{"title":"Adaptive control systems for dual axis tracker using clear sky index and output power forecasting based on ML in overcast weather conditions","authors":"Nursultan Koshkarbay , Saad Mekhilef , Ahmet Saymbetov , Nurzhigit Kuttybay , Madiyar Nurgaliyev , Gulbakhar Dosymbetova , Sayat Orynbassar , Evan Yershov , Ainur Kapparova , Batyrbek Zholamanov , Askhat Bolatbek","doi":"10.1016/j.egyai.2024.100432","DOIUrl":"10.1016/j.egyai.2024.100432","url":null,"abstract":"<div><div>The use of artificial intelligence in renewable energy systems increases energy generation and improves energy system management. The control system of many solar trackers is designed for maximum radiation power conditions and shows decent performance indicators, but during rapidly changing weather conditions or cloudy days, the performance of the solar trackers is reduced due to moving parts and low irradiance. Some studies show that the horizontal configuration produces more energy with scattered solar radiation than solar tracking systems. This work shows the possibility of using solar tracking systems under different weather conditions and cloudy days. To achieve the goals, a new adaptive control system for dual-axis solar trackers with astronomical tracking was developed, which differs from traditional controls in the use of horizontal configurations under certain weather conditions. The assessment of spatio-temporal weather conditions was carried out using the Clear Sky Index (CSI) and was complemented by forecasting the panel's power output. The study found that at 0.4 CSI values, the horizontal configuration exhibits higher power output than solar tracking systems, providing the potential to use the threshold for adaptive control. The developed system is more efficient by 18.3 %, 14.9 %, and 10.01 % than the horizontal configuration, single-axis, and dual-axis solar trackers.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"18 ","pages":"Article 100432"},"PeriodicalIF":9.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142534495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Energy and AIPub Date : 2024-10-09DOI: 10.1016/j.egyai.2024.100431
Grant Buster, Pavlo Pinchuk, Jacob Barrons, Ryan McKeever, Aaron Levine, Anthony Lopez
{"title":"Supporting energy policy research with large language models: A case study in wind energy siting ordinances","authors":"Grant Buster, Pavlo Pinchuk, Jacob Barrons, Ryan McKeever, Aaron Levine, Anthony Lopez","doi":"10.1016/j.egyai.2024.100431","DOIUrl":"10.1016/j.egyai.2024.100431","url":null,"abstract":"<div><div>The recent growth in renewable energy development in the United States has been accompanied by a simultaneous surge in renewable energy siting ordinances. These zoning laws play a critical role in dictating the placement of wind and solar resources that are critical for achieving low-carbon energy futures. In this context, efficient access to and management of siting ordinance data becomes imperative. The National Renewable Energy Laboratory (NREL) recently introduced a public wind and solar siting database to fill this need. This paper presents a method for harnessing Large Language Models (LLMs) to automate the extraction of these siting ordinances from legal documents, enabling this database to maintain accurate up-to-date information in the rapidly changing energy policy landscape. A novel contribution of this research is the integration of a decision tree framework with LLMs. Our results show that this approach is 85 to 90 % accurate with outputs that can be used directly in downstream quantitative modeling. We discuss opportunities to use this work to support similar large-scale policy research in the energy sector. By unlocking new efficiencies in the extraction and analysis of legal documents using LLMs, this study enables a path forward for automated large-scale energy policy research.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"18 ","pages":"Article 100431"},"PeriodicalIF":9.6,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142434515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Energy and AIPub Date : 2024-09-27DOI: 10.1016/j.egyai.2024.100430
Pu He , Jun-Hong Chen , Chen-Zi Zhang , Zi-Yan Yu , Ming-Yang Wang , Jun-Yu Chen , Jia-Le Song , Yu-Tong Mu , Kun-Ying Gong , Wen-Quan Tao
