Pub Date : 2021-04-01DOI: 10.1109/ACPEE51499.2021.9437089
Nawaraj Kumar Mahato, Jie Dong, C. Song, Zhimin Chen, Nan Wang, Hongliang Ma, Gangjun Gong
This paper puts forward a Bi-LSTM attention mechanism model based on voltage phasor for electric power system transient stability assessment. The Bi-LSTM attention mechanism is used to map the relationship between voltage phasor and power system transient stability, and by establishing a sample matrix of transient stability information in the initial stage of the perturbation level, the extracted features are more robust, effectively reducing the false and missing samples, thus improving the generalization ability and evaluation performance of the model. Furthermore, by adjusting the network structure parameters of the best evaluation indicator. The mapping model between input features and transient stability is established to further reduce false positives and sample loss, and to improve the accuracy of network model evaluation. The improved model combines Bi-LSTM feature extraction layer and attention mechanism to form a hybrid model for a transient stability classification model, and the IEEE-39 bus New England test system is used to verify the accuracy of the model, and the wide-area noise is introduced into the generated data to evaluate the robustness of the system. Finally, the method is used to realize the transient stability evaluation of the electric power system based on voltage phasor data, and the validity of the proposed model is authenticated by comparative analysis of the proposed hybrid model with another deep learning models.
{"title":"Electric Power System Transient Stability Assessment Based on Bi-LSTM Attention Mechanism","authors":"Nawaraj Kumar Mahato, Jie Dong, C. Song, Zhimin Chen, Nan Wang, Hongliang Ma, Gangjun Gong","doi":"10.1109/ACPEE51499.2021.9437089","DOIUrl":"https://doi.org/10.1109/ACPEE51499.2021.9437089","url":null,"abstract":"This paper puts forward a Bi-LSTM attention mechanism model based on voltage phasor for electric power system transient stability assessment. The Bi-LSTM attention mechanism is used to map the relationship between voltage phasor and power system transient stability, and by establishing a sample matrix of transient stability information in the initial stage of the perturbation level, the extracted features are more robust, effectively reducing the false and missing samples, thus improving the generalization ability and evaluation performance of the model. Furthermore, by adjusting the network structure parameters of the best evaluation indicator. The mapping model between input features and transient stability is established to further reduce false positives and sample loss, and to improve the accuracy of network model evaluation. The improved model combines Bi-LSTM feature extraction layer and attention mechanism to form a hybrid model for a transient stability classification model, and the IEEE-39 bus New England test system is used to verify the accuracy of the model, and the wide-area noise is introduced into the generated data to evaluate the robustness of the system. Finally, the method is used to realize the transient stability evaluation of the electric power system based on voltage phasor data, and the validity of the proposed model is authenticated by comparative analysis of the proposed hybrid model with another deep learning models.","PeriodicalId":127882,"journal":{"name":"2021 6th Asia Conference on Power and Electrical Engineering (ACPEE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122539692","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 : 2021-04-01DOI: 10.1109/ACPEE51499.2021.9436946
Tao Liu, Haibo Yu, H. Yin, Zhenlei Zhang, Zhiwei Sui, Dianchao Zhu, Lu Gao, Zhen Li
This article introduces the research and application of digital twin technology in the development of power grids. It relies on the Planning Information System management platform of the State Grid Corporation of China, with the goal of scientifically leading the development of a strong smart grid. It takes the Internet of things, blockchain, big data and other technologies as the support, and integrates massive data such as power, pipe trench corridor, regulatory planning and meteorological data, to build an online platform on which the power grid can be planned, constructed, and operated. At present, the Planning Information System platform is based on digital twin technology, which has integrated 22 sets of professional systems such as infrastructure, dispatching, equipment and marketing, and has access to 334 categories and 56 billion pieces of data such as equipment ledger, operation curve, project data and space resources. Through the above research, we have realized the "digital twin" of "physical power grid" and "online power grid", which supports the high-quality development of power grid business.
