Pub Date : 2024-08-29DOI: 10.3389/fenrg.2024.1428458
Subhojit Dawn, Shreya Shree Das, M. Ramesh, G. Seshadri, Sai Ram Inkollu, Thandava Krishna Sai Pandraju, Umit Cali, Taha Selim Ustun
The depletion of conventional energy sources has led to an increase in interest in renewable energy across the globe. The usage of renewable energy has lowered economic risk in the electricity markets. This study presents an approach to utilize solar photovoltaic as a renewable energy source, fuel cells as the energy storage system, and Flexible AC Transmission networks (FACTS) to reduce system risk in deregulated networks. The difference between real and expected renewable energy data is the primary cause of disequilibrium pricing (DP) in the renewable energy-integrated system. Integration of the FCs with a Unified Power Flow Controller (UPFC) can play an important role in coping with the disequilibrium pricing, emphasizing optimizing profitability and societal welfare in a deregulated environment. The paper also evaluates the system voltage outline and LBMP (location-based marginal pricing) scenarios, both with and without the integration of solar power. Two distinct factors, i.e., Bus Sensitivity Index (BSI) and Line Congestion Factor (LCF), have been proposed to identify the key buses and lines for solar power and Unified Power Flow Controller installation in the system. The study also employs conditional-value-at-risk (CVaR) and value-at-risk (VaR) to assess the system’s risk. Using a real-time IEEE 39-bus New England system, multiple optimization algorithms including Sequential Quadratic Programming and the Slime Mould Algorithm (SMA) are employed to estimate the financial risk of the considered system. This analysis demonstrates that the risk coefficient values improve with the placement of UPFC and fuel cells in the renewable incorporated system.
{"title":"Risk alleviation and social welfare maximization by the placement of fuel cell and UPFC in a renewable integrated system","authors":"Subhojit Dawn, Shreya Shree Das, M. Ramesh, G. Seshadri, Sai Ram Inkollu, Thandava Krishna Sai Pandraju, Umit Cali, Taha Selim Ustun","doi":"10.3389/fenrg.2024.1428458","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1428458","url":null,"abstract":"The depletion of conventional energy sources has led to an increase in interest in renewable energy across the globe. The usage of renewable energy has lowered economic risk in the electricity markets. This study presents an approach to utilize solar photovoltaic as a renewable energy source, fuel cells as the energy storage system, and Flexible AC Transmission networks (FACTS) to reduce system risk in deregulated networks. The difference between real and expected renewable energy data is the primary cause of disequilibrium pricing (DP) in the renewable energy-integrated system. Integration of the FCs with a Unified Power Flow Controller (UPFC) can play an important role in coping with the disequilibrium pricing, emphasizing optimizing profitability and societal welfare in a deregulated environment. The paper also evaluates the system voltage outline and LBMP (location-based marginal pricing) scenarios, both with and without the integration of solar power. Two distinct factors, i.e., Bus Sensitivity Index (BSI) and Line Congestion Factor (LCF), have been proposed to identify the key buses and lines for solar power and Unified Power Flow Controller installation in the system. The study also employs conditional-value-at-risk (CVaR) and value-at-risk (VaR) to assess the system’s risk. Using a real-time IEEE 39-bus New England system, multiple optimization algorithms including Sequential Quadratic Programming and the Slime Mould Algorithm (SMA) are employed to estimate the financial risk of the considered system. This analysis demonstrates that the risk coefficient values improve with the placement of UPFC and fuel cells in the renewable incorporated system.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215111","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 : 2024-08-29DOI: 10.3389/fenrg.2024.1364445
Jiayong Zhong, Yongtao Chen, Jin Gao, Xiaohong Lv
In today’s era of rapid technological advancement, the emergence of drone technology and intelligent power systems has brought tremendous convenience to society. However, the challenges associated with drone image recognition and intelligent grid device fault detection are becoming increasingly significant. In practical applications, the rapid and accurate identification of drone images and the timely detection of faults in intelligent grid devices are crucial for ensuring aviation safety and the stable operation of power systems. This article aims to integrate Transformer models, transfer learning, and generative adversarial networks to enhance the accuracy and efficiency of drone image recognition and intelligent grid device fault detection.In the methodology section, we first employ the Transformer model, a deep learning model based on self-attention mechanisms that has demonstrated excellent performance in handling image sequences, capturing complex spatial relationships in images. To address limited data issues, we introduce transfer learning, accelerating the learning process in the target domain by training the model on a source domain. To further enhance the model’s robustness and generalization capability, we incorporate generative adversarial networks to generate more representative training samples.In the experimental section, we validate our model using a large dataset of real drone images and intelligent grid device fault data. Our model shows significant improvements in metrics such as specificity, accuracy, recall, and F1-score. Specifically, in the experimental data, we observe a notable advantage of our model over traditional methods in both drone image recognition and intelligent grid device fault detection. Particularly in the detection of intelligent grid device faults, our model successfully captures subtle fault features, achieving an accuracy of over 90%, an improvement of more than 17% compared to traditional methods, and an outstanding F1-score of around 91%.In summary, this article achieves a significant improvement in the fields of drone image recognition and intelligent grid device fault detection by cleverly integrating Transformer models, transfer learning, and generative adversarial networks. Our approach not only holds broad theoretical application prospects but also receives robust support from experimental data, providing strong support for research and applications in related fields.
