Pub Date : 2022-11-07DOI: 10.1109/IGESSC55810.2022.9955323
A. Leedy, Muhammad Abdelraziq, Kristen Booth
In this paper, a step-by-step solution procedure used to estimate the single-diode model parameters is proposed. The procedure is a combination of least-squares, Newtonian, and quasi- Newtonian numerical methods. Current and voltage measurements are acquired from a conventional 36-cell photovoltaic (PV) module manufactured by AMERESCO Solar. The single-diode equation was then fit to the acquired data in the least-squares sense. The developed least-squares equation is solved by two different numerical methods, the Newton-Raphson (NR) method, and Broyden’s method. Since there are five different parameters to be determined, a system of five nonlinear equations was developed and solved. The main distinction between the NR and Broyden’s algorithms is the way they handle the Jacobian matrix. The NR algorithm requires the computation of a new Jacobian matrix at every iteration. Broyden’s algorithm only requires an initial Jacobian, and then the Jacobian is updated iteratively by means of a correction formula. The functionality of the two algorithms is compared, and the five parameters extracted from each algorithm are used to simulate a 36-cell PV module. The simulation results are compared to experimental data to provide validation and to determine how accurate each procedure was in estimating the model parameters.
{"title":"A Comparison of Numerical Techniques used for PV Module Model Parameter Extraction","authors":"A. Leedy, Muhammad Abdelraziq, Kristen Booth","doi":"10.1109/IGESSC55810.2022.9955323","DOIUrl":"https://doi.org/10.1109/IGESSC55810.2022.9955323","url":null,"abstract":"In this paper, a step-by-step solution procedure used to estimate the single-diode model parameters is proposed. The procedure is a combination of least-squares, Newtonian, and quasi- Newtonian numerical methods. Current and voltage measurements are acquired from a conventional 36-cell photovoltaic (PV) module manufactured by AMERESCO Solar. The single-diode equation was then fit to the acquired data in the least-squares sense. The developed least-squares equation is solved by two different numerical methods, the Newton-Raphson (NR) method, and Broyden’s method. Since there are five different parameters to be determined, a system of five nonlinear equations was developed and solved. The main distinction between the NR and Broyden’s algorithms is the way they handle the Jacobian matrix. The NR algorithm requires the computation of a new Jacobian matrix at every iteration. Broyden’s algorithm only requires an initial Jacobian, and then the Jacobian is updated iteratively by means of a correction formula. The functionality of the two algorithms is compared, and the five parameters extracted from each algorithm are used to simulate a 36-cell PV module. The simulation results are compared to experimental data to provide validation and to determine how accurate each procedure was in estimating the model parameters.","PeriodicalId":166147,"journal":{"name":"2022 IEEE Green Energy and Smart System Systems(IGESSC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126329578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/IGESSC55810.2022.9955335
Loai Al-Adim, Mehrdad Aliasgari, M. Mozumdar, Saleh Al Jufout
This paper investigates the effect of Medium-Voltage (MV) capacitor banks on the number of central inverters of grid-connected Photovoltaic (PV) plants. All generators including renewable energy sources must meet the Intermit Renewable Resource (IRR)–Transmission Interconnection Code (TIC). To comply with this code, the number of central inverters of the grid-connected PV plant must be increased, which leads to additional costs. In this paper, three cases of a 200-MW gridconnected PV plant were investigated. These cases are with and without increasing the number of the central inverters; while the third case is by adding MV capacitor banks to meet the grid code requirements. In this paper, calculations have been performed using ETAP software for all cases. The P-Q capability curves have been discussed for all cases.