{"title":"Research and Application of Digital Twin Technology in Power Grid Development Business","authors":"Tao Liu, Haibo Yu, H. Yin, Zhenlei Zhang, Zhiwei Sui, Dianchao Zhu, Lu Gao, Zhen Li","doi":"10.1109/ACPEE51499.2021.9436946","DOIUrl":"https://doi.org/10.1109/ACPEE51499.2021.9436946","url":null,"abstract":"This article introduces the research and application of digital twin technology in the development of power grids. It relies on the Planning Information System management platform of the State Grid Corporation of China, with the goal of scientifically leading the development of a strong smart grid. It takes the Internet of things, blockchain, big data and other technologies as the support, and integrates massive data such as power, pipe trench corridor, regulatory planning and meteorological data, to build an online platform on which the power grid can be planned, constructed, and operated. At present, the Planning Information System platform is based on digital twin technology, which has integrated 22 sets of professional systems such as infrastructure, dispatching, equipment and marketing, and has access to 334 categories and 56 billion pieces of data such as equipment ledger, operation curve, project data and space resources. Through the above research, we have realized the \"digital twin\" of \"physical power grid\" and \"online power grid\", which supports the high-quality development of power grid business.","PeriodicalId":127882,"journal":{"name":"2021 6th Asia Conference on Power and Electrical Engineering (ACPEE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124262726","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}
In order to meet the reliability requirements of Xinjiang EHV power grid, improve the switching operation efficiency of EHV substation, and reduce the risk of misoperation, this paper determines the sequence control judgment based on different control modes and primary equipment, and proposes the design and application of one key sequence control in EHV substation by comparing the technology and economy of sensors, combining with anti misoperation host and intelligent operation order technology. On the premise of ensuring safety, it can effectively reduce the operation and outage time, reduce the misoperation rate, thus reduce the accident rate of power grid, and prevent large-scale blackout, which has certain guiding significance for the subsequent scheme design of EHV substation.
{"title":"Study on Application of One Key Sequence Control in 750 kV Substation","authors":"Zaibao Xiong, Xing Gan, Yu Gao, Yanning Li, D. Ding, Yingtao Tian","doi":"10.1109/ACPEE51499.2021.9436875","DOIUrl":"https://doi.org/10.1109/ACPEE51499.2021.9436875","url":null,"abstract":"In order to meet the reliability requirements of Xinjiang EHV power grid, improve the switching operation efficiency of EHV substation, and reduce the risk of misoperation, this paper determines the sequence control judgment based on different control modes and primary equipment, and proposes the design and application of one key sequence control in EHV substation by comparing the technology and economy of sensors, combining with anti misoperation host and intelligent operation order technology. On the premise of ensuring safety, it can effectively reduce the operation and outage time, reduce the misoperation rate, thus reduce the accident rate of power grid, and prevent large-scale blackout, which has certain guiding significance for the subsequent scheme design of EHV substation.","PeriodicalId":127882,"journal":{"name":"2021 6th Asia Conference on Power and Electrical Engineering (ACPEE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125324284","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 : 2021-04-01DOI: 10.1109/ACPEE51499.2021.9436903
Lingxiao Li, Xin Bai, Yaosong Guo, Jun Zhang, Cai-sheng Chen, Yapeng Yi, Aiping Wang
With the increasing of DC load and the maturity of power electronics technology, AC/DC hybrid microgrid (HMG), as a new form of microgrid, has been widely concerned. The optimal dispatching method has become a key technology for the rapid development of AC/DC HMG. Based on the consensus algorithm, a distributed optimal dispatching method is proposed in this paper. Firstly, a convex optimization model about AC/DC HMG is established. Secondly, based on the multi-agent system, a distributed control framework is presented. The "Leader-Follow" consensus algorithm is the solution of optimization model, and the incremental cost of distributed generator (DG) and energy storage is selected as the consensus variable. The solution process is divided into two stages to meet AC and DC load respectively for reducing the energy conversion loss. Finally, the results of an example prove the feasibility of the presented distributed optimal dispatching method.