{"title":"Drone image recognition and intelligent power distribution network equipment fault detection based on the transformer model and transfer learning","authors":"Jiayong Zhong, Yongtao Chen, Jin Gao, Xiaohong Lv","doi":"10.3389/fenrg.2024.1364445","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1364445","url":null,"abstract":"In today’s era of rapid technological advancement, the emergence of drone technology and intelligent power systems has brought tremendous convenience to society. However, the challenges associated with drone image recognition and intelligent grid device fault detection are becoming increasingly significant. In practical applications, the rapid and accurate identification of drone images and the timely detection of faults in intelligent grid devices are crucial for ensuring aviation safety and the stable operation of power systems. This article aims to integrate Transformer models, transfer learning, and generative adversarial networks to enhance the accuracy and efficiency of drone image recognition and intelligent grid device fault detection.In the methodology section, we first employ the Transformer model, a deep learning model based on self-attention mechanisms that has demonstrated excellent performance in handling image sequences, capturing complex spatial relationships in images. To address limited data issues, we introduce transfer learning, accelerating the learning process in the target domain by training the model on a source domain. To further enhance the model’s robustness and generalization capability, we incorporate generative adversarial networks to generate more representative training samples.In the experimental section, we validate our model using a large dataset of real drone images and intelligent grid device fault data. Our model shows significant improvements in metrics such as specificity, accuracy, recall, and F1-score. Specifically, in the experimental data, we observe a notable advantage of our model over traditional methods in both drone image recognition and intelligent grid device fault detection. Particularly in the detection of intelligent grid device faults, our model successfully captures subtle fault features, achieving an accuracy of over 90%, an improvement of more than 17% compared to traditional methods, and an outstanding F1-score of around 91%.In summary, this article achieves a significant improvement in the fields of drone image recognition and intelligent grid device fault detection by cleverly integrating Transformer models, transfer learning, and generative adversarial networks. Our approach not only holds broad theoretical application prospects but also receives robust support from experimental data, providing strong support for research and applications in related fields.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215107","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 : 2024-08-29DOI: 10.3389/fenrg.2024.1442185
Ruifeng Wang, Mingchuan Shi, Ke Zhu, Jun Yu, Wei Ren, Guohong Yan, Zhiqiang Yin, Shujie Gao
The Double U-pipe ground heat exchanger, known for its simple process, cost-effectiveness, high heat exchange efficiency, and low thermal resistance, remains the predominant type of ground heat exchanger in today’s shallow geothermal energy development and utilization. In recent years, significant research has focused on the factors influencing heat transfer and the heat exchange performance of Double U-pipe ground heat exchangers through experimental testing methods. However, studies that integrate numerical simulation with in situ testing have been less common. Utilizing the cylindrical heat source model theory and the results of regional in situ thermal response tests, this paper develops a Double U-pipe ground heat transfer model by establishing physical, mathematical, and heat transfer geometric models. It evaluates the effects of varying inlet temperatures, flow rates, and initial ground temperatures on heat exchange efficiency under heating conditions. The results confirm the accuracy of the Double U-pipe ground heat exchanger model based on in situ testing. They indicate that increasing the temperature differential between the inlet and initial temperatures, raising the initial ground temperature, and moderately enhancing the flow rate can improve the system’s heat exchange efficiency.
