Pub Date : 2024-09-06DOI: 10.3389/fenrg.2024.1413297
Xu Wen, Quan Zhou, Baosong Luo, Yang Yang, Rui Mao, Dong Fan
Insufficient flexibility is a major barrier to the development of new power systems. Leveraging the resource allocation function of the electricity market is a promising way to enhance the flexibility of power systems and promote the consumption of renewables. The reasonable allocation of ancillary service costs plays a pivotal role in this function. Towards the target of “who causes, who shares,” various research related to cost allocation has been conducted. However, there is a lack of quantitative analysis of the impact of different cost allocation mechanisms on the market participants’ revenues. Whether various cost allocation mechanisms can alleviate the insufficient flexibility problem of power systems needs to be validated. With this in mind, taking operating reserve ancillary services as an example, a long-term market operation simulation model with energy-reserve joint clearing is established in this paper based on the time series production simulation. According to this, the revenues of market participants under different reserve cost allocation mechanisms are quantified. Besides, a self-dispatch model for the energy storage (ES) equipped by renewables is established, based on which the impact of ES on the revenues of renewables under different cost allocation mechanisms is analyzed. Case studies based on practical data from a provincial power grid in China demonstrate that with the well-designed reserve cost allocation mechanism, the revenues of flexible resources can be ensured. Meanwhile, renewables are incentivized to reduce their fluctuations and uncertainties by equipping the ES. Hence, the insufficient flexibility problem of power systems can be alleviated from both supply and requirements perspectives.
灵活性不足是新型电力系统发展的主要障碍。发挥电力市场的资源配置功能,是提高电力系统灵活性、促进可再生能源消纳的有效途径。在这一功能中,辅助服务成本的合理分配起着举足轻重的作用。为了实现 "谁造成、谁分担 "的目标,人们开展了与成本分配相关的各种研究。然而,不同成本分配机制对市场参与者收益的影响缺乏定量分析。各种成本分配机制能否缓解电力系统灵活性不足的问题还需要验证。鉴于此,本文以运行储备辅助服务为例,基于时间序列生产仿真,建立了能量储备联合清算的长期市场运行仿真模型。据此,量化了不同储备成本分配机制下市场参与者的收益。此外,本文还建立了可再生能源配备的储能装置(ES)的自我调度模型,并在此基础上分析了不同成本分配机制下储能装置对可再生能源收益的影响。基于中国某省级电网实际数据的案例研究表明,通过精心设计的储备成本分配机制,可确保灵活资源的收益。同时,可再生能源可以通过配备 ES 来减少其波动和不确定性。因此,电力系统灵活性不足的问题可以从供应和需求两个角度得到缓解。
{"title":"Impact of different reserve cost allocation mechanisms on market participants’ revenues: a quantitative analysis","authors":"Xu Wen, Quan Zhou, Baosong Luo, Yang Yang, Rui Mao, Dong Fan","doi":"10.3389/fenrg.2024.1413297","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1413297","url":null,"abstract":"Insufficient flexibility is a major barrier to the development of new power systems. Leveraging the resource allocation function of the electricity market is a promising way to enhance the flexibility of power systems and promote the consumption of renewables. The reasonable allocation of ancillary service costs plays a pivotal role in this function. Towards the target of “who causes, who shares,” various research related to cost allocation has been conducted. However, there is a lack of quantitative analysis of the impact of different cost allocation mechanisms on the market participants’ revenues. Whether various cost allocation mechanisms can alleviate the insufficient flexibility problem of power systems needs to be validated. With this in mind, taking operating reserve ancillary services as an example, a long-term market operation simulation model with energy-reserve joint clearing is established in this paper based on the time series production simulation. According to this, the revenues of market participants under different reserve cost allocation mechanisms are quantified. Besides, a self-dispatch model for the energy storage (ES) equipped by renewables is established, based on which the impact of ES on the revenues of renewables under different cost allocation mechanisms is analyzed. Case studies based on practical data from a provincial power grid in China demonstrate that with the well-designed reserve cost allocation mechanism, the revenues of flexible resources can be ensured. Meanwhile, renewables are incentivized to reduce their fluctuations and uncertainties by equipping the ES. Hence, the insufficient flexibility problem of power systems can be alleviated from both supply and requirements perspectives.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-06DOI: 10.3389/fenrg.2024.1445383
Ji Xiaotong, Jiang Kezheng, Wang Chenyu, Ye Chang, Liu Dan