{"title":"Optimization of modeling and temperature control of air-cooled PEMFC based on TLBO-DE","authors":"Pu He , Jun-Hong Chen , Chen-Zi Zhang , Zi-Yan Yu , Ming-Yang Wang , Jun-Yu Chen , Jia-Le Song , Yu-Tong Mu , Kun-Ying Gong , Wen-Quan Tao","doi":"10.1016/j.egyai.2024.100430","DOIUrl":"10.1016/j.egyai.2024.100430","url":null,"abstract":"<div><div>The temperature control of the air-cooled proton exchange membrane fuel cell (PEMFC) is important for effective and safe operation. To develop a practical and precise controller, this study combines the Radial Basis Function (RBF) neural network with Back Propagation neural network adaptive Proportion Integration Differentiation (BP-PID), and then a metaheuristic algorithm is used to optimize the parameters of RBF-BP-PID for further improvement in temperature control. First, an air-cooled PEMFC system model is established. To match the simulation data with the experimental data, Teaching Learning Based Optimization–Differential Evolution (TLBO-DE) is proposed to identify the unknown parameters, and the maximum relative error is <3.5 %. Second, RBF neural network is introduced to identify the stack temperature and provide the accurate <span><math><mfrac><mrow><mi>∂</mi><mi>y</mi><mo>(</mo><mi>k</mi><mo>)</mo></mrow><mrow><mi>∂</mi><mi>u</mi><mo>(</mo><mi>k</mi><mo>)</mo></mrow></mfrac></math></span> for BP-PID, which solves the problem of using sign function sgn(<span><math><mfrac><mrow><mi>∂</mi><mi>y</mi><mo>(</mo><mi>k</mi><mo>)</mo></mrow><mrow><mi>∂</mi><mi>u</mi><mo>(</mo><mi>k</mi><mo>)</mo></mrow></mfrac></math></span>) to approximate the <span><math><mfrac><mrow><mi>∂</mi><mi>y</mi><mo>(</mo><mi>k</mi><mo>)</mo></mrow><mrow><mi>∂</mi><mi>u</mi><mo>(</mo><mi>k</mi><mo>)</mo></mrow></mfrac></math></span> in BP-PID. Regarding the temperature control of air-cooled PEMFC, several controllers are compared, including PID, Fuzzy-PID, BP-PID and RBF-BP-PID. The proposed RBF-BP-PID achieves the best control effect, which reduces the integrated time and absolute error (ITAE) by 3.4 % and 15.8 % based on BP-PID in the startup and steady phases, respectively. Since the <span><math><mfrac><mrow><mi>∂</mi><mi>y</mi><mo>(</mo><mi>k</mi><mo>)</mo></mrow><mrow><mi>∂</mi><mi>u</mi><mo>(</mo><mi>k</mi><mo>)</mo></mrow></mfrac></math></span> provided by RBF changes softly and continuously during the control process, the parameters self-tuning ability of RBF-BP-PID is better than BP-PID. Third, to improve the control effect of RBF-BP-PID further, TLBO-DE is adopted to optimize the parameters of RBF neural network and BP neural network.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"18 ","pages":"Article 100430"},"PeriodicalIF":9.6,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Energy and AIPub Date : 2024-09-25DOI: 10.1016/j.egyai.2024.100429
Qi Wang , Haomin Zhu , Gang Pan , Jianguo Wei , Chen Zhang , Zhu Huang , Guowei Ling
{"title":"Distributed decision making for unmanned aerial vehicle inspection with limited energy constraint","authors":"Qi Wang , Haomin Zhu , Gang Pan , Jianguo Wei , Chen Zhang , Zhu Huang , Guowei Ling","doi":"10.1016/j.egyai.2024.100429","DOIUrl":"10.1016/j.egyai.2024.100429","url":null,"abstract":"<div><div>The unsatisfactory energy density of the state-of-art batteries imposes constraints on the practical application of unmanned aerial vehicles (UAVs). Establishing a UAV airport network that integrates energy supply and information exchange functionalities represents an ideal solution for enabling synergistic UAV operations. However, devising efficient distribution protocols for these airports remains a challenge. By leveraging modeling and analysis of the energy density of existing UAV batteries, we can forecast the flight range and distances achievable by UAVs. Here, we propose a distribution protocol for UAV airport platforms aimed at enhancing distribution accuracy by the use of AI principles. Furthermore, considering the possibility of emergency UAV stop, we introduce an emergency stop system in conjunction with standard stopping procedures to optimize distribution efficiency and enhance UAV inspection safety. Moreover, existing UAV airports usually provide energy to UAVs without harnessing UAVs to facilitate interconnection and interoperability among different airports. This inefficiency leads to significant resource wastage in energy distribution. To address this, we introduce a shared energy network that allows different companies to operate according to energy distribution needs. This network not only supplies energy to UAVs but also employs UAVs for energy collection and transportation, facilitating energy trading, business collaboration, and data transmission among diverse organizations. By enabling ubiquitous energy trading, this study provides us an ideal strategy for the future construction of energy network with interconnection and interoperability, which can be extended to other applications calling for energy distribution.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"18 ","pages":"Article 100429"},"PeriodicalIF":9.6,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142418643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Energy and AIPub Date : 2024-09-20DOI: 10.1016/j.egyai.2024.100427
Michael Meiser , Benjamin Duppe , Ingo Zinnikus , Alexander Anisimov
