Advances in Applied Energy最新文献

{"title":"Optimal scheduling of smart home energy systems: A user-friendly and adaptive home intelligent agent with self-learning capability","authors":"Zhengyi Luo ,&nbsp;Jinqing Peng ,&nbsp;Xuefen Zhang ,&nbsp;Haihao Jiang ,&nbsp;Rongxin Yin ,&nbsp;Yutong Tan ,&nbsp;Mengxin Lv","doi":"10.1016/j.adapen.2024.100182","DOIUrl":"10.1016/j.adapen.2024.100182","url":null,"abstract":"<div><p>This paper proposed a user-friendly and adaptive home intelligent agent with self-learning capability for optimal scheduling of smart home energy systems. The intelligent agent autonomously identifies model parameters based on system operation data, eliminating the need for manual input and making it more user-friendly and practical to implement. It can also self-learn the latest energy consumption information from an updated dataset and adaptively adjust model parameters to accommodate changing conditions. Utilizing these determined models as input, the intelligent agent performs day-ahead optimal scheduling using the proposed many-objective integer nonlinear optimization model and automatically controls system operation. Experimental studies were conducted on a laboratory-based smart home energy system to verify the effectiveness of the developed intelligent agent in different scenarios. The results consistently demonstrate Mean Absolute Percentage Errors below -12.7 % across all three scenarios, indicating the accuracy of the intelligent agent. Furthermore, the optimal scheduling significantly enhances system performances. After optimization, daily operational costs, peak-valley differences, and CO₂ emissions were reduced by 34.1 % to 81.6 %, 29.2 % to 36.7 %, and 19.6 % to 43.2 %, respectively. Moreover, the PV generation self-consumption rate and self-sufficiency rate improved by 29.6 % to 38.0 % and 40.5 % to 49.4 %, respectively. The proposed intelligent agent provides invaluable guidance for optimal dispatch of smart home energy systems in real-world settings.</p></div>","PeriodicalId":34615,"journal":{"name":"Advances in Applied Energy","volume":"15 ","pages":"Article 100182"},"PeriodicalIF":13.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666792424000209/pdfft?md5=1cedc846099a911397ba821e7c77e286&pid=1-s2.0-S2666792424000209-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141623286","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}

{"title":"Risk-aware microgrid operation and participation in the day-ahead electricity market","authors":"Robert Herding ,&nbsp;Emma Ross ,&nbsp;Wayne R. Jones ,&nbsp;Elizabeth Endler ,&nbsp;Vassilis M. Charitopoulos ,&nbsp;Lazaros G. Papageorgiou","doi":"10.1016/j.adapen.2024.100180","DOIUrl":"https://doi.org/10.1016/j.adapen.2024.100180","url":null,"abstract":"<div><p>This work examines the daily bidding problem of a grid-connected microgrid with locally deployed resources for electricity generation, storage and its own electricity demand. Trading electricity in energy markets may offer economic incentives but exposes the microgrid to financial risk caused by market commitments. Hence, a multi-objective, two-stage stochastic mixed integer linear programming (MILP) model is formulated, extending prior work of a risk-neutral microgrid bidding approach. The multi-objective model minimises both expected total cost of day-ahead microgrid operations and financial risk from bidding measured by conditional value-at-risk (CVaR). Bidding curves derived as first stage decisions are always feasible under present market rules – including a limitation on the number of break points per submitted curve – while being near optimal for the microgrid’s day-ahead recourse schedule. The proposed optimisation model is embedded in a variant of the <span><math><mi>ɛ</mi></math></span>-constrained method to generate bidding curve candidates with different trade-offs between the two conflicting objectives. Moreover, scenario reduction is used to compromise accuracy of the uncertainty set for better computational performance. Particularly, the marginal relative probability distance between initial and reduced scenario set is suggested to make a decision on the extent of scenario reduction. The proposed solution procedure is tested in a computational study to demonstrate its applicability to generate optimal microgrid bidding curve candidates with different emphasis between total cost and CVaR in reasonable computational time.</p></div>","PeriodicalId":34615,"journal":{"name":"Advances in Applied Energy","volume":"15 ","pages":"Article 100180"},"PeriodicalIF":13.0,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666792424000180/pdfft?md5=96b7a1215928fbf42c89bb54f97b0164&pid=1-s2.0-S2666792424000180-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141540414","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}