With the continuous advancement of science and technology, there is a growing global focus on new energy sources. Despite the rapid progress of offshore wind power generation systems, they are still plagued by issues such as significant transmission loss, limited transmission distance, and low-frequency oscillation, which hinder further development. To address these challenges, the Flexible Direct Current Transmission System (VSC-HVDC) has emerged as a widely studied solution. The integration of energy storage power stations presents new opportunities for enhancing offshore wind power transmission systems. These power stations not only serve as energy buffer pools to reduce transmission loss but also improve transmission efficiency through intelligent regulation and control, effectively mitigating low-frequency oscillation. This article introduces an optimization control parameter design method based on sensitivity analysis to enhance the stability of MTDC based on MMC. It outlines the topology structure of the offshore VSC-HVDC system, covering the main circuit and control system. Additionally, the article delves into the derivation of the small signal stability model of the system and investigates the selection of control parameters based on the eigenvalue objective function. Lastly, it analyzes the impact of the control system on the stability of the wind power flexible direct output converter station, highlighting the significant influence of control system parameters on the small signal stability of MTDC systems based on MMC. The MMC parameter selection strategy proposed in this paper is shown to effectively enhance system stability.
{"title":"MMC parameter selection and stability control for flexible direct transmission converter station of energy storage power station","authors":"Ji Xiaotong, Jiang Kezheng, Wang Chenyu, Ye Chang, Liu Dan","doi":"10.3389/fenrg.2024.1445383","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1445383","url":null,"abstract":"With the continuous advancement of science and technology, there is a growing global focus on new energy sources. Despite the rapid progress of offshore wind power generation systems, they are still plagued by issues such as significant transmission loss, limited transmission distance, and low-frequency oscillation, which hinder further development. To address these challenges, the Flexible Direct Current Transmission System (VSC-HVDC) has emerged as a widely studied solution. The integration of energy storage power stations presents new opportunities for enhancing offshore wind power transmission systems. These power stations not only serve as energy buffer pools to reduce transmission loss but also improve transmission efficiency through intelligent regulation and control, effectively mitigating low-frequency oscillation. This article introduces an optimization control parameter design method based on sensitivity analysis to enhance the stability of MTDC based on MMC. It outlines the topology structure of the offshore VSC-HVDC system, covering the main circuit and control system. Additionally, the article delves into the derivation of the small signal stability model of the system and investigates the selection of control parameters based on the eigenvalue objective function. Lastly, it analyzes the impact of the control system on the stability of the wind power flexible direct output converter station, highlighting the significant influence of control system parameters on the small signal stability of MTDC systems based on MMC. The MMC parameter selection strategy proposed in this paper is shown to effectively enhance system stability.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-05DOI: 10.3389/fenrg.2024.1323357
Imane Hammou Ou Ali, Ali Agga, Mohammed Ouassaid, Mohamed Maaroufi, Ali Elrashidi, Hossam Kotb
The forecasting of home energy consumption is a crucial and challenging topic within the realm of artificial intelligence (AI)-enhanced energy management in smart grids (SGs). The primary goal of this study is to provide accurate energy consumption forecasts for a smart home. Two deep learning models are implemented: ConvLSTM, which combines convolutional operations with Long Short-Term Memory (LSTM), and the CNN-LSTM model, which synergizes Convolutional Neural Networks (CNN) and LSTM networks. Both hybrid models offer a comprehensive approach to modeling complex relationships in spatial and temporal patterns. Additionally, two baseline models—LSTM and CNN—are employed for comparative analysis. Utilizing real data from a smart home in Houston, Texas, the results demonstrate that both the hybrid models deliver highly accurate predictions for energy consumption. However, the ConvLSTM model outperforms all proposed models, improving predictions in terms of mean absolute percentage error by 4.52%, 9.59%, and 10.53% for 1 day, 3 days, and 6 days in advance, respectively.