{"title":"VA-Creator—A Virtual Appliance Creator based on adaptive Neural Networks to generate synthetic power consumption patterns","authors":"Michael Meiser , Benjamin Duppe , Ingo Zinnikus , Alexander Anisimov","doi":"10.1016/j.egyai.2024.100427","DOIUrl":"10.1016/j.egyai.2024.100427","url":null,"abstract":"<div><p>With the advent of the Smart Home domain and the increasingly widespread application of Machine Learning (ML), obtaining power consumption data is becoming more and more important. Collecting real-world energy data using sensors is time consuming, expensive, error-prone and in some situations not possible. Therefore, we present the VA-Creator, a framework to create Virtual Appliances (VAs). These VAs synthesize power consumption patterns (PCPs) based on Neural Networks (NNs) which adapt their architecture to the training data structure to simplify the creation of new VAs. To be able to generate all appliance types available in a typical household we use various kinds of NN, including Multilayer Perceptrons (MLPs), Long Short-Term Memorys (LSTMs) and a specific Generative Adversarial Network (GAN) as well as different ML techniques such as XGBoost, selecting the appropriate technique depending on each appliance’s characteristics. We then compare the results of the ML models against real data and evaluate them by using Dynamic time Warping (DTW) as well as the classification performance of an MLP discriminator as metrics. Additionally, to ensure that the VAs allow to meaningfully train ML models, we use them to generate synthetic data and then train Non intrusive Load Monitoring (NILM) models in an extensive evaluation. The presented evaluation provides evidence that the VA models produce realistic and meaningful results.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"18 ","pages":"Article 100427"},"PeriodicalIF":9.6,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000934/pdfft?md5=7a1899b5d91ed06095525435800ee68a&pid=1-s2.0-S2666546824000934-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142273969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Energy and AIPub Date : 2024-09-18DOI: 10.1016/j.egyai.2024.100428
Yiheng Pang , Yun Wang , Zhiqiang Niu
{"title":"Deep learning from three-dimensional lithium-ion battery multiphysics model part I: Data development","authors":"Yiheng Pang , Yun Wang , Zhiqiang Niu","doi":"10.1016/j.egyai.2024.100428","DOIUrl":"10.1016/j.egyai.2024.100428","url":null,"abstract":"<div><div>Fast growing demands for electric vehicles require better longevity, safety and reliability for next-generation high-energy battery technologies. A data-centered battery management system is thus desired to interpret complex battery data and make decisions for properly managing multi-physics battery dynamics. Nowadays, Battery informatics are emerging as promising solutions by leveraging advanced machine learning tools to deliver accurate prediction of battery performance, health and safety, but is hurdled by a scarcity of data. To mitigate this issue, this study presents one of the first studies for data development through both experimental studies and three-dimensional (3-D) multi-physics modeling to underpin a deep learning framework with in-depth examination for battery performance and thermal risk prediction. Specifically, Part I focused on the development of the battery model which was thoroughly validated and analyzed to guarantee the model accuracy by two steps: firstly, we validated the multi-physics model against two commercial Lithium-ion batteries, i.e., Panasonic NCR18650B and 18650BD; Then, the coupling between thermal and electrochemical battery behaviors were analyzed deeply to demonstrate insights obtained from the model, such as voltage evolution and maximum local temperature (hot spot). The developed model proves to be capable of providing insightful and reliable data for the training of convolutional neural network and long short-term memory (CNN-LSTM) in part II.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"18 ","pages":"Article 100428"},"PeriodicalIF":9.6,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000946/pdfft?md5=2dba62c12bcdcee726bf78d19f8b94e2&pid=1-s2.0-S2666546824000946-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142310540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Energy and AIPub Date : 2024-09-17DOI: 10.1016/j.egyai.2024.100424
Mariah Batool , Oluwafemi Sanumi , Jasna Jankovic