{"title":"Life cycle assessment of ammonia co-firing power plants: A comprehensive review and analysis from a whole industrial chain perspective","authors":"Hui Kong ,&nbsp;Yueqiao Sun ,&nbsp;Hongsheng Wang ,&nbsp;Jian Wang ,&nbsp;Liping Sun ,&nbsp;Jun Shen","doi":"10.1016/j.adapen.2024.100178","DOIUrl":"10.1016/j.adapen.2024.100178","url":null,"abstract":"<div><p>Ammonia, a reliable low-carbon alternative fuel with energy storage capabilities, has garnered increasing attention for its application of co-firing in coal-fired power plants as a strategy to mitigate direct carbon emissions. However, various types of ammonia production technologies result in diverse economic feasibility and emission intensities. Simultaneously, each stage, spanning from upstream processes such as raw material extraction to downstream applications, contributes to carbon emissions, which cannot be ignored. It is crucial to select the appropriate assessment method to determine the transformation pathways for co-firing systems. To this end, this review presents a comprehensive life cycle assessment of ammonia co-firing systems from a whole industrial chain perspective, encompassing the entire gamut of processes from fuel production and transportation to co-firing. Studies of the industrial chain perspective and of life cycle assessment methodology that are uniquely tailored for co-firing systems are presented. A nuanced exploration of distinct technologies across the spectrum of system processes ensues, including the advantages, limitations, and trends in advancement, based on carbon emissions and economic criteria. Considering the diverse fuel production, especially ammonia, typologies and intricate processes have undergone comprehensive review. The combustion characteristics, emissions, and economic factors associated with the co-firing process are systematically summarized, drawing upon aspects such as dynamics, experiments, simulations, and demonstration projects. This study illuminates the progression and technology selection of co-firing systems across multiple stages of the whole industry chain, thereby furnishing insights relevant to the low-carbon transformation of ammonia co-firing with coal in power plants.</p></div>","PeriodicalId":34615,"journal":{"name":"Advances in Applied Energy","volume":"14 ","pages":"Article 100178"},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666792424000167/pdfft?md5=2eee1ae8953fb0299668fa2c01a83efe&pid=1-s2.0-S2666792424000167-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141138685","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}

{"title":"Variational quantum circuit learning-enabled robust optimization for AI data center energy control and decarbonization","authors":"Akshay Ajagekar ,&nbsp;Fengqi You","doi":"10.1016/j.adapen.2024.100179","DOIUrl":"https://doi.org/10.1016/j.adapen.2024.100179","url":null,"abstract":"<div><p>As the demand for artificial intelligence (AI) models and applications continues to grow, data centers that handle AI workloads are experiencing a rise in energy consumption and associated carbon footprint. This work proposes a variational quantum computing-based robust optimization (VQC-RO) framework for control and energy management in large-scale data centers to address the computational challenges and overcome limitations of conventional model-based and model-free strategies. The VQC-RO framework integrates variational quantum circuits (VQCs) with classical optimization to enable efficient and uncertainty-aware control of energy systems in AI data centers. Quantum algorithms executed on noisy intermediate-scale quantum (NISQ) devices are used for value function estimation trained with Q-learning, leading to the formulation of a robust optimization problem with uncertain coefficients. The quantum computing-based robust control strategy is designed to address uncertainties associated with weather conditions and renewable energy generation while optimizing energy consumption in AI data centers. This work also outlines the computational experiments conducted at various AI data center locations in the United States to analyze the reduction in power consumption and carbon emission levels associated with the proposed quantum computing-based robust control framework. This work contributes a novel approach to energy-efficient and sustainable data center operation, promising to reduce carbon emissions and energy consumption in large-scale data centers handling AI workloads by 9.8 % and 12.5 %, respectively.</p></div>","PeriodicalId":34615,"journal":{"name":"Advances in Applied Energy","volume":"14 ","pages":"Article 100179"},"PeriodicalIF":0.0,"publicationDate":"2024-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666792424000179/pdfft?md5=21c93fc476ac75038664b923e8d0dd02&pid=1-s2.0-S2666792424000179-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140948357","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}