{"title":"Predicting short-term energy usage in a smart home using hybrid deep learning models","authors":"Imane Hammou Ou Ali, Ali Agga, Mohammed Ouassaid, Mohamed Maaroufi, Ali Elrashidi, Hossam Kotb","doi":"10.3389/fenrg.2024.1323357","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1323357","url":null,"abstract":"The forecasting of home energy consumption is a crucial and challenging topic within the realm of artificial intelligence (AI)-enhanced energy management in smart grids (SGs). The primary goal of this study is to provide accurate energy consumption forecasts for a smart home. Two deep learning models are implemented: ConvLSTM, which combines convolutional operations with Long Short-Term Memory (LSTM), and the CNN-LSTM model, which synergizes Convolutional Neural Networks (CNN) and LSTM networks. Both hybrid models offer a comprehensive approach to modeling complex relationships in spatial and temporal patterns. Additionally, two baseline models—LSTM and CNN—are employed for comparative analysis. Utilizing real data from a smart home in Houston, Texas, the results demonstrate that both the hybrid models deliver highly accurate predictions for energy consumption. However, the ConvLSTM model outperforms all proposed models, improving predictions in terms of mean absolute percentage error by 4.52%, 9.59%, and 10.53% for 1 day, 3 days, and 6 days in advance, respectively.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The increasing number of electric Vehicles (EVs) and their influence on the power grid present difficulties that this article addresses by suggesting optimal planning methods for EV charging and discharging. EV charging and discharging operations are effectively managed by creating both locally and globally optimal planning schemes. Future transportation could be changed by the widespread adoption of dynamic wireless power transfer systems in conjunction with EVs, as they would enable speedier travel and continuous EV battery recharging. Dynamic wireless power transfer is a practical answer to problems with electric vehicles. The electrification of automobiles will have a significant influence on the power infrastructure due to the increase in demand for electricity. In this study, we provide an optimal planning method worldwide and a locally optimal strategy for EV charging and discharging. To minimize the total cost of all EVs that charge and discharge during the day, we propose an optimization problem for global planning in which the charging powers are optimized. The simulation results demonstrate that the proposed planning schemes can effectively reduce the total electricity cost for EV owners while also minimizing the impact on the power grid. The globally optimal planning scheme achieves the lowest electricity cost, while the locally optimal scheme provides a good balance between cost reduction and computational complexity.
{"title":"Optimal planning strategy for charging and discharging an electric vehicle connected to the grid through wireless recharger","authors":"Asma Boukhchana, Aymen Flah, Abdulaziz Alkuhayli, Rahmat Ullah, Claude Ziad El-Bayeh","doi":"10.3389/fenrg.2024.1453711","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1453711","url":null,"abstract":"The increasing number of electric Vehicles (EVs) and their influence on the power grid present difficulties that this article addresses by suggesting optimal planning methods for EV charging and discharging. EV charging and discharging operations are effectively managed by creating both locally and globally optimal planning schemes. Future transportation could be changed by the widespread adoption of dynamic wireless power transfer systems in conjunction with EVs, as they would enable speedier travel and continuous EV battery recharging. Dynamic wireless power transfer is a practical answer to problems with electric vehicles. The electrification of automobiles will have a significant influence on the power infrastructure due to the increase in demand for electricity. In this study, we provide an optimal planning method worldwide and a locally optimal strategy for EV charging and discharging. To minimize the total cost of all EVs that charge and discharge during the day, we propose an optimization problem for global planning in which the charging powers are optimized. The simulation results demonstrate that the proposed planning schemes can effectively reduce the total electricity cost for EV owners while also minimizing the impact on the power grid. The globally optimal planning scheme achieves the lowest electricity cost, while the locally optimal scheme provides a good balance between cost reduction and computational complexity.