{"title":"Reducing the Number of Central Inverters of a Photovoltaic Plant Using Medium-Voltage Capacitor Banks","authors":"Loai Al-Adim, Mehrdad Aliasgari, M. Mozumdar, Saleh Al Jufout","doi":"10.1109/IGESSC55810.2022.9955335","DOIUrl":"https://doi.org/10.1109/IGESSC55810.2022.9955335","url":null,"abstract":"This paper investigates the effect of Medium-Voltage (MV) capacitor banks on the number of central inverters of grid-connected Photovoltaic (PV) plants. All generators including renewable energy sources must meet the Intermit Renewable Resource (IRR)–Transmission Interconnection Code (TIC). To comply with this code, the number of central inverters of the grid-connected PV plant must be increased, which leads to additional costs. In this paper, three cases of a 200-MW gridconnected PV plant were investigated. These cases are with and without increasing the number of the central inverters; while the third case is by adding MV capacitor banks to meet the grid code requirements. In this paper, calculations have been performed using ETAP software for all cases. The P-Q capability curves have been discussed for all cases.","PeriodicalId":166147,"journal":{"name":"2022 IEEE Green Energy and Smart System Systems(IGESSC)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129910497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/IGESSC55810.2022.9955328
Farshina Nazrul Shimim, Bradley M. Whitaker
Scheduling or day-ahead planning improves the efficiency of a process and often leads to other advantages such as energy savings and increased revenue. However, most real-world scheduling problems are very complicated and are usually affected by several external parameters. Hence, finding the best schedule given a set of jobs requires extensive calculations that increase exponentially with the number of jobs. Traditional schedulers are, at times, unable to address uncertainties in the system. This paper proposes a Reinforcement Learning approach for solving the Job Scheduling Problem in a dynamic environment with an aim to minimize the peak instantaneous electricity consumption. The training instance is randomly reset after a certain period and the solver uses online training to adapt to the new environment. Simulation results show that both the proposed approach and a Genetic Algorithm-based approach achieve the minimum peak power consumption possible, which is 58% less than on-demand dispatch. Also, for 82.2% of the simulations, our method finds a better schedule than its initialization.
{"title":"A Reinforcement Learning Approach to the Dynamic Job Scheduling Problem","authors":"Farshina Nazrul Shimim, Bradley M. Whitaker","doi":"10.1109/IGESSC55810.2022.9955328","DOIUrl":"https://doi.org/10.1109/IGESSC55810.2022.9955328","url":null,"abstract":"Scheduling or day-ahead planning improves the efficiency of a process and often leads to other advantages such as energy savings and increased revenue. However, most real-world scheduling problems are very complicated and are usually affected by several external parameters. Hence, finding the best schedule given a set of jobs requires extensive calculations that increase exponentially with the number of jobs. Traditional schedulers are, at times, unable to address uncertainties in the system. This paper proposes a Reinforcement Learning approach for solving the Job Scheduling Problem in a dynamic environment with an aim to minimize the peak instantaneous electricity consumption. The training instance is randomly reset after a certain period and the solver uses online training to adapt to the new environment. Simulation results show that both the proposed approach and a Genetic Algorithm-based approach achieve the minimum peak power consumption possible, which is 58% less than on-demand dispatch. Also, for 82.2% of the simulations, our method finds a better schedule than its initialization.","PeriodicalId":166147,"journal":{"name":"2022 IEEE Green Energy and Smart System Systems(IGESSC)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128802559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/IGESSC55810.2022.9955331
Ibrahim M Ali, H. Yeh, Yu Yang
The objective of this paper is to improve the F-1 score computed in classifying shark raw-data into behaviors, namely; Resting, Swimming, Feeding, and Non-Directed Motion (NDM). Combining two different sets of pre-processed data into one image is examined for F-1 score improvement. The two sets of pre-processed data are Fast Fourier Transformation (FFT) and Walsh-Hadamard Transformation (WHT). Combining these two sets in a Convolutional Neural Network (CNN) model resulted in considerably improved F-1 score, while combining them in a K-Nearest Neighbors (K-NN) model averaged their individual F-1 scores.
{"title":"Improvement of F-1 Score in Classifying Shark Data into Shark Behaviors","authors":"Ibrahim M Ali, H. Yeh, Yu Yang","doi":"10.1109/IGESSC55810.2022.9955331","DOIUrl":"https://doi.org/10.1109/IGESSC55810.2022.9955331","url":null,"abstract":"The objective of this paper is to improve the F-1 score computed in classifying shark raw-data into behaviors, namely; Resting, Swimming, Feeding, and Non-Directed Motion (NDM). Combining two different sets of pre-processed data into one image is examined for F-1 score improvement. The two sets of pre-processed data are Fast Fourier Transformation (FFT) and Walsh-Hadamard Transformation (WHT). Combining these two sets in a Convolutional Neural Network (CNN) model resulted in considerably improved F-1 score, while combining them in a K-Nearest Neighbors (K-NN) model averaged their individual F-1 scores.","PeriodicalId":166147,"journal":{"name":"2022 IEEE Green Energy and Smart System Systems(IGESSC)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132445604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vehicle detection plays an important role in analyzing traffic flow data for efficient planning in intelligent transportation. Machine Learning technology has been increasingly used for vehicle detection in traffic flows. However, adverse weather conditions bring challenges for 2D vehicle detection. There is a lack of research on real-time vehicle detection using 3D LiDAR point clouds, which are more resistant to adverse weather conditions. In this paper, we proposed a system for collecting real-time traffic data using both 2D and 3D LiDAR cameras, processing the collected data for vehicle detection, and providing a web-based service with statistical traffic flow data visualization and 2D real-time vehicle detection stream display. We generated 1980 images from the 2D traffic flow videos that were collected in California Highway, and trained a 2D machine learning model on Darknet using YOLO algorithm. Approximately, 7000 frames of LiDAR point cloud data were labeled and pre-processed, and a new deep learning model for 3D vehicle detection was proposed. Compared with YOLO’s original pre-trained mode, our 2D machine learning model improved the vehicle detection that 6 different types of vehicles could be classified with an average precision of 89.25%.