{"title":"Distributed optimal dispatching of AC/DC hybrid microgrid based on consensus algorithm","authors":"Lingxiao Li, Xin Bai, Yaosong Guo, Jun Zhang, Cai-sheng Chen, Yapeng Yi, Aiping Wang","doi":"10.1109/ACPEE51499.2021.9436903","DOIUrl":"https://doi.org/10.1109/ACPEE51499.2021.9436903","url":null,"abstract":"With the increasing of DC load and the maturity of power electronics technology, AC/DC hybrid microgrid (HMG), as a new form of microgrid, has been widely concerned. The optimal dispatching method has become a key technology for the rapid development of AC/DC HMG. Based on the consensus algorithm, a distributed optimal dispatching method is proposed in this paper. Firstly, a convex optimization model about AC/DC HMG is established. Secondly, based on the multi-agent system, a distributed control framework is presented. The \"Leader-Follow\" consensus algorithm is the solution of optimization model, and the incremental cost of distributed generator (DG) and energy storage is selected as the consensus variable. The solution process is divided into two stages to meet AC and DC load respectively for reducing the energy conversion loss. Finally, the results of an example prove the feasibility of the presented distributed optimal dispatching method.","PeriodicalId":127882,"journal":{"name":"2021 6th Asia Conference on Power and Electrical Engineering (ACPEE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125389810","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 : 2021-04-01DOI: 10.1109/ACPEE51499.2021.9436956
Fang Lin, Yan Lin, Huiyu Zhang, Daoshan Huang
Power quality monitoring involves multiple types of interrelated data information, and the relationship between data entities is complex and dense, so graph database is more suitable for storage. Based on graph database and power graph computing platform, a power quality monitoring and visualization system based on the graph database is proposed. The power grid spatial data, real-time data of power grid users and equipment, and geographic environment data of power grid topology and its connection are stored through the graph database, so as to calculate the power graph related to power quality monitoring. Through the human-machine interface of the graph database query design, the multi-directional multi-angle visual display of power quality monitoring applications such as voltage sag location and voltage sag risk assessment are carried out.
{"title":"Power quality monitoring and its visualization application based on graph database","authors":"Fang Lin, Yan Lin, Huiyu Zhang, Daoshan Huang","doi":"10.1109/ACPEE51499.2021.9436956","DOIUrl":"https://doi.org/10.1109/ACPEE51499.2021.9436956","url":null,"abstract":"Power quality monitoring involves multiple types of interrelated data information, and the relationship between data entities is complex and dense, so graph database is more suitable for storage. Based on graph database and power graph computing platform, a power quality monitoring and visualization system based on the graph database is proposed. The power grid spatial data, real-time data of power grid users and equipment, and geographic environment data of power grid topology and its connection are stored through the graph database, so as to calculate the power graph related to power quality monitoring. Through the human-machine interface of the graph database query design, the multi-directional multi-angle visual display of power quality monitoring applications such as voltage sag location and voltage sag risk assessment are carried out.","PeriodicalId":127882,"journal":{"name":"2021 6th Asia Conference on Power and Electrical Engineering (ACPEE)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126380937","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 : 2021-04-01DOI: 10.1109/ACPEE51499.2021.9437117
Jingyan Liu, Pu Zhang, Qing Fang, Defei Yao, Xuenan Li, Jiayin Song, Siqi Guo, Ying Lian
The accurate and flexible observation, measurement and control of load is realized by the rapid development of big data, cloud computing technologies. Beijing power grid demand side resources has great potential for the adjustable, flexible and controllable load distribution. It is of great significance to study the response characteristics of flexible and controllable loads, establish the curve model of controllable loads and optimize the load curves of the power grid at all levels to explore a new power grid development mode of flexible interaction between multiple loads and the power grid. This paper presents the study of the flexible controllable load response characteristics based on Beijing power grid, established a controllable load curve model and control strategy. optimized the load curve at full voltage level in the grid. This research explores the new development of diversified load and the trend of flexible interactive networks in the future power grid.
{"title":"Load Optimization and Control Strategy Research Based on Flexible and Controllable Load Characteristics","authors":"Jingyan Liu, Pu Zhang, Qing Fang, Defei Yao, Xuenan Li, Jiayin Song, Siqi Guo, Ying Lian","doi":"10.1109/ACPEE51499.2021.9437117","DOIUrl":"https://doi.org/10.1109/ACPEE51499.2021.9437117","url":null,"abstract":"The accurate and flexible observation, measurement and control of load is realized by the rapid development of big data, cloud computing technologies. Beijing power grid demand side resources has great potential for the adjustable, flexible and controllable load distribution. It is of great significance to study the response characteristics of flexible and controllable loads, establish the curve model of controllable loads and optimize the load curves of the power grid at all levels to explore a new power grid development mode of flexible interaction between multiple loads and the power grid. This paper presents the study of the flexible controllable load response characteristics based on Beijing power grid, established a controllable load curve model and control strategy. optimized the load curve at full voltage level in the grid. This research explores the new development of diversified load and the trend of flexible interactive networks in the future power grid.","PeriodicalId":127882,"journal":{"name":"2021 6th Asia Conference on Power and Electrical Engineering (ACPEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129691293","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 : 2021-04-01DOI: 10.1109/ACPEE51499.2021.9436840
Yan Li, Yazhong Ye, Hong Li, Haifeng Liang, Qun Zhang, Qingshan Wang, Qiong Wang
Multi-station integration is conducive to intensive and efficient utilization of resources and provides basic guarantee for the construction of ubiquitous power internet of things. This paper studies the integration mode of "substation + data center station + battery energy storage station", and further explores the energy supply structure of the multi-station integration energy service station under different integrated element scenarios. Secondly, the planning-operation bi-layer model of multi-station integration is established, which aims at minimizing the total economic cost of equivalent annual value, and comprehensively considers the characteristics of multi-energy complementary energy flow of the system as well as the operation constraints under the function positioning of substations. Then the CPLEX solver is called under the YALMIP platform through MATLAB and combined with the improved particle swarm algorithm to complete the interactive solution of the upper and lower model. Finally, an example is used to verify the correctness of the model and analyze the economics of multi-station integration, which provides a reference for the actual construction of multi-station integration.