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Currently, there is a scarcity of studies exploring the safe operating parameters for coal-fired power units at loads below 30%.To accurately understand the operating characteristics of coal-fired units under low load conditions, and to provide a design basis for flexibility modifications, a simulation model coupled with boiler and turbine was established, which includes the flue gas and air system, steam and water system, steam turbine, and steam extraction heat recovery system, and the iterative calculation strategy for low load conditions was proposed. The simulation calculation was performed on a 350 MW supercritical coal-fired unit, with the model results showing a high degree of alignment with the unit’s design and operational parameters. Under the condition of 269MW, the maximum calculation error between the model’s predicted exit flue gas temperature of the air preheater and the actual operational results was 8.84%. This discrepancy was due to a sudden increase in the operating flue gas temperature, which may be associated with a blockage in the air preheater. And the simulation results under low load conditions indicate that when the unit load is below 20%, the furnace total airflow is controlled to no less than 30% of the airflow at Maximum Continuous Rating (BMCR) and the minimum feedwater flow rate can be reduced to 20% of that in Turbine Heat Acceptance (THA) load, and the unit switches to wet state operation around 20% load. As the unit load decreases, the coal consumption rate for power generation and steam turbine heat consumption rate both increase significantly. The coal consumption rate for power generation at 30% load is increased by 13.3% compared to BMCR load, and it is increased by 32.5% at 15% load which is operated in wet state. Under low load conditions, the coal consumption rate of the unit can be reduced by decreasing the oxygen content in the flue gas, reducing the minimum feedwater flow rate, and implementing boiler water recirculation.
{"title":"Simulation of low-load operation for a 350 MW supercritical unit","authors":"Shiming Xu, Bo Yu, Qiang Zhou, Xiangyu Zhang, Fujun Wang, Huaichun Zhou","doi":"10.3389/fenrg.2024.1448416","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1448416","url":null,"abstract":"Currently, there is a scarcity of studies exploring the safe operating parameters for coal-fired power units at loads below 30%.To accurately understand the operating characteristics of coal-fired units under low load conditions, and to provide a design basis for flexibility modifications, a simulation model coupled with boiler and turbine was established, which includes the flue gas and air system, steam and water system, steam turbine, and steam extraction heat recovery system, and the iterative calculation strategy for low load conditions was proposed. The simulation calculation was performed on a 350 MW supercritical coal-fired unit, with the model results showing a high degree of alignment with the unit’s design and operational parameters. Under the condition of 269MW, the maximum calculation error between the model’s predicted exit flue gas temperature of the air preheater and the actual operational results was 8.84%. This discrepancy was due to a sudden increase in the operating flue gas temperature, which may be associated with a blockage in the air preheater. And the simulation results under low load conditions indicate that when the unit load is below 20%, the furnace total airflow is controlled to no less than 30% of the airflow at Maximum Continuous Rating (BMCR) and the minimum feedwater flow rate can be reduced to 20% of that in Turbine Heat Acceptance (THA) load, and the unit switches to wet state operation around 20% load. As the unit load decreases, the coal consumption rate for power generation and steam turbine heat consumption rate both increase significantly. The coal consumption rate for power generation at 30% load is increased by 13.3% compared to BMCR load, and it is increased by 32.5% at 15% load which is operated in wet state. Under low load conditions, the coal consumption rate of the unit can be reduced by decreasing the oxygen content in the flue gas, reducing the minimum feedwater flow rate, and implementing boiler water recirculation.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-05DOI: 10.3389/fenrg.2024.1421519
Dan Gabriel Cacuci
This work presents a representative application of the newly developed “nth-order feature adjoint sensitivity analysis methodology for response-coupled forward/adjoint linear systems” (abbreviated as “nth-FASAM-L”), which enables the most efficient computation of exactly obtained mathematical expressions of arbitrarily high-order (nth-order) sensitivities of a generic system response with respect to all of the parameters (including boundary and initial conditions) underlying the respective forward/adjoint systems. The nth-FASAM-L has been developed to treat responses of linear systems that simultaneously depend on both the forward and adjoint state functions. Such systems cannot be considered particular cases of nonlinear systems, as illustrated in this work by analyzing an analytically solvable model of the energy distribution of the “contributon flux” of neutrons in a mixture of materials. The unparalleled efficiency and accuracy of the nth-FASAM-L stem from the maximal reduction in the number of adjoint computations (which are “large-scale” computations) for determining the exact expressions of arbitrarily high-order sensitivities since the number of large-scale computations when applying the nth-FASAM-N is proportional to the number of model features as opposed to the number of model parameters (which are considerably more than the number of features). Hence, the higher the order of computed sensitivities, the more efficient the nth-FASAM-N becomes compared to any other methodology. Furthermore, as illustrated in this work, the probability of encountering identically vanishing sensitivities is much higher when using the nth-FASAM-L than other methods.