{"title":"Advances in model predictive control for large-scale wind power integration in power systems","authors":"Peng Lu ,&nbsp;Ning Zhang ,&nbsp;Lin Ye ,&nbsp;Ershun Du ,&nbsp;Chongqing Kang","doi":"10.1016/j.adapen.2024.100177","DOIUrl":"10.1016/j.adapen.2024.100177","url":null,"abstract":"<div><p>Wind power exhibits low controllability and is situated in dispersed geographical locations, presenting complex coupling and aggregation characteristics in both temporal and spatial dimensions. When large-scale wind power is integrated into the power grid, it will bring a significant technical challenge: the highly variable nature of wind power poses a threat to the safe and stable control of the power, frequency, and voltage in the power system. Simultaneously, the model predictive control (MPC) technology provides more opportunities for investigating control issues related to large-scale wind power integration in power systems. This paper provides a timely and systematic overview of the applications of MPC in the field of wind power for the first time, innovatively embedding MPC technology into multi-level (e.g., wind turbines, wind farms, wind power cluster, and power grids) and multi-objective (e.g., power, frequency, and voltage) control. Firstly, the basic concept and classification criteria of MPC are developed, and the available modeling methods in wind power are carefully compared. Secondly, the application scenarios of MPC in multi-level and multi-objective wind power control are summarized. Finally, how to use a variety of optimization algorithms to solve these models is discussed. Based on the broad review above, we summarize several key scientific issues related to predictive control and discuss the challenges and future development directions in detail. This paper details the role of MPC technology in multi-level and multi-objective control within the wind power sector, aiming to help engineers and scientists understand its substantial potential in wind power integration in power systems.</p></div>","PeriodicalId":34615,"journal":{"name":"Advances in Applied Energy","volume":"14 ","pages":"Article 100177"},"PeriodicalIF":0.0,"publicationDate":"2024-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666792424000155/pdfft?md5=8da5ee9be84dc66a46cbd485ccbef1b0&pid=1-s2.0-S2666792424000155-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140760201","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}

{"title":"Introducing sodium lignosulfonate as an effective promoter for CO2 sequestration as hydrates targeting gaseous and liquid CO2","authors":"Hailin Huang ,&nbsp;Xuejian Liu ,&nbsp;Hongfeng Lu ,&nbsp;Chenlu Xu ,&nbsp;Jianzhong Zhao ,&nbsp;Yan Li ,&nbsp;Yuhang Gu ,&nbsp;Zhenyuan Yin","doi":"10.1016/j.adapen.2024.100175","DOIUrl":"10.1016/j.adapen.2024.100175","url":null,"abstract":"<div><p>Hydrate-based CO₂ sequestration (HBCS) emerges as a promising solution to sequestrate CO₂ as solid hydrates for the benefit of reducing CO₂ concentration in the atmosphere. The natural conditions of high-pressure and low-temperature in marine seabed provide an ideal reservoir for CO₂ hydrate, enabling long-term sequestration. A significant challenge in the application of HBCS is the identification of an environmental-friendly promoter to enhance or tune CO₂ hydrate kinetics, which is intrinsically sluggish. In addition, the promoter identified should be effective in all CO₂ sequestration conditions, covering CO₂ injection as gas or liquid. In this study, we introduced sodium lignosulfonate (SL), a by-product from the papermaking industry, as an eco-friendly kinetic promoter for CO₂ hydrate formation. The impact of SL (0–3.0 wt.%) on the kinetics of CO₂ hydrate formation from gaseous and liquid CO₂ was systematically investigated. CO₂ hydrate morphology images were acquired for both gaseous and liquid CO₂ in the presence of SL for the explanation of the observed promotion effect. The promotion effect of SL on CO₂ hydrate formation is optimal at 1.0 wt.% with induction time reduced to 5.3 min and 21.1 min for gaseous and liquid CO₂, respectively. Moreover, CO₂ storage capacity increases by around two times at 1.0 wt.% SL, reaching 85.1 v/v and 57.1 v/v for gaseous and liquid CO₂, respectively. The applicability of SL as an effective kinetic promoter for both gaseous and liquid CO₂ was first demonstrated. A mechanism explaining how SL promotes CO₂ hydrate formation was formulated with additional nucleation sites by SL micelles and the extended contact surface offered by generated gas bubbles or liquid droplets with SL. The study demonstrates that SL as an effective promoter for CO₂ hydrate kinetics is possible for adoption in large-scale HBCS projects both nearshore and offshore.</p></div>","PeriodicalId":34615,"journal":{"name":"Advances in Applied Energy","volume":"14 ","pages":"Article 100175"},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666792424000131/pdfft?md5=0849e60616fc3e08beffef6ac31ad037&pid=1-s2.0-S2666792424000131-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140792160","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}