双 U 管地热交换器以其工艺简单、成本效益高、热交换效率高、热阻小而著称,仍是当今浅层地热能开发利用中最主要的地热交换器类型。近年来,通过实验测试方法对双 U 型管地热交换器的传热影响因素和热交换性能进行了大量研究。然而,将数值模拟与现场测试相结合的研究却并不多见。本文利用圆柱热源模型理论和区域原位热响应测试结果,通过建立物理、数学和传热几何模型,开发了双 U 型管地面传热模型。它评估了在供暖条件下,不同的入口温度、流速和初始地温对热交换效率的影响。结果证实了基于现场测试的双 U 型管地热交换器模型的准确性。结果表明,增大入口温度与初始温度之间的温差、提高初始地温以及适度提高流速可以提高系统的热交换效率。
{"title":"Research on the heat transfer model of double U-pipe ground heat exchanger based on in-situ testing","authors":"Ruifeng Wang, Mingchuan Shi, Ke Zhu, Jun Yu, Wei Ren, Guohong Yan, Zhiqiang Yin, Shujie Gao","doi":"10.3389/fenrg.2024.1442185","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1442185","url":null,"abstract":"The Double U-pipe ground heat exchanger, known for its simple process, cost-effectiveness, high heat exchange efficiency, and low thermal resistance, remains the predominant type of ground heat exchanger in today’s shallow geothermal energy development and utilization. In recent years, significant research has focused on the factors influencing heat transfer and the heat exchange performance of Double U-pipe ground heat exchangers through experimental testing methods. However, studies that integrate numerical simulation with <jats:italic>in situ</jats:italic> testing have been less common. Utilizing the cylindrical heat source model theory and the results of regional <jats:italic>in situ</jats:italic> thermal response tests, this paper develops a Double U-pipe ground heat transfer model by establishing physical, mathematical, and heat transfer geometric models. It evaluates the effects of varying inlet temperatures, flow rates, and initial ground temperatures on heat exchange efficiency under heating conditions. The results confirm the accuracy of the Double U-pipe ground heat exchanger model based on <jats:italic>in situ</jats:italic> testing. They indicate that increasing the temperature differential between the inlet and initial temperatures, raising the initial ground temperature, and moderately enhancing the flow rate can improve the system’s heat exchange efficiency.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215104","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 : 2024-08-29DOI: 10.3389/fenrg.2024.1427587
Yueguang Zhou, Xiuxiang Fan
The wind energy industry is witnessing a new era of extraordinary growth as the demand for renewable energy continues to grow. However, accurately predicting wind speed remains a significant challenge due to its high fluctuation and randomness. These difficulties hinder effective wind farm management and integration into the power grid. To address this issue, we propose the MRGS-LSTM model to improve the accuracy and reliability of wind speed prediction results, which considers the complex spatio-temporal correlations between features at multiple sites. First, mRMR-RF filters the input multidimensional meteorological variables and computes the feature subset with minimum information redundancy. Second, the feature map topology is constructed by quantifying the spatial distance distribution of the multiple sites and the maximum mutual information coefficient among the features. On this basis, the GraphSAGE framework is used to sample and aggregate the feature information of neighboring sites to extract spatial feature vectors. Then, the spatial feature vectors are input into the long short-term memory (LSTM) model after sliding window sampling. The LSTM model learns the temporal features of wind speed data to output the predicted results of the spatio-temporal correlation at each site. Finally, through the simulation experiments based on real historical data from the Roscoe Wind Farm in Texas, United States, we prove that our model MRGS-LSTM improves the performance of MAE by 15.43%–27.97% and RMSE by 12.57%–25.40% compared with other models of the same type. The experimental results verify the validity and superiority of our proposed model and provide a more reliable basis for the scheduling and optimization of wind farms.