{"title":"nth-order feature adjoint sensitivity analysis methodology for response-coupled forward/adjoint linear systems: II. Illustrative application to a paradigm energy system","authors":"Dan Gabriel Cacuci","doi":"10.3389/fenrg.2024.1421519","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1421519","url":null,"abstract":"This work presents a representative application of the newly developed “n<jats:sup>th</jats:sup>-order feature adjoint sensitivity analysis methodology for response-coupled forward/adjoint linear systems” (abbreviated as “n<jats:sup>th</jats:sup>-FASAM-L”), which enables the most efficient computation of exactly obtained mathematical expressions of arbitrarily high-order (n<jats:sup>th</jats:sup>-order) sensitivities of a generic system response with respect to all of the parameters (including boundary and initial conditions) underlying the respective forward/adjoint systems. The n<jats:sup>th</jats:sup>-FASAM-L has been developed to treat responses of linear systems that simultaneously depend on both the forward and adjoint state functions. Such systems cannot be considered particular cases of nonlinear systems, as illustrated in this work by analyzing an analytically solvable model of the energy distribution of the “contributon flux” of neutrons in a mixture of materials. The unparalleled efficiency and accuracy of the n<jats:sup>th</jats:sup>-FASAM-L stem from the maximal reduction in the number of adjoint computations (which are “large-scale” computations) for determining the exact expressions of arbitrarily high-order sensitivities since the number of large-scale computations when applying the n<jats:sup>th</jats:sup>-FASAM-N is proportional to the number of model features as opposed to the number of model parameters (which are considerably more than the number of features). Hence, the higher the order of computed sensitivities, the more efficient the n<jats:sup>th</jats:sup>-FASAM-N becomes compared to any other methodology. Furthermore, as illustrated in this work, the probability of encountering identically vanishing sensitivities is much higher when using the n<jats:sup>th</jats:sup>-FASAM-L than other methods.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-04DOI: 10.3389/fenrg.2024.1442502
Hasnain Iftikhar, Justyna Zywiołek, Javier Linkolk López-Gonzales, Olayan Albalawi
In today’s world, a country’s economy is one of the most crucial foundations. However, industries’ financial operations depend on their ability to meet their electricity demands. Thus, forecasting electricity consumption is vital for properly planning and managing energy resources. In this context, a new approach based on ensemble learning has been developed to predict monthly electricity consumption. The method divides electricity consumption time series into deterministic and stochastic components. The deterministic component, which consists of a secular long-term trend and an annual seasonality, is estimated using a multiple regression model. In contrast, the stochastic part considers the short-run random fluctuations of the consumption time series. It is forecasted by four different time series, four machine learning models, and three novel proposed ensemble models: the time series homogeneous ensemble model, the machine learning ensemble model, and the heterogeneous ensemble model. The study analyzed data on Pakistan’s monthly electricity consumption from 1991-January to 2022-December. The evaluation of the forecasting models is based on three criteria: accuracy metrics (including the mean absolute percent error (MAPE), the mean absolute error (MAE), the root mean squared error (RMSE), and the root relative squared error (RRSE)); an equality forecast statistical test (the Diebold and Mariano’s test); and a graphical assessment. The heterogeneous ensemble model’s forecasting results show lower error values compared to the homogeneous ensemble models and the singles models, with accuracy metrics measured by MAPE, MAE, RMSE, and RRSE at 5.0027, 460.4800, 614.5276, and 0.2933, respectively. Additionally, the heterogeneous ensemble model is statistically significant (p < 0.05) and superior to the rest of the models. Also, the heterogeneous ensemble model demonstrates considerable performance with the least mean error, which is comparatively better than the individual and best models reported in the literature and are considered baseline models. Further, the forecast values’ monthly behavior depicts that electricity consumption is higher during the summer season, and this demand will be highest in June and July. The forecast model and graph reveal that electricity consumption rapidly increases with time. This indirectly indicates that the government of Pakistan must take adequate steps to improve electricity production through different energy sources to restore the country’s economic status by meeting the country’s electricity demand. Despite several studies conducted from various perspectives, no analysis has been undertaken using an ensemble learning approach to forecast monthly electricity consumption for Pakistan.