{"title":"Assessing the conditions for economic viability of dynamic electricity retail tariffs for households","authors":"Judith Stute ,&nbsp;Sabine Pelka ,&nbsp;Matthias Kühnbach ,&nbsp;Marian Klobasa","doi":"10.1016/j.adapen.2024.100174","DOIUrl":"https://doi.org/10.1016/j.adapen.2024.100174","url":null,"abstract":"<div><p>The success of the energy transition relies on effectively utilizing flexibility in the power system. Dynamic tariffs are a highly discussed and promising innovation for incentivizing the use of residential flexibility. However, their full potential can only be realized if households achieve significant benefits. This paper specifically addresses this topic. We examine the leverage of household flexibility and the financial benefits of using dynamic tariffs, considering household heterogeneity, the costs of home energy management systems and smart meters, the impact of higher electricity prices and price spreads and the differences between types of prosumers. To comprehensively address this topic, we use the EVaTar-building model, a simulation framework that includes embedded optimization designed to simulate household electricity consumption patterns under the influence of a home energy management system or in response to dynamic tariffs. The study's main finding is that households can achieve significant cost savings and increase flexibility utilization by using a home energy management system and dynamic electricity tariffs, provided that electricity prices and price spreads reach higher levels. When comparing price levels in a low and high electricity price scenario, with an increase of the average electricity price by 15.2 €ct/kWh (67 % higher than the average for the year 2019) and an increase of the price spread by 8.9 €ct/kWh (494 % higher), the percentage of households achieving cost savings increases from 3.9 % to 62.5 %. Households with both an electric vehicle and a heat pump observed the highest cost benefits. Sufficiently high price incentives or sufficiently low costs for home energy management systems and metering point operation are required to enable households to mitigate rising electricity costs and ensure residential flexibility for the energy system through electric vehicles and heat pumps.</p></div>","PeriodicalId":34615,"journal":{"name":"Advances in Applied Energy","volume":"14 ","pages":"Article 100174"},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S266679242400012X/pdfft?md5=0189c869809c5ea6aa382102696e1ea8&pid=1-s2.0-S266679242400012X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140644365","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}

{"title":"Reconfigurable supply-based feedback control for enhanced energy flexibility of air-conditioning systems facilitating grid-interactive buildings","authors":"Mingkun Dai ,&nbsp;Hangxin Li ,&nbsp;Xiuming Li ,&nbsp;Shengwei Wang","doi":"10.1016/j.adapen.2024.100176","DOIUrl":"https://doi.org/10.1016/j.adapen.2024.100176","url":null,"abstract":"<div><p>Air-conditioning systems have great potential to provide energy flexibility services to the power grids of high-renewable penetration, due to their high power consumption and inherent energy flexibilities. Direct load control by switching off some operating chillers is the simplest and effective means for air-conditioning systems in buildings to respond to urgent power reduction requests of power grids. However, the implementation of this approach in today's buildings, which widely adopt demand-based feedback controls, would result in serious problems including disordered cooling distribution and likely extra energy consumption. This study, therefore, proposes a reconfigurable control strategy to address these problems. This strategy consists of supply-based feedback control, incorporated with the conventional demand-based feedback control, a control loop reconfiguration scheme and a setpoint reset scheme, facilitating effective control under limited cooling supply and smooth transition between supply-based and demand-based feedback control modes. The proposed control strategy is deployed in a commonly-used digital controller to conduct hardware-in-the-loop control tests on an air-conditioning system involving six AHUs. Test results show that the reconfigurable control achieves commendable control performance. Proper chilled water distribution enables even thermal comfort control among the building zones during demand response and rebound periods. Temperature deviation of the building zones is controlled below 0.2 K most of the time. 11.6 % and 27 % of power demand reductions are achieved during demand response and rebound periods respectively, using the proposed reconfigurable control compared with that using conventional controls.</p></div>","PeriodicalId":34615,"journal":{"name":"Advances in Applied Energy","volume":"14 ","pages":"Article 100176"},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666792424000143/pdfft?md5=5d7aa405b6962d8965ddb55dd055d25f&pid=1-s2.0-S2666792424000143-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140638188","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}