{"title":"Scenarios Analysis and Energy Supply Optimization Configuration for Multi-station Integration","authors":"Yan Li, Yazhong Ye, Hong Li, Haifeng Liang, Qun Zhang, Qingshan Wang, Qiong Wang","doi":"10.1109/ACPEE51499.2021.9436840","DOIUrl":"https://doi.org/10.1109/ACPEE51499.2021.9436840","url":null,"abstract":"Multi-station integration is conducive to intensive and efficient utilization of resources and provides basic guarantee for the construction of ubiquitous power internet of things. This paper studies the integration mode of \"substation + data center station + battery energy storage station\", and further explores the energy supply structure of the multi-station integration energy service station under different integrated element scenarios. Secondly, the planning-operation bi-layer model of multi-station integration is established, which aims at minimizing the total economic cost of equivalent annual value, and comprehensively considers the characteristics of multi-energy complementary energy flow of the system as well as the operation constraints under the function positioning of substations. Then the CPLEX solver is called under the YALMIP platform through MATLAB and combined with the improved particle swarm algorithm to complete the interactive solution of the upper and lower model. Finally, an example is used to verify the correctness of the model and analyze the economics of multi-station integration, which provides a reference for the actual construction of multi-station integration.","PeriodicalId":127882,"journal":{"name":"2021 6th Asia Conference on Power and Electrical Engineering (ACPEE)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129755268","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 : 2021-04-01DOI: 10.1109/ACPEE51499.2021.9436926
Dalian Wang, Siqi Li, Congcong Li, Yingying Zhang
The DC-DC power supply has been widely used in the fields of industry, military and other fields with high efficiency and low cost, and it is also becoming more and more important to the fault diagnosis and analysis of the DC-DC power supply. In this article, based on the failure mode and effects analysis (FMEA) and the fault tree analysis (FTA) method, a 48V DC-DC power supply is used as an application example, and the possible mode of the fault can be obtained by analyzing the circuit principle of the power supply, and then the possible cause of the failure is analyzed, and the fault tree is finally drawn. According to the change of the simulated output voltage waveform, it can provide guidance for the troubleshooting and rapid positioning of the actual project. The fault diagnosis and analysis method for the DC-DC power supply is suitable for other similar power sources, and the application of power supply in practical engineering is promoted.