{"title":"MRGS-LSTM: a novel multi-site wind speed prediction approach with spatio-temporal correlation","authors":"Yueguang Zhou, Xiuxiang Fan","doi":"10.3389/fenrg.2024.1427587","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1427587","url":null,"abstract":"The wind energy industry is witnessing a new era of extraordinary growth as the demand for renewable energy continues to grow. However, accurately predicting wind speed remains a significant challenge due to its high fluctuation and randomness. These difficulties hinder effective wind farm management and integration into the power grid. To address this issue, we propose the MRGS-LSTM model to improve the accuracy and reliability of wind speed prediction results, which considers the complex spatio-temporal correlations between features at multiple sites. First, mRMR-RF filters the input multidimensional meteorological variables and computes the feature subset with minimum information redundancy. Second, the feature map topology is constructed by quantifying the spatial distance distribution of the multiple sites and the maximum mutual information coefficient among the features. On this basis, the GraphSAGE framework is used to sample and aggregate the feature information of neighboring sites to extract spatial feature vectors. Then, the spatial feature vectors are input into the long short-term memory (LSTM) model after sliding window sampling. The LSTM model learns the temporal features of wind speed data to output the predicted results of the spatio-temporal correlation at each site. Finally, through the simulation experiments based on real historical data from the Roscoe Wind Farm in Texas, United States, we prove that our model MRGS-LSTM improves the performance of MAE by 15.43%–27.97% and RMSE by 12.57%–25.40% compared with other models of the same type. The experimental results verify the validity and superiority of our proposed model and provide a more reliable basis for the scheduling and optimization of wind farms.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215105","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}
IntroductionWhen a distributed photovoltaic (PV) system has access to a large urban distribution network, the active balance is primarily borne by the main network gas unit; when the scale of the distributed PV system is very large, the main network can only provide limited regulation capacity, and the distribution network must determine the active optimal scheduling strategy.MethodsThis work proposes an active optimization scheduling model for the distribution network by considering the regulation capacity of the main network. In terms of the optimisation objectives, the maximum consumption of the distributed PVs and minimum power fluctuation at the demarcation point of the main distribution network are proposed as the main objectives, while the minimum total exchanged power in a cycle at the main distribution demarcation point and minimum distribution network loss are considered as the secondary objectives. In terms of constraints, it is proposed that the main network’s regulation capacity be characterized by the main network’s gas-fired unit creep constraints. A fast solution method for active optimization of the distribution network is designed herein to formulate the priority control order of the adjustable units according to the dispatch economic performances of various types of adjustable resources in the distribution network; this reduces the number of variables involved in the optimization at each step and improves the optimized solution speed.ResultsFinally, Simulation verification by IEEE 33-node distribution network arithmetic example based on Matlab simulation platform.DiscussionSimulation results show the effectiveness of the method in achieving maximum PV consumption and reflecting the limited regulation capacity of the main grid.
{"title":"Active power optimisation scheduling method for large-scale urban distribution networks with distributed photovoltaics considering the regulating capacity of the main network","authors":"Cheng Gong, Wei Wang, Wenhan Zhang, Nan Dong, Xuquan Liu, Yechun Dong, Dongying Zhang","doi":"10.3389/fenrg.2024.1450986","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1450986","url":null,"abstract":"IntroductionWhen a distributed photovoltaic (PV) system has access to a large urban distribution network, the active balance is primarily borne by the main network gas unit; when the scale of the distributed PV system is very large, the main network can only provide limited regulation capacity, and the distribution network must determine the active optimal scheduling strategy.MethodsThis work proposes an active optimization scheduling model for the distribution network by considering the regulation capacity of the main network. In terms of the optimisation objectives, the maximum consumption of the distributed PVs and minimum power fluctuation at the demarcation point of the main distribution network are proposed as the main objectives, while the minimum total exchanged power in a cycle at the main distribution demarcation point and minimum distribution network loss are considered as the secondary objectives. In terms of constraints, it is proposed that the main network’s regulation capacity be characterized by the main network’s gas-fired unit creep constraints. A fast solution method for active optimization of the distribution network is designed herein to formulate the priority control order of the adjustable units according to the dispatch economic performances of various types of adjustable resources in the distribution network; this reduces the number of variables involved in the optimization at each step and improves the optimized solution speed.ResultsFinally, Simulation verification by IEEE 33-node distribution network arithmetic example based on Matlab simulation platform.DiscussionSimulation results show the effectiveness of the method in achieving maximum PV consumption and reflecting the limited regulation capacity of the main grid.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215106","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}
This work presents a system design for extracting maximum power using the modified maximum power point tracking (MPPT) technique and a novel high-gain DC-DC converter, which was then used to supply a microgrid system with a conventional buck converter. We present a novel structure comprising the MPPT, voltage boosting, and voltage regulating components for a DC microgrid in a single system. The most important features of a photovoltaic (PV) system include a high-gain converter and maximum PV power extraction; considering these, we present a high-gain DC-DC converter that boosts the output voltage to ten times the input voltage. Furthermore, the MPPT technique extracts maximum power from the PV panel based on model predictive control through its better transient response than the conventional incremental conductance method. The MPPT approach was tested with both fixed- and variable-step operations, and the results were compared for load variations. Considering the economics of the system, the proposed approach attempts cost reduction by optimizing the number of sensors to two instead of three. Simulations were conducted under different environmental conditions using MATLAB-Simulink, and the performance differences between the conventional incremental conductance and proposed MPPT-based methods are shown. Next, DC voltage regulation was implemented for the proposed PV and existing systems by considering different load and irradiation conditions while maintaining constant temperature. The simulation results showed the latter system had better performance than the former under different environmental conditions, with persistent results for voltage regulation at different load and irradiation conditions.