{"title":"Application of artificial intelligence in the materials science, with a special focus on fuel cells and electrolyzers","authors":"Mariah Batool , Oluwafemi Sanumi , Jasna Jankovic","doi":"10.1016/j.egyai.2024.100424","DOIUrl":"10.1016/j.egyai.2024.100424","url":null,"abstract":"<div><p>Artificial Intelligence (AI) has revolutionized technological development globally, delivering relatively more accurate and reliable solutions to critical challenges across various research domains. This impact is particularly notable within the field of materials science and engineering, where artificial intelligence has catalyzed the discovery of new materials, enhanced design simulations, influenced process controls, and facilitated operational analysis and predictions of material properties and behaviors. Consequently, these advancements have streamlined the synthesis, simulation, and processing procedures, leading to material optimization for diverse applications. A key area of interest within materials science is the development of hydrogen-based electrochemical systems, such as fuel cells and electrolyzers, as clean energy solutions, known for their promising high energy density and zero-emission operations. While artificial intelligence shows great potential in studying both fuel cells and electrolyzers, existing literature often separates them, with a clear gap in comprehensive studies on electrolyzers despite their similarities. This review aims to bridge that gap by providing an integrated overview of artificial intelligence's role in both technologies. This review begins by explaining the fundamental concepts of artificial intelligence and introducing commonly used artificial intelligence-based algorithms in a simplified and clearly comprehensible way, establishing a foundational knowledge base for further discussion. Subsequently, it explores the role of artificial intelligence in materials science, highlighting the critical applications and drawing on examples from recent literature to build on the discussion. The paper then examines how artificial intelligence has propelled significant advancements in studying various types of fuel cells and electrolyzers, specifically emphasizing proton exchange membrane (PEM) based systems. It thoroughly explores the artificial intelligence tools and techniques for characterizing, manufacturing, testing, analyzing, and optimizing these systems. Additionally, the review critically evaluates the current research landscape, pinpointing progress and prevailing challenges. Through this thorough analysis, the review underscores the fundamental role of artificial intelligence in advancing the generation and utilization of clean energy, illustrating its transformative potential in this area of research.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"18 ","pages":"Article 100424"},"PeriodicalIF":9.6,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000909/pdfft?md5=b83f9a182a85a5f48c45be65e082c851&pid=1-s2.0-S2666546824000909-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142242848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Energy and AIPub Date : 2024-09-16DOI: 10.1016/j.egyai.2024.100425
Ziling Guo, Hui Wang, Huangyi Zhu, Zhiguo Qu
{"title":"Constraint-incorporated deep learning model for predicting heat transfer in porous media under diverse external heat fluxes","authors":"Ziling Guo, Hui Wang, Huangyi Zhu, Zhiguo Qu","doi":"10.1016/j.egyai.2024.100425","DOIUrl":"10.1016/j.egyai.2024.100425","url":null,"abstract":"<div><p>The temperature field within porous media is considerably affected by different boundary conditions, and effective thermal conductivity varies with spatial structure morphologies. At present, traditional prediction methods for the temperature field are expensive and time consuming, particularly for large structures and dimensions, whereas deep learning surrogate models have limitations related to constant boundary conditions and two-dimensional input slices, lacking the three-dimensional topology and spatial correlations. Herein, a constraint-incorporated model using U-Net architecture as the backbone is proposed to predict the temperature field and effective thermal conductivity of sphere-packed porous media, considering diverse external heat fluxes. A total of 510 original samples of temperature fields are generated through lattice Boltzmann method (LBM) simulations, which are further augmented to 33,150 samples using the self-amplification method for the training. Physical prior knowledge is incorporated into the model to constrain the training direction by adding physical constraint terms as well as adaptive weights to the loss function. Input vectors with different heat fluxes and porosities are embedded into latent features for predicting different boundary conditions. Results indicate that the constraint-incorporated model has a mean relative error ranging between 1.1 % and 5.7 % compared with the LBM results in the testing set. It exhibits weak dependence on the database size and substantially reduces computational time, with a maximum speedup ratio of 7.14 × 10<sup>6</sup>. This study presents a deep learning model with physical constraints for predicting heat conduction in porous media, alleviating the burden of extensive experiments and simulations.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"18 ","pages":"Article 100425"},"PeriodicalIF":9.6,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000910/pdfft?md5=545491ffe1f995bdf2ca44a0c51b3205&pid=1-s2.0-S2666546824000910-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142273968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Energy and AIPub Date : 2024-09-16DOI: 10.1016/j.egyai.2024.100426