{"title":"Fault Diagnosis Analysis and Application of DC-DC Power Supply based on FMEA and FTA","authors":"Dalian Wang, Siqi Li, Congcong Li, Yingying Zhang","doi":"10.1109/ACPEE51499.2021.9436926","DOIUrl":"https://doi.org/10.1109/ACPEE51499.2021.9436926","url":null,"abstract":"The DC-DC power supply has been widely used in the fields of industry, military and other fields with high efficiency and low cost, and it is also becoming more and more important to the fault diagnosis and analysis of the DC-DC power supply. In this article, based on the failure mode and effects analysis (FMEA) and the fault tree analysis (FTA) method, a 48V DC-DC power supply is used as an application example, and the possible mode of the fault can be obtained by analyzing the circuit principle of the power supply, and then the possible cause of the failure is analyzed, and the fault tree is finally drawn. According to the change of the simulated output voltage waveform, it can provide guidance for the troubleshooting and rapid positioning of the actual project. The fault diagnosis and analysis method for the DC-DC power supply is suitable for other similar power sources, and the application of power supply in practical engineering is promoted.","PeriodicalId":127882,"journal":{"name":"2021 6th Asia Conference on Power and Electrical Engineering (ACPEE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129474537","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 : 2021-04-01DOI: 10.1109/ACPEE51499.2021.9437025
Danjie Zhang, Jianjun Zhang, Tuo Deng, J. Ren, Wei Liu, Yan Zhang
In recent years, the application of Electric-Gas Integrated Energy System(EG-IES) has continued to develop, the coupling and connection between energy sources have become more and more close, and the interaction between power system and natural gas system has become complex. The change of power system network state will not only affect its own system, but also affect the natural gas system through coupling devices, which will cause huge economic loss when it is serious. This paper first analyzes the impact of voltage sag events in the power system on the electricity-gas integrated energy system, and then considers the natural gas system user economic loss assessment based on the process parameter immune time curve to provide a basis for subsequent voltage sag control methods. Finally, an electric-gas integrated energy system composed of IEEE14-node and 10-node natural gas systems is selected as an example to verify the correctness and effectiveness of the evaluation method.
{"title":"Assessment of economic losses of natural gas systems considering the effects of voltage sag","authors":"Danjie Zhang, Jianjun Zhang, Tuo Deng, J. Ren, Wei Liu, Yan Zhang","doi":"10.1109/ACPEE51499.2021.9437025","DOIUrl":"https://doi.org/10.1109/ACPEE51499.2021.9437025","url":null,"abstract":"In recent years, the application of Electric-Gas Integrated Energy System(EG-IES) has continued to develop, the coupling and connection between energy sources have become more and more close, and the interaction between power system and natural gas system has become complex. The change of power system network state will not only affect its own system, but also affect the natural gas system through coupling devices, which will cause huge economic loss when it is serious. This paper first analyzes the impact of voltage sag events in the power system on the electricity-gas integrated energy system, and then considers the natural gas system user economic loss assessment based on the process parameter immune time curve to provide a basis for subsequent voltage sag control methods. Finally, an electric-gas integrated energy system composed of IEEE14-node and 10-node natural gas systems is selected as an example to verify the correctness and effectiveness of the evaluation method.","PeriodicalId":127882,"journal":{"name":"2021 6th Asia Conference on Power and Electrical Engineering (ACPEE)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124606489","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}
Compared with traditional intrusive load monitoring system, the non-intrusive load monitoring system only needs to install a monitoring equipment at the entrance of the power supply. In this paper, we focus on the feature extraction for non-intrusive load monitoring system. By extracting features from the monitored voltage and current and training them in machine learning model, we can identify the types and operation states of different loads. Meanwhile, these features reflect the electrical characteristics (e.g., power) and can be used to detect the events (i.e., switch of operation states) for every load. Specifically, the features are obtained via time and frequency domain analysis. In time domain, energy ratio is calculated to detect the events during the operation of loads. Besides, active and reactive power, power factor and current peak coefficient are also calculated. To identify the load with current peak distortion, we innovatively propose a position ratio, defined as the ratio of the ramp-off time over the ramp-up time for a period of current waveform. In frequency domain, harmonic and total harmonic current distortion are extracted. Apart from this, the harmonic ratio such as the ratio of third harmonic to fundamental wave is proposed for load identification. It can be seen that, for resistive load such as heating kettle, the harmonic ratio is quite close to zero; for inductive load such as washing machine, the harmonic ratio is close to 1.
{"title":"Feature Extraction for Non-intrusive Load Monitoring System","authors":"Qiuzhan Zhou, Jiahui Wei, Mingyu Sun, Cong Wang, Jing Rong, Jikang Hu, Tong Yang","doi":"10.1109/ACPEE51499.2021.9436971","DOIUrl":"https://doi.org/10.1109/ACPEE51499.2021.9436971","url":null,"abstract":"Compared with traditional intrusive load monitoring system, the non-intrusive load monitoring system only needs to install a monitoring equipment at the entrance of the power supply. In this paper, we focus on the feature extraction for non-intrusive load monitoring system. By extracting features from the monitored voltage and current and training them in machine learning model, we can identify the types and operation states of different loads. Meanwhile, these features reflect the electrical characteristics (e.g., power) and can be used to detect the events (i.e., switch of operation states) for