{"title":"A model predictive control based MPPT technique for novel DC-DC converter and voltage regulation in DC microgrid","authors":"Kunte Abhijit Bhagwan, Udaya Bhasker Manthati, Faisal Alsaif","doi":"10.3389/fenrg.2024.1471499","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1471499","url":null,"abstract":"This work presents a system design for extracting maximum power using the modified maximum power point tracking (MPPT) technique and a novel high-gain DC-DC converter, which was then used to supply a microgrid system with a conventional buck converter. We present a novel structure comprising the MPPT, voltage boosting, and voltage regulating components for a DC microgrid in a single system. The most important features of a photovoltaic (PV) system include a high-gain converter and maximum PV power extraction; considering these, we present a high-gain DC-DC converter that boosts the output voltage to ten times the input voltage. Furthermore, the MPPT technique extracts maximum power from the PV panel based on model predictive control through its better transient response than the conventional incremental conductance method. The MPPT approach was tested with both fixed- and variable-step operations, and the results were compared for load variations. Considering the economics of the system, the proposed approach attempts cost reduction by optimizing the number of sensors to two instead of three. Simulations were conducted under different environmental conditions using MATLAB-Simulink, and the performance differences between the conventional incremental conductance and proposed MPPT-based methods are shown. Next, DC voltage regulation was implemented for the proposed PV and existing systems by considering different load and irradiation conditions while maintaining constant temperature. The simulation results showed the latter system had better performance than the former under different environmental conditions, with persistent results for voltage regulation at different load and irradiation conditions.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215110","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 : 2024-08-29DOI: 10.3389/fenrg.2024.1353312
Juanjuan Yang
IntroductionIn the context of energy resource scarcity and environmental pressures, accurately forecasting energy consumption and optimizing financial strategies in smart grids are crucial. The high dimensionality and dynamic nature of the data present significant challenges, hindering accurate prediction and strategy optimization.MethodsThis paper proposes a fusion algorithm for smart grid enterprise decision-making and economic benefit analysis, aiming to enhance decision-making accuracy and predictive capability. The method combines deep reinforcement learning (DRL), long short-term memory (LSTM) networks, and the Transformer algorithm. LSTM is utilized to process and analyze time series data, capturing historical patterns of energy prices and usage. Subsequently, DRL and the Transformer algorithm are employed to further analyze the data, enabling the formulation and optimization of energy purchasing and usage strategies.ResultsExperimental results demonstrate that the proposed approach outperforms traditional methods in improving energy cost prediction accuracy and optimizing financial strategies. Notably, on the EIA Dataset, the proposed algorithm achieves a reduction of over 48.5% in FLOP, a decrease in inference time by over 49.8%, and an improvement of 38.6% in MAPE.DiscussionThis research provides a new perspective and tool for energy management in smart grids. It offers valuable insights for handling other high-dimensional and dynamically changing data processing and decision optimization problems. The significant improvements in prediction accuracy and strategy optimization highlight the potential for widespread application in the energy sector and beyond.