{"title":"A data-aided robust approach for bottleneck identification in power transmission grids for achieving transportation electrification ambition: a case study in New York state","authors":"Qianzhi Zhang ,&nbsp;Yuechen Sopia Liu ,&nbsp;H.Oliver Gao ,&nbsp;Fengqi You","doi":"10.1016/j.adapen.2024.100173","DOIUrl":"https://doi.org/10.1016/j.adapen.2024.100173","url":null,"abstract":"<div><p>As the enthusiasm for electric vehicles passes the range anxiety and other tests, large-scale transportation electrification becomes a prominent topic in research and policy discussions. In consequence, the public attention has shifted upstream and holistically towards the integration of large-scale transportation electrification to power systems. This paper proposes a method to identify bottlenecks in power transmission systems to accommodate large-scale and stochastic electric vehicles charging demands. First, a distributionally robust chance-constrained direct current optimal power flow model is developed to quantify the impacts of stochastic electric vehicles charging demands. Subsequently, an agent-based model with the trip-chain method is applied to obtain the spatiotemporal distributions of electric vehicles charging demands for both light-duty electric vehicles and medium and heavy-duty electric vehicles. The first two moments of those distributions are extracted to build an ambiguity set of electric vehicles charging demands. Finally, a 121-bus synthetic transmission network for New York State power systems is used to validate the future transportation electrification in New York State from 2025 to 2035. Results show that the large-scale transportation electrification in New York State will account for approximately 13.33 % to 16.79 % of the total load demand by 2035. The transmission capacity is the major bottleneck in supporting New York State to achieve its transportation electrification. To resolve the bottlenecks, we explore some possible solutions, such as transmission capacity expansion and distributed energy resources investment. Wind power shows an advantage over solar energy in terms of total operational costs due to better peak alignment between wind power and electric vehicles charging demand.</p></div>","PeriodicalId":34615,"journal":{"name":"Advances in Applied Energy","volume":"14 ","pages":"Article 100173"},"PeriodicalIF":0.0,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666792424000118/pdfft?md5=f52488c0b3d8b48dd2976c65034b9e55&pid=1-s2.0-S2666792424000118-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140639244","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}

{"title":"SkyGPT: Probabilistic ultra-short-term solar forecasting using synthetic sky images from physics-constrained VideoGPT","authors":"Yuhao Nie ,&nbsp;Eric Zelikman ,&nbsp;Andea Scott ,&nbsp;Quentin Paletta ,&nbsp;Adam Brandt","doi":"10.1016/j.adapen.2024.100172","DOIUrl":"https://doi.org/10.1016/j.adapen.2024.100172","url":null,"abstract":"<div><p>The variability of solar photovoltaic (PV) power output, driven by rapidly changing cloud dynamics, hinders the transition to reliable renewable energy systems. Information on future sky conditions, especially cloud coverage, holds the promise for improving PV output forecasting. Leveraging recent advances in generative artificial intelligence (AI), we introduce <em>SkyGPT</em>, a physics-constrained stochastic video prediction model, which predicts plausible future images of the sky using historical sky images. We show that <em>SkyGPT</em> can accurately capture cloud dynamics, producing highly realistic and diverse future sky images. We further demonstrate its efficacy in 15-minute-ahead probabilistic PV output forecasting using real-world power generation data from a 30-kW rooftop PV system. By coupling <em>SkyGPT</em> with a U-Net-based PV power prediction model, we observe superior prediction reliability and sharpness compared with several benchmark methods. The propose approach achieves a continuous ranked probability score (CRPS) of 2.81 kW, outperforming a classic convolutional neural network (CNN) baseline by 13% and the smart persistence model by 23%. The findings of this research could aid efficient and resilient management of solar electricity generation, particularly as we transition to renewable-heavy grids. The study also provides valuable insights into stochastic cloud modeling for a broad research community, encompassing fields such as solar energy meteorology and atmospheric sciences.</p></div>","PeriodicalId":34615,"journal":{"name":"Advances in Applied Energy","volume":"14 ","pages":"Article 100172"},"PeriodicalIF":0.0,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666792424000106/pdfft?md5=9fe829b2f1a0245854798ffc7c7f513a&pid=1-s2.0-S2666792424000106-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140555380","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}