Apri Wahyudi , Uthaiporn Suriyapraphadilok
{"title":"Predicting CO2 equilibrium solubility in various amine-CO2 systems using an artificial neural network model","authors":"Apri Wahyudi , Uthaiporn Suriyapraphadilok","doi":"10.1016/j.egyai.2024.100426","DOIUrl":"10.1016/j.egyai.2024.100426","url":null,"abstract":"<div><p>Three proposed reaction mechanisms can occur in an amine-CO<sub>2</sub> system: either zwitterionic or termolecular mechanisms for primary/secondary amines and base-catalyzed hydration for tertiary amines. The intricacy of this system hinders the construction of a general model for all types of amines. This study attempts to build an artificial neural network model that predicts the equilibrium solubility of any nonblended aqueous amine-CO<sub>2</sub> system under given operating conditions, regardless of the reaction mechanism. This is a novel approach that has not yet been reported. The amines were characterized using molecular descriptors derived from COSMO theory through density functional theory calculations to incorporate molecular structures as model features. Our model achieved performance metrics (R<sup>2</sup>) of 0.9645 and 0.9481 for the training and validation sets, respectively. For unfamiliar amines that were absent in both the training and validation sets, our model achieved an R<sup>2</sup> of 0.8601. Model benchmarking was performed using a previously established thermodynamic model. Interpretations of the model are also provided based on the chosen features. This study also offers exploratory insight into how the molecular structure and operating conditions affect the CO<sub>2</sub> equilibrium solubility in amines. The model developed in this study has the potential to reduce the solvent screening time in determining appropriate amines for larger-scale applications.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"18 ","pages":"Article 100426"},"PeriodicalIF":9.6,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000922/pdfft?md5=647dc9192891d787388e9c313289c368&pid=1-s2.0-S2666546824000922-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142274547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Energy and AIPub Date : 2024-09-11DOI: 10.1016/j.egyai.2024.100422
Viktor Walter , Andreas Wagner
{"title":"Probabilistic simulation of electricity price scenarios using Conditional Generative Adversarial Networks","authors":"Viktor Walter , Andreas Wagner","doi":"10.1016/j.egyai.2024.100422","DOIUrl":"10.1016/j.egyai.2024.100422","url":null,"abstract":"<div><p>A novel approach for generative time series simulation of electricity price scenarios is presented. A “Time Series Simulation Conditional Generative Adversarial Network” (TSS-CGAN) generates short-term electricity price scenarios. In particular, the network is capable of generating a 24-dimensional output vector that corresponds to the expected behavior of electricity markets. The model can replace typical approaches from financial mathematics like statistical factor models to model the price distribution around a given forecast. The data cover a 3-year period from 2020 to 2023. Our empirical study is conducted on the EPEX SPOT market in Europe. An electricity price scenario includes the prices of the hourly contracts of a day-ahead auction at the EPEX SPOT power exchange. The model uses multivariate time series as input factors, consisting of point forecasts of electricity prices and fundamental data on generation and load profiles. The architecture of a TSS-CGAN is based on the idea of Conditional Generative Adversarial Networks combined with 1D Convolutional Neural Networks and Bidirectional Long Short-Term Memory. The model is evaluated using qualitative and quantitative criteria. For the evaluation, 10,000 simulations of a test period are carried out. Qualitative criteria are whether the model follows certain electricity market-specific regularities and depicts them adequately. The quantitative analysis includes common error metric, compared to benchmark models, like DeepAR, Prophet and Temporal Fusion Transformer, the examination of the quantile ranges, the error distribution and a sensitivity analysis. The results show that the TSS-CGAN outperforms benchmark models such as DeepAR by reducing the continuous ranked probability score by 50% and considers market-specific circumstances such as the production of fluctuating energies and reacts correctly to changes in the corresponding variables.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"18 ","pages":"Article 100422"},"PeriodicalIF":9.6,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000880/pdfft?md5=68acafc3eee4796c88abd4e8470f8783&pid=1-s2.0-S2666546824000880-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142242214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}