{"title":"Electricity consumption forecasting using a novel homogeneous and heterogeneous ensemble learning","authors":"Hasnain Iftikhar, Justyna Zywiołek, Javier Linkolk López-Gonzales, Olayan Albalawi","doi":"10.3389/fenrg.2024.1442502","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1442502","url":null,"abstract":"In today’s world, a country’s economy is one of the most crucial foundations. However, industries’ financial operations depend on their ability to meet their electricity demands. Thus, forecasting electricity consumption is vital for properly planning and managing energy resources. In this context, a new approach based on ensemble learning has been developed to predict monthly electricity consumption. The method divides electricity consumption time series into deterministic and stochastic components. The deterministic component, which consists of a secular long-term trend and an annual seasonality, is estimated using a multiple regression model. In contrast, the stochastic part considers the short-run random fluctuations of the consumption time series. It is forecasted by four different time series, four machine learning models, and three novel proposed ensemble models: the time series homogeneous ensemble model, the machine learning ensemble model, and the heterogeneous ensemble model. The study analyzed data on Pakistan’s monthly electricity consumption from 1991-January to 2022-December. The evaluation of the forecasting models is based on three criteria: accuracy metrics (including the mean absolute percent error (MAPE), the mean absolute error (MAE), the root mean squared error (RMSE), and the root relative squared error (RRSE)); an equality forecast statistical test (the Diebold and Mariano’s test); and a graphical assessment. The heterogeneous ensemble model’s forecasting results show lower error values compared to the homogeneous ensemble models and the singles models, with accuracy metrics measured by MAPE, MAE, RMSE, and RRSE at 5.0027, 460.4800, 614.5276, and 0.2933, respectively. Additionally, the heterogeneous ensemble model is statistically significant (p <jats:inline-formula><mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mo><</mml:mo></mml:math></jats:inline-formula> 0.05) and superior to the rest of the models. Also, the heterogeneous ensemble model demonstrates considerable performance with the least mean error, which is comparatively better than the individual and best models reported in the literature and are considered baseline models. Further, the forecast values’ monthly behavior depicts that electricity consumption is higher during the summer season, and this demand will be highest in June and July. The forecast model and graph reveal that electricity consumption rapidly increases with time. This indirectly indicates that the government of Pakistan must take adequate steps to improve electricity production through different energy sources to restore the country’s economic status by meeting the country’s electricity demand. Despite several studies conducted from various perspectives, no analysis has been undertaken using an ensemble learning approach to forecast monthly electricity consumption for Pakistan.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-04DOI: 10.3389/fenrg.2024.1454398
Kena Chen, Lei Luo, Wei Lei, Pinlei Lv, Liang Zhang