{"title":"Real-time Vehicle Detection System for Intelligent Transportation using Machine Learning","authors":"Ruihan Wu, Ziaur Chowdhury, Gustavo Velasquez Sanchez, Xin Gao, Cesar Villa, Xunfei Jiang","doi":"10.1109/IGESSC55810.2022.9955329","DOIUrl":"https://doi.org/10.1109/IGESSC55810.2022.9955329","url":null,"abstract":"Vehicle detection plays an important role in analyzing traffic flow data for efficient planning in intelligent transportation. Machine Learning technology has been increasingly used for vehicle detection in traffic flows. However, adverse weather conditions bring challenges for 2D vehicle detection. There is a lack of research on real-time vehicle detection using 3D LiDAR point clouds, which are more resistant to adverse weather conditions. In this paper, we proposed a system for collecting real-time traffic data using both 2D and 3D LiDAR cameras, processing the collected data for vehicle detection, and providing a web-based service with statistical traffic flow data visualization and 2D real-time vehicle detection stream display. We generated 1980 images from the 2D traffic flow videos that were collected in California Highway, and trained a 2D machine learning model on Darknet using YOLO algorithm. Approximately, 7000 frames of LiDAR point cloud data were labeled and pre-processed, and a new deep learning model for 3D vehicle detection was proposed. Compared with YOLO’s original pre-trained mode, our 2D machine learning model improved the vehicle detection that 6 different types of vehicles could be classified with an average precision of 89.25%.","PeriodicalId":166147,"journal":{"name":"2022 IEEE Green Energy and Smart System Systems(IGESSC)","volume":"921 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131993741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/IGESSC55810.2022.9955326
Ching-Yen Chung, Yingqi Xiong, E. Kim, Charlie Qiu, C. Chu, R. Gadh
Unpredictable and unmanaged Electric Vehicle (EV) charging together with intermittent solar generation remains a challenge in modern distributed energy implementation. Without the technology for harnessing EV charging to the benefit of the grid, there will be no market for grid services and little impact for aggregators. This paper provides systematic approaches for Vehicle-Grid Integrated microgrid planning. Several tools from governments and commercial simulation packages including Interruption Cost Estimate (ICE) Calculator, PVWatts, Storage Value Estimation Tool (StorageVETTM), Electrical Transient Analyzer Program (ETAP), and Real Time Digital Simulator (RTDS), are used to verify the design requirements and simulate the electric load changes using smart charging and Vehicle-to-Grid (V2G). The simulation results showed that load shaping by smart charging and V2G fattened undesirable ramps and halved the system’s peak load, which can be translated to significant cost savings for the grid operator.
{"title":"Challenges of Vehicle-Grid Integration as Modern Distributed Energy Implementation","authors":"Ching-Yen Chung, Yingqi Xiong, E. Kim, Charlie Qiu, C. Chu, R. Gadh","doi":"10.1109/IGESSC55810.2022.9955326","DOIUrl":"https://doi.org/10.1109/IGESSC55810.2022.9955326","url":null,"abstract":"Unpredictable and unmanaged Electric Vehicle (EV) charging together with intermittent solar generation remains a challenge in modern distributed energy implementation. Without the technology for harnessing EV charging to the benefit of the grid, there will be no market for grid services and little impact for aggregators. This paper provides systematic approaches for Vehicle-Grid Integrated microgrid planning. Several tools from governments and commercial simulation packages including Interruption Cost Estimate (ICE) Calculator, PVWatts, Storage Value Estimation Tool (StorageVETTM), Electrical Transient Analyzer Program (ETAP), and Real Time Digital Simulator (RTDS), are used to verify the design requirements and simulate the electric load changes using smart charging and Vehicle-to-Grid (V2G). The simulation results showed that load shaping by smart charging and V2G fattened undesirable ramps and halved the system’s peak load, which can be translated to significant cost savings for the grid operator.","PeriodicalId":166147,"journal":{"name":"2022 IEEE Green Energy and Smart System Systems(IGESSC)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128074679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/IGESSC55810.2022.9955324
Masato Yokoyama, S. Narieda, H. Naruse
In this paper, we propose an energy detection based signal detection algorithm that can reduce power consumption by decreasing the number of samples when the target signal seems to be absent. The general concept of the proposed technique is the same as that of light-emitting diode dynamic lighting systems for energy efficiency, and decreasing the number of samples for signal detection can be achieved under the assumption of dynamic power management technologies, such as clock gating or power gating, which can reduce the power consumption of digital hardware. To avoid the deterioration of signal detection accuracy owing to the continuous signal detection mentioned above, traditional energy detection is executed when the target signal seems to be present. In the proposed algorithm, the transition between the two types of signal detection schemes is determined by the previous signal detection results. Numerical examples are presented to demonstrate the fundamental characteristics of the proposed signal detection algorithm.