{"title":"Energy cost forecasting and financial strategy optimization in smart grids via ensemble algorithm","authors":"Juanjuan Yang","doi":"10.3389/fenrg.2024.1353312","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1353312","url":null,"abstract":"IntroductionIn the context of energy resource scarcity and environmental pressures, accurately forecasting energy consumption and optimizing financial strategies in smart grids are crucial. The high dimensionality and dynamic nature of the data present significant challenges, hindering accurate prediction and strategy optimization.MethodsThis paper proposes a fusion algorithm for smart grid enterprise decision-making and economic benefit analysis, aiming to enhance decision-making accuracy and predictive capability. The method combines deep reinforcement learning (DRL), long short-term memory (LSTM) networks, and the Transformer algorithm. LSTM is utilized to process and analyze time series data, capturing historical patterns of energy prices and usage. Subsequently, DRL and the Transformer algorithm are employed to further analyze the data, enabling the formulation and optimization of energy purchasing and usage strategies.ResultsExperimental results demonstrate that the proposed approach outperforms traditional methods in improving energy cost prediction accuracy and optimizing financial strategies. Notably, on the EIA Dataset, the proposed algorithm achieves a reduction of over 48.5% in FLOP, a decrease in inference time by over 49.8%, and an improvement of 38.6% in MAPE.DiscussionThis research provides a new perspective and tool for energy management in smart grids. It offers valuable insights for handling other high-dimensional and dynamically changing data processing and decision optimization problems. The significant improvements in prediction accuracy and strategy optimization highlight the potential for widespread application in the energy sector and beyond.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215108","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}
Under the dual-carbon target, hydrogen energy, as a zero-carbon secondary energy source, has great scope for replacing fossil feedstocks in the fields of energy, transportation and industry. However, the current research on the competitiveness of hydrogen energy in various fields is not sufficiently addressed. In this paper, we use the LEAP model to predict the future scale of hydrogen use and the two-factor learning curve to predict the trend of hydrogen price change from 2025 to 2050, using Qinghai Province as the research background. At the same time, considering the carbon emission reduction benefits and raw material costs, the competitiveness of hydrogen energy in energy, transportation, industry and other fields in the future is compared. The results show that: 1) The hydrogen load scale in Qinghai Province will grow fast from 2025 to 2030. From 2030 to 2040, it slows under the steady and basic scenarios but remains high under the accelerated one. By 2040, the consumption scales are 1.057 million, 649,000 and 442,000 tons respectively. 2) The price of hydrogen energy will drop rapidly from the current 28 CNY/kg to about 20 CNY/kg in the next 5 years. By 2040, the price of hydrogen energy will be reduced to about 17 CNY/kg. 3) In terms of hydrogen energy competitiveness, when carbon emissions are not taken into account, hydrogen energy is currently competitive in the transportation field. During 2032–2038, it will be competitive in the field of methanol synthesis. By 2040, hydrogen energy will not be competitive in the fields of ammonia synthesis and power/heating. When considering carbon emissions, the competitiveness of hydrogen energy in the transportation field will become greater. The competitive year in the field of methanol synthesis will be 1–2 years ahead. By 2040, it will not be competitive in the field of synthetic ammonia and power/heating, but the gap will be significantly reduced due to the consideration of carbon emissions.
{"title":"Prediction of hydrogen consumption scale and hydrogen price based on LEAP model and two-factor learning curve","authors":"Hongxia Li, Haiguo Yu, Haiting Wang, Xiaokan Gou, Fei Liu, Lixin Li, Qian Wang, Xin Zhang, Yuanyuan Li","doi":"10.3389/fenrg.2024.1450966","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1450966","url":null,"abstract":"Under the dual-carbon target, hydrogen energy, as a zero-carbon secondary energy source, has great scope for replacing fossil feedstocks in the fields of energy, transportation and industry. However, the current research on the competitiveness of hydrogen energy in various fields is not sufficiently addressed. In this paper, we use the LEAP model to predict the future scale of hydrogen use and the two-factor learning curve to predict the trend of hydrogen price change from 2025 to 2050, using Qinghai Province as the research background. At the same time, considering the carbon emission reduction benefits and raw material costs, the competitiveness of hydrogen energy in energy, transportation, industry and other fields in the future is compared. The results show that: 1) The hydrogen load scale in Qinghai Province will grow fast from 2025 to 2030. From 2030 to 2040, it slows under the steady and basic scenarios but remains high under the accelerated one. By 2040, the consumption scales are 1.057 million, 649,000 and 442,000 tons respectively. 2) The price of hydrogen energy will drop rapidly from the current 28 CNY/kg to about 20 CNY/kg in the next 5 years. By 2040, the price of hydrogen energy will be reduced to about 17 CNY/kg. 3) In terms of hydrogen energy competitiveness, when carbon emissions are not taken into account, hydrogen energy is currently competitive in the transportation field. During 2032–2038, it will be competitive in the field of methanol synthesis. By 2040, hydrogen energy will not be competitive in the fields of ammonia synthesis and power/heating. When considering carbon emissions, the competitiveness of hydrogen energy in the transportation field will become greater. The competitive year in the field of methanol synthesis will be 1–2 years ahead. By 2040, it will not be competitive in the field of synthetic ammonia and power/heating, but the gap will be significantly reduced due to the consideration of carbon emissions.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215113","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 : 2024-08-28DOI: 10.3389/fenrg.2024.1438961
Yongbiao Yang, Dengxin Ai, Li Zhang, Yawen Zheng
When multiple CCHP microgrids are integrated into an active distribution network (ADN), the microgrids and the distribution network serve as distinct stakeholders, making the economic optimal dispatch of the system more complex. This paper proposes a distributed dispatch model of ADN with CCHP multi-microgrid, and refines the objective functions of each region. The analytical target cascading approach (ATC) is employed to model the power transaction as virtual sources/loads, and solve the optimal dispatch in parallel. Case studies demonstrate the proposed distributed model is capable of achieving economic optimization for both stakeholders.