Battery pack provides the backup power supply for DC system of power substations. In the event of an AC power outage or other accidents, it is an important guarantee for the reliable operation of power substation. To prevent possible failures, batteries usually require careful maintenance. Common methods are online monitoring, condition assessments, and health management. Among these, model-based techniques are widely used for battery monitoring and prognostics optimization. Data-driven methods are a good alternative solution when no mathematical models are available. As substations develop towards intelligent and unmanned modes, this paper proposes an online battery monitoring and management system based on the “cloud-network-edge-end” Internet of Things (IoT) architecture. Firstly, advanced battery monitoring system based on IoT architecture is reviewed in depth. It provides basis for later designing. Secondly, the battery online monitoring and management system is designed considering functional requirements and data link. Designing functions include ledger management, basic battery information display, real-time display of battery monitoring data, and the visualization of battery alarm information. It can implement online monitoring and intelligent maintenance management for battery operating status. Finally, the designed and developed system is applied in a 110 kV offshore substation, mainly providing battery maintenance suggestions and fault alarm prompts. Typical results of ledger information management, key parameter monitoring and alarm prompt are presented. This verifies the effectiveness and convenience of IoT-based system for the monitoring and management of batteries.
{"title":"Design and implementation of online battery monitoring and management system based on the internet of things","authors":"Kena Chen, Lei Luo, Wei Lei, Pinlei Lv, Liang Zhang","doi":"10.3389/fenrg.2024.1454398","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1454398","url":null,"abstract":"Battery pack provides the backup power supply for DC system of power substations. In the event of an AC power outage or other accidents, it is an important guarantee for the reliable operation of power substation. To prevent possible failures, batteries usually require careful maintenance. Common methods are online monitoring, condition assessments, and health management. Among these, model-based techniques are widely used for battery monitoring and prognostics optimization. Data-driven methods are a good alternative solution when no mathematical models are available. As substations develop towards intelligent and unmanned modes, this paper proposes an online battery monitoring and management system based on the “cloud-network-edge-end” Internet of Things (IoT) architecture. Firstly, advanced battery monitoring system based on IoT architecture is reviewed in depth. It provides basis for later designing. Secondly, the battery online monitoring and management system is designed considering functional requirements and data link. Designing functions include ledger management, basic battery information display, real-time display of battery monitoring data, and the visualization of battery alarm information. It can implement online monitoring and intelligent maintenance management for battery operating status. Finally, the designed and developed system is applied in a 110 kV offshore substation, mainly providing battery maintenance suggestions and fault alarm prompts. Typical results of ledger information management, key parameter monitoring and alarm prompt are presented. This verifies the effectiveness and convenience of IoT-based system for the monitoring and management of batteries.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Against the backdrop of smart grid development, the electric power system demands higher accuracy and comprehensiveness in fault analysis. Establishing a digital twin platform for multiple equipment faults represents the future direction of power system development. Presently, while many researchers employ artificial intelligence algorithms to diagnose faults in key equipment such as transmission lines and transformers, intelligent diagnostic methods for busbar faults remain insufficient. Therefore, this paper proposes a busbar fault diagnosis method based on multi-source information fusion. Initially, the diagnostic method for busbar faults is explored, conducting both time-domain and frequency-domain analyses on simulated fault data. The data of this model are optimized using Dempster-Shafer evidence theory to enhance algorithm training speed. Subsequently, BP neural network training is implemented. Finally, validation testing of fault data demonstrates a fault recognition accuracy of 99.1% for this method. Experimental results illustrate the method’s feasibility and low computational costs, thereby advancing the development of digital twin platforms for power system fault diagnosis.