{"title":"Fundamental Studies of Signal Detection Based on Dynamic Power Management for Wireless Systems","authors":"Masato Yokoyama, S. Narieda, H. Naruse","doi":"10.1109/IGESSC55810.2022.9955324","DOIUrl":"https://doi.org/10.1109/IGESSC55810.2022.9955324","url":null,"abstract":"In this paper, we propose an energy detection based signal detection algorithm that can reduce power consumption by decreasing the number of samples when the target signal seems to be absent. The general concept of the proposed technique is the same as that of light-emitting diode dynamic lighting systems for energy efficiency, and decreasing the number of samples for signal detection can be achieved under the assumption of dynamic power management technologies, such as clock gating or power gating, which can reduce the power consumption of digital hardware. To avoid the deterioration of signal detection accuracy owing to the continuous signal detection mentioned above, traditional energy detection is executed when the target signal seems to be present. In the proposed algorithm, the transition between the two types of signal detection schemes is determined by the previous signal detection results. Numerical examples are presented to demonstrate the fundamental characteristics of the proposed signal detection algorithm.","PeriodicalId":166147,"journal":{"name":"2022 IEEE Green Energy and Smart System Systems(IGESSC)","volume":"175 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131391111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/IGESSC55810.2022.9955343
Shreya Agarwal, D. Black
Distributed energy resources (DER) microgrids, especially photovoltaic (PV) and battery energy storage systems (BESS) are being more widely deployed behind the meter for decarbonizing the grid. This paper studies their impact on providing resilience to critical infrastructure, particularly which have a flat daily load profile such as hospitals and data centers. The study models load data from Lawrence Berkeley National Lab (LBNL) which has a flat critical load profile. The authors model a single and multi-day outage using the Distributed Energy Resources Customer Adoption Model (DERCAM) to optimize the configuration of DER based microgrids to support these outages. The authors expand these microgrid configurations to determine the microgrid DER sizes for other critical load levels which have a similar flat profile. The economic analysis presented here includes savings from cost of lost load due to outages, utility bill savings and carbon emission savings to compute a more complete accounting of costs and benefits. These results are then compared to the cost of resilience support traditionally provided by diesel generators. Finally, the net economic benefits are summarized suggesting that including resilience costs from lost load and other economic factors supports investments in DER microgrids for resilience support.
{"title":"Optimal sizing of microgrid DERs for specialized critical load resilience","authors":"Shreya Agarwal, D. Black","doi":"10.1109/IGESSC55810.2022.9955343","DOIUrl":"https://doi.org/10.1109/IGESSC55810.2022.9955343","url":null,"abstract":"Distributed energy resources (DER) microgrids, especially photovoltaic (PV) and battery energy storage systems (BESS) are being more widely deployed behind the meter for decarbonizing the grid. This paper studies their impact on providing resilience to critical infrastructure, particularly which have a flat daily load profile such as hospitals and data centers. The study models load data from Lawrence Berkeley National Lab (LBNL) which has a flat critical load profile. The authors model a single and multi-day outage using the Distributed Energy Resources Customer Adoption Model (DERCAM) to optimize the configuration of DER based microgrids to support these outages. The authors expand these microgrid configurations to determine the microgrid DER sizes for other critical load levels which have a similar flat profile. The economic analysis presented here includes savings from cost of lost load due to outages, utility bill savings and carbon emission savings to compute a more complete accounting of costs and benefits. These results are then compared to the cost of resilience support traditionally provided by diesel generators. Finally, the net economic benefits are summarized suggesting that including resilience costs from lost load and other economic factors supports investments in DER microgrids for resilience support.","PeriodicalId":166147,"journal":{"name":"2022 IEEE Green Energy and Smart System Systems(IGESSC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121878013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/IGESSC55810.2022.9955332
Ian Guzmán, Keith Goossen, K. Barner
Smart electric meters require efficient signal processing algorithms for load identification and energy disaggregation. Non-intrusive load monitoring (NILM) systems are able to extract features from the fundamental power signal in order to collect information about the end use of electric loads. Switching transients induced by turning on or off a certain appliance can be used to identify which appliance is connected or disconnected at a given time in the electrical network. The dataset used in this work is the most recent version of the Plug-Load Appliance Identification Dataset (PLAID) which contains records of voltages and currents of different electrical appliances captured at a high sampling frequency (30 kHz). This paper presents a new approach for appliance classification with deep learning techniques by using a finite impulse response (FIR) high pass filter to remove the fundamental signal, then the short time Fourier transform (STFT) is computed for the feature extraction of high frequency start-up transients induced in the fundamental signal. The proposed convolutional neural network architecture yields a classification accuracy of 95.22% and 88.20% for twelve and sixteen different appliances, respectively.
