Comprehensive Assessment and Comparative Analysis of Deep Learning Models for Large-Scale Renewable Energy Power Generation Prediction: A National Perspective
Author:
Aksoy Necati1, Genc Istemihan2
Affiliation:
1. Bursa Technical University 2. Istanbul Technical University
Abstract
Abstract
In forecasting the future energy consumption and generation at the national level, strategic planning for both the medium and long term becomes imperative. The trajectory of renewable energy contribution to the smart grid, whether in the short or long term, significantly influences the grid's operational dynamics. This study is dedicated to the development of deep learning-based power prediction models tailored for a nation characterized by extensive reliance on renewable energy sources. Specifically, four distinct deep learning methodologies—namely,Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), and Gated Recurrent Unit (GRU)—have been formulated and rigorously examined for their efficacy within this domain. These models have been individually tailored for the prediction of power generation from solar photovoltaic plants and wind turbines, leveraging the inherent advantages of architectures featuring memory cells. The outcomes of these predictive models, which encompass the entire spectrum of renewable energy sources, exhibit remarkable precision. Furthermore, an exhaustive analysis of the performance metrics derived from these models has been conducted, affording a comprehensive and nuanced comparison. The findings contribute valuable insights into the suitability and effectiveness of the aforementioned deep learning methodologies in forecasting power generation from renewable sources at a national scale.
Publisher
Research Square Platform LLC
Reference31 articles.
1. LeCun, Yann and Bengio, Yoshua and Hinton, Geoffrey (2015) Deep learning. Nature 521(7553): 436-444 https://doi.org/10.1038/nature14539, 1476-4687, Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech., 01, May 2. Srinivasan, Sabarathinam and Kumarasamy, Suresh and Andreadakis, Zacharias E. and Lind, Pedro G. (2023) Artificial Intelligence and Mathematical Models of Power Grids Driven by Renewable Energy Sources: A Survey. Energies 16(14) https://doi.org/10.3390/en16145383, To face the impact of climate change in all dimensions of our society in the near future, the European Union (EU) has established an ambitious target. Until 2050, the share of renewable power shall increase up to 75% of all power injected into nowadays ’ power grids. While being clean and having become significantly cheaper, renewable energy sources (RES) still present an important disadvantage compared to conventional sources. They show strong fluctuations, which introduce significant uncertainties when predicting the global power outcome and confound the causes and mechanisms underlying the phenomena in the grid, such as blackouts, extreme events, and amplitude death. To properly understand the nature of these fluctuations and model them is one of the key challenges in future energy research worldwide. This review collects some of the most important and recent approaches to model and assess the behavior of power grids driven by renewable energy sources. The goal of this survey is to draw a map to facilitate the different stakeholders and power grid researchers to navigate through some of the most recent advances in this field. We present some of the main research questions underlying power grid functioning and monitoring, as well as the main modeling approaches. These models can be classified as AI- or mathematically inspired models and include dynamical systems, Bayesian inference, stochastic differential equations, machine learning methods, deep learning, reinforcement learning, and reservoir computing. The content is aimed at the broad audience potentially interested in this topic, including academic researchers, engineers, public policy, and decision-makers. Additionally, we also provide an overview of the main repositories and open sources of power grid data and related data sets, including wind speed measurements and other geophysical data., 1996-1073, 5383 3. Huaizhi Wang and Zhenxing Lei and Xian Zhang and Bin Zhou and Jianchun Peng (2019) A review of deep learning for renewable energy forecasting. Energy Conversion and Management 198: 111799 https://doi.org/https://doi.org/10.1016/j.enconman.2019.111799, As renewable energy becomes increasingly popular in the global electric energy grid, improving the accuracy of renewable energy forecasting is critical to power system planning, management, and operations. However, this is a challenging task due to the intermittent and chaotic nature of renewable energy data. To date, various methods have been developed, including physical models, statistical methods, artificial intelligence techniques, and their hybrids to improve the forecasting accuracy of renewable energy. Among them, deep learning, as a promising type of machine learning capable for discovering the inherent nonlinear features and high-level invariant structures in data, has been frequently reported in the literature. This paper provides a comprehensive and extensive review of renewable energy forecasting methods based on deep learning to explore its effectiveness, efficiency and application potential. We divide the existing deterministic and probabilistic forecasting methods based on deep learning into four groups, namely deep belief network, stack auto-encoder, deep recurrent neural network and others. We also dissect the feasible data preprocessing techniques and error post-correction methods to improve the forecasting accuracy. Extensive analysis and discussion of various deep learning based forecasting methods are given. Finally, we explore the current research activities, challenges and potential future research directions in this topic., Deep learning, Renewable energy, Deterministic forecasting, Probabilistic forecasting, Machine learning, 0196-8904 4. Yuan Gao and Shohei Miyata and Yasunori Akashi (2022) Interpretable deep learning models for hourly solar radiation prediction based on graph neural network and attention. Applied Energy 321: 119288 https://doi.org/https://doi.org/10.1016/j.apenergy.2022.119288, With the rapid development of high-performance computing technology, data-driven models, especially deep learning models, are being used increasingly for solar radiation prediction. However, the characteristics of the black box model lead to a lack of interpretability in their prediction results. This limits the application of the model in final optimization scenarios (such as model predictive control), as operation managers might not fully trust models lacking explanatory results. In our study, models were proposed based on the prediction model of the recurrent neural network. We hope to improve the interpretability of the models through the design and improvement of the model structure, thereby increasing the credibility of the model results. The interpretability in time and spatial dependencies of the prediction process were studied by the attention mechanism and graph neural network, respectively. Our results showed that the deep learning model, with attention, could effectively shift the attention mechanism to adapt to varying prediction target hours. The graph neural network expresses the most relevant variables in the dataset related to solar radiation through a self-learning graph structure. The results showed that solar radiation is connected directly with month, hour, temperature, penetrating rainfall, water vapor pressure, and radiation time., Solar radiation prediction, Interpretable deep learning, Graph neural network, Attention, 0306-2619 5. David A. Wood (2020) Hourly-averaged solar plus wind power generation for Germany 2016: Long-term prediction, short-term forecasting, data mining and outlier analysis. Sustainable Cities and Society 60: 102227 https://doi.org/https://doi.org/10.1016/j.scs.2020.102227, Nationwide, hourly-averaged solar plus wind power generation (MW) data compiled for Germany for year 2016 is evaluated with ten influencing variables. Those variables cover, on an hourly basis, weather and ground-surface conditions and electricity prices. The transparent open box (TOB) algorithm accurately predicts and forecasts power generation (MW) for this dataset (prediction RMSE = 1175 MW and R2 = 0.9804; hour ahead forecast RMSE = 1632 MW and R2 = 0.9609) and meaningfully data mines the prediction outliers. Some 1.5 % of the data records display significant prediction errors. These records are mined to reveal that many of them form trends on a few specific days displaying unusual and rapidly changing weather conditions. Derivatives of ground level solar radiation, wind velocity and air pressure can meaningfully distinguish such unusual conditions and can be used to filter the dataset to further improve prediction accuracy. Derivatives and ratios of variables are also exploited to focus and modify feature selection for TOB analysis on approximately 10 % of the dataset (900 data records) responsible for the least accurate predictions. This more focused feature selection improves prediction accuracy for these more difficult to predict data records (RMSE improves from 3544 to 2630 MW; R2 from 0.8027 to 0.8938)., Country-wide renewable power generation, Combined solar and wind power planning, Predictions integrating diverse variables, Short-Term time series power forecasts, Prediction outlier analysis data filtering, 2210-6707
|
|