在智能电网发展的背景下,电力系统对故障分析的准确性和全面性提出了更高的要求。建立多设备故障数字孪生平台是未来电力系统发展的方向。目前,许多研究人员采用人工智能算法诊断输电线路和变压器等关键设备的故障,但母线故障的智能诊断方法仍然不足。因此,本文提出了一种基于多源信息融合的母线故障诊断方法。首先,探讨了母线故障诊断方法,对模拟故障数据进行了时域和频域分析。利用 Dempster-Shafer 证据理论对该模型的数据进行了优化,以提高算法训练速度。随后,实施了 BP 神经网络训练。最后,故障数据的验证测试表明,该方法的故障识别准确率达到 99.1%。实验结果表明了该方法的可行性和低计算成本,从而推动了用于电力系统故障诊断的数字孪生平台的发展。
{"title":"Busbar fault diagnosis method based on multi-source information fusion","authors":"Xuebao Jiang, Haiou Cao, Chenbin Zhou, Xuchao Ren, Jiaoxiao Shen, Jiayan Yu","doi":"10.3389/fenrg.2024.1443570","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1443570","url":null,"abstract":"Against the backdrop of smart grid development, the electric power system demands higher accuracy and comprehensiveness in fault analysis. Establishing a digital twin platform for multiple equipment faults represents the future direction of power system development. Presently, while many researchers employ artificial intelligence algorithms to diagnose faults in key equipment such as transmission lines and transformers, intelligent diagnostic methods for busbar faults remain insufficient. Therefore, this paper proposes a busbar fault diagnosis method based on multi-source information fusion. Initially, the diagnostic method for busbar faults is explored, conducting both time-domain and frequency-domain analyses on simulated fault data. The data of this model are optimized using Dempster-Shafer evidence theory to enhance algorithm training speed. Subsequently, BP neural network training is implemented. Finally, validation testing of fault data demonstrates a fault recognition accuracy of 99.1% for this method. Experimental results illustrate the method’s feasibility and low computational costs, thereby advancing the development of digital twin platforms for power system fault diagnosis.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the large-scale interconnection of wind power generation, the voltage problem of the power system becomes more and more prominent. Compared with adding external reactive power compensation devices, it is more economical and responsive for fans to adjust their control strategies to provide reactive power support. To make full use of reactive power supported by wind turbines, a mathematical model of doubly fed induction generator (DFIG) wind turbines is constructed to characterize the reactive power boundary of wind turbines. Then, active disturbance rejection control (ADRC) is used to generate a voltage control signal to effectively improve the unit’s reactive response speed; in addition, a variable gain coefficient is used to adjust the reactive power output of the unit, which effectively improves the reactive power response speed and its control adaptability and robustness under changing power grid conditions. Finally, a wind turbine generator (WTG) simulation model is built using MATLAB/Simulink simulation software, different fault locations are perturbed, and the effectiveness of reactive power support of the proposed ADRC-based strategy is simulated and verified. The proposed ADRC-based strategy could inject more reactive power to the grid to improve the voltage.
{"title":"Reactive power regulation strategy for WTGs based on active disturbance rejection control","authors":"Shuilian Xue, Zhilong Yin, Zhiguo Wang, Feng Yu, Hailiang Chen","doi":"10.3389/fenrg.2024.1447094","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1447094","url":null,"abstract":"With the large-scale interconnection of wind power generation, the voltage problem of the power system becomes more and more prominent. Compared with adding external reactive power compensation devices, it is more economical and responsive for fans to adjust their control strategies to provide reactive power support. To make full use of reactive power supported by wind turbines, a mathematical model of doubly fed induction generator (DFIG) wind turbines is constructed to characterize the reactive power boundary of wind turbines. Then, active disturbance rejection control (ADRC) is used to generate a voltage control signal to effectively improve the unit’s reactive response speed; in addition, a variable gain coefficient is used to adjust the reactive power output of the unit, which effectively improves the reactive power response speed and its control adaptability and robustness under changing power grid conditions. Finally, a wind turbine generator (WTG) simulation model is built using MATLAB/Simulink simulation software, different fault locations are perturbed, and the effectiveness of reactive power support of the proposed ADRC-based strategy is simulated and verified. The proposed ADRC-based strategy could inject more reactive power to the grid to improve the voltage.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}