{"title":"Classification of High Frequency NILM Transients Based on Convolutional Neural Networks","authors":"Ian Guzmán, Keith Goossen, K. Barner","doi":"10.1109/IGESSC55810.2022.9955332","DOIUrl":"https://doi.org/10.1109/IGESSC55810.2022.9955332","url":null,"abstract":"Smart electric meters require efficient signal processing algorithms for load identification and energy disaggregation. Non-intrusive load monitoring (NILM) systems are able to extract features from the fundamental power signal in order to collect information about the end use of electric loads. Switching transients induced by turning on or off a certain appliance can be used to identify which appliance is connected or disconnected at a given time in the electrical network. The dataset used in this work is the most recent version of the Plug-Load Appliance Identification Dataset (PLAID) which contains records of voltages and currents of different electrical appliances captured at a high sampling frequency (30 kHz). This paper presents a new approach for appliance classification with deep learning techniques by using a finite impulse response (FIR) high pass filter to remove the fundamental signal, then the short time Fourier transform (STFT) is computed for the feature extraction of high frequency start-up transients induced in the fundamental signal. The proposed convolutional neural network architecture yields a classification accuracy of 95.22% and 88.20% for twelve and sixteen different appliances, respectively.","PeriodicalId":166147,"journal":{"name":"2022 IEEE Green Energy and Smart System Systems(IGESSC)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130679777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/IGESSC55810.2022.9955336
A. Jamehbozorg, Masood Shahverdi, Christopher Serrato, Nelson Flores
Utilizing an energy storage system (ESS) is an effective solution for both solving the uncertainty problem of renewable energy sources and optimizing the cost of operation of the microgrid (MG). When planning for the sizing of an ESS in a longer span (e.g., a decade ahead), precise formulation of the optimization objective function relies on ESS degradation and O&M costs, and the predicted trends of variables like hourly electricity rates, load, and generation. In addition, the characteristics of the to-be-deployed control strategy significantly affect the optimal size. Thus, this paper proposes a modular solution to the sizing problem of ESS under the rapid growth of Electric vehicle charging demand while all the mentioned concerning factors are considered. The same to-be-deployed top layer of operation hierarchical control is used at the time of sizing and an innovative cost function is developed to model the complexity of the time of use plan. The results of the optimization determine the optimal size of the battery storages in each stage and the yearly savings in operation cost considering the battery cost.
{"title":"Optimal Size of Energy Storage Systems in Microgrids Under Rapid Growth of EV Charging Demands","authors":"A. Jamehbozorg, Masood Shahverdi, Christopher Serrato, Nelson Flores","doi":"10.1109/IGESSC55810.2022.9955336","DOIUrl":"https://doi.org/10.1109/IGESSC55810.2022.9955336","url":null,"abstract":"Utilizing an energy storage system (ESS) is an effective solution for both solving the uncertainty problem of renewable energy sources and optimizing the cost of operation of the microgrid (MG). When planning for the sizing of an ESS in a longer span (e.g., a decade ahead), precise formulation of the optimization objective function relies on ESS degradation and O&M costs, and the predicted trends of variables like hourly electricity rates, load, and generation. In addition, the characteristics of the to-be-deployed control strategy significantly affect the optimal size. Thus, this paper proposes a modular solution to the sizing problem of ESS under the rapid growth of Electric vehicle charging demand while all the mentioned concerning factors are considered. The same to-be-deployed top layer of operation hierarchical control is used at the time of sizing and an innovative cost function is developed to model the complexity of the time of use plan. The results of the optimization determine the optimal size of the battery storages in each stage and the yearly savings in operation cost considering the battery cost.","PeriodicalId":166147,"journal":{"name":"2022 IEEE Green Energy and Smart System Systems(IGESSC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129286945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：