared with, how much better the results were than those obtained by alternative methods. HYBRID MODEL WITH DEEP LEARNING: Various types of models have been developed such as statistical, physical, and hybrid models. Hybrid models perform better than standalone ones. However, hybrid models have more complex structures than standalone ones and provide better accuracies as a single structure fails to reach the desired accuracy. The hybrid structure of deep learning models of RNN, CNN, LSTM, and ELM with optimization techniques like PSO, GA, and firefly perform better than isolated models where PSO attains good remarks for accuracy. (Article-2)
- 10. Short Conclusion Solar irradiance is highly dependent on various geographical and climatic parameters. The dynamic behavior of solar irradiance directly influences the reliability of PV integrated systems, energy market, and power utility agencies. The comparison of the performance of different models is very complicated due to different region/place of interest, variation in input-output data availability, variation in climatic conditions, time-horizon, and use of diverse error matrices. Therefore, the hybridization of the models with various combination techniques and correct consideration of pre-processing techniques along with the proper selection of input parameters for a specific location enriches the precision and reliability of solar forecasting. LINK: https://doi.org/10.1007/s11708-021-0722-7 (Article-2)
- 11. The solved problem and Tasks are named. Motivated by factors such as the reduction in cost and the need for a shift towards achieving UN’s Sustainable Development Goals, PV (Photovoltaic) power generation is getting more attention in the cold regions of the Nordic countries and Canada. The cold climate and the albedo effect of snow in these regions present favorable operating conditions for PV cells and an opportunity to realize the seasonal matching of generation and consumption. However, the erratic nature of PV brings a threat to the operation of the grid. PV power forecasting has been used as an economical solution to minimize and even overcome this limitation. Our main objective in this paper is therefore to quantitatively and qualitatively assess the role that AI/ML technology play in forecasting the amount and variation of output power focusing on PV plants located in cold regions A Review of Machine Learning-Based Photovoltaic Output Power Forecasting: Nordic Context (Article-3)
- 12. Named Intellectual Methods, selected for problem solving. The common AI algorithms that are widely used in the literature for PV power forecasting can be broadly grouped into conventional ML models and DL models. A brief description of these models is given below. CONVENTIONAL ML MODELS: Support Vector Machine (SVM) Ensemble of Trees DEEP LEARNING MODELS Convolutional Neural Network (CNN) Long short-term memory (LSTM) (Article-3)
- 13. The method used by the authors to highlight the advantages of their solution is given: what data was used for testing, what alternative algorithms were compared with, how much better the results were than those obtained by alternative methods. LSTM: An LSTM network is a popular RNN architecture that solves this problem of vanishing gradient. LSTM deal with the vanishing gradient problem by not imposing any bias toward recent observations, but it keeps constant error flowing back through time [29]. This is possible by the introduction of gates (input, forget, and output) into the internal structure of LSTM based neurons (also called memory cells). This structure allows better control of the gradient flow and enables better preservation of long- term dependencies. Only LSTM-based models have the ability to support time sequence in the data. This is one reason that these models and their variations have emerged as particularly attractive algorithms to design a PV power forecasting model recently. (Article-3)
- 14. Short Conclusion This review shows that the choice of a particular type of ML algorithm to apply for PV output power forecasting depends on the weather condition of the area where the plant is located similar to the forecast time step and horizon. For stable weather conditions, the deterministic component (which is explained by the movement of the sun) of the PV output power is more dominant than the stochastic component (which is explained by the movement of cloud). In such cases, conventional ML algorithms such as RF and SVM can result in a sufficiently good-performing prediction model. However, in areas where the stochastic component is equally important as the deterministic component, the conventional ML algorithms are found to be mostly inadequate. In cases like this, DL algorithms such as LSTM and CNN have been implemented to overcome this inherent limitation. It was found in our analysis that such approaches can fully capture highly complex input-output relationships and result in a high-performing prediction model. This research work has also shown that for PV output power forecasting models based on DL algorithms, auto-encoder and attention mechanism techniques can be included to improve performance. LINK: https://doi.org/10.1109/access.2022.3156942 (Article-3)
- 15. The solved problem and Tasks are named. Solar power has rapidly become an increasingly important energy source in many countries over recent years; however, the intermittent nature of photovoltaic (PV) power generation has a significant impact on existing power systems. To reduce this uncertainty and maintain system security, precise solar power forecasting methods are required. This study summarizes and compares various PV power forecasting approaches, including time-series statistical methods, physical methods, ensemble methods, and machine and deep learning methods, the last of which there is a particular focus. A complete and comprehensive solar power forecasting process must include data processing and feature extraction capabilities, a powerful deep learning structure for training, and a method to evaluate the uncertainty in its predictions. Completed Review of Various Solar Power Forecasting Techniques Considering Different Viewpoints (Article-4)
- 16. Named Intellectual Methods, selected for problem solving. An ANN has been developed to derivative methods to make the forecasting methods more suitable in different fields are follows: A Radial Basis Function Neural Network (RBFNN) A Convolutional Neural Network (CNN) A Recurrent Neural Network (RNN) An LSTM An Extreme Learning Machine (ELM) An Online Sequential Extreme Learning Machine (OS-ELM) (Article-4)
- 17. The method used by the authors to highlight the advantages of their solution is given: what data was used for testing, what alternative algorithms were compared with, how much better the results were than those obtained by alternative methods. Online Sequential Extreme Learning Machine (OS-ELM): An OS-ELM is an advanced version of an ELM. An ELM needs to retrain and test new data, but an OS-ELM does not need this action. As new data arrives, an OS-ELM does not need to retrain the model with old data. It can insert data to the network to update the model continuously. However, since the structure of an OS-ELM is a single hidden layer network, it is difficult to effectively deal with complex applications even if a large number of hidden layer nodes are set. An OS-ELM is suitable for short-time learning but its performance for long-time learning is poor (Article-4)
- 18. Short Conclusion PV power generation has an inherent problem of intermittency, which affects power system reliability. Therefore, it is essential to design reliable forecasting models for such systems. In this article, the techniques used for solar power forecasting are summarized in a systematic and comprehensive manner. The key topics identified from the survey were learning techniques, data processing, the classification of forecasting methods, major factors that affect the forecasting performance, and the estimation of forecasting uncertainties. It was observed that supervised learning methods were used more frequently than unsupervised methods and also that most forecasting methods applied a data cleaning and normalization process to reduce forecasting errors Machine learning was the most popular method used for PV forecasting. Of particular interest is the fact that various machine learning models that employ optimal algorithms have received an increasing amount of attention. LINK: https://doi.org/10.3390/ en15093320 (Article-4)
- 19. THANK YOU