{"title":"Economic optimal dispatch of active distribution network with CCHP multi-microgrid based on analytical target cascading","authors":"Yongbiao Yang, Dengxin Ai, Li Zhang, Yawen Zheng","doi":"10.3389/fenrg.2024.1438961","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1438961","url":null,"abstract":"When multiple CCHP microgrids are integrated into an active distribution network (ADN), the microgrids and the distribution network serve as distinct stakeholders, making the economic optimal dispatch of the system more complex. This paper proposes a distributed dispatch model of ADN with CCHP multi-microgrid, and refines the objective functions of each region. The analytical target cascading approach (ATC) is employed to model the power transaction as virtual sources/loads, and solve the optimal dispatch in parallel. Case studies demonstrate the proposed distributed model is capable of achieving economic optimization for both stakeholders.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215115","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 reliability of the power supply for 5G base stations (BSs) is increasing. A large amount of BS backup energy storage (BES) remains underutilized. This study establishes a double-layer optimization distribution network (DN) considering BS clusters. An energy consumption characteristics and scheduling ability model of the BSs was established to address the differences in the characteristics of different traffic flows. A double-tier planning model for BS-joining grid market ancillary services is proposed. The upper-layer model addresses optimal tidal flow problems in DNs to minimize integrated operating costs, while the lower-layer model focuses on BES economic optimization. The double-layer model changes into a single-layer linear model using the Karush–Kuhn–Tucker (KKT) condition and the Big M method. Simulation validation using the IEEE-33 node DN proves that this approach can reduce DN operating costs, regulate voltage fluctuations, and guarantee economical and safe DN operation.
5G 基站(BS)的供电可靠性要求越来越高。大量基站备用储能(BES)仍未得到充分利用。本研究建立了一个考虑到 BS 集群的双层优化配电网络(DN)。针对不同流量特征的差异,建立了 BS 的能耗特征和调度能力模型。提出了 BS 加入电网市场辅助服务的双层规划模型。上层模型解决 DNs 的最优潮流问题,以最小化综合运营成本,而下层模型则侧重于 BES 的经济优化。利用 Karush-Kuhn-Tucker (KKT) 条件和 Big M 方法,双层模型变为单层线性模型。利用 IEEE-33 节点 DN 进行的仿真验证证明,这种方法可以降低 DN 运行成本,调节电压波动,并保证 DN 运行的经济性和安全性。
{"title":"A double-layer optimization strategy for distribution networks considering 5G base station clusters","authors":"Zhipeng Lv, Bingjian Jia, Zhenhao Song, Fei Yang, Shan Zhou","doi":"10.3389/fenrg.2024.1454382","DOIUrl":"https://doi.org/10.3389/fenrg.2024.1454382","url":null,"abstract":"The reliability of the power supply for 5G base stations (BSs) is increasing. A large amount of BS backup energy storage (BES) remains underutilized. This study establishes a double-layer optimization distribution network (DN) considering BS clusters. An energy consumption characteristics and scheduling ability model of the BSs was established to address the differences in the characteristics of different traffic flows. A double-tier planning model for BS-joining grid market ancillary services is proposed. The upper-layer model addresses optimal tidal flow problems in DNs to minimize integrated operating costs, while the lower-layer model focuses on BES economic optimization. The double-layer model changes into a single-layer linear model using the Karush–Kuhn–Tucker (KKT) condition and the Big M method. Simulation validation using the IEEE-33 node DN proves that this approach can reduce DN operating costs, regulate voltage fluctuations, and guarantee economical and safe DN operation.","PeriodicalId":12428,"journal":{"name":"Frontiers in Energy Research","volume":null,"pages":null},"PeriodicalIF":3.4,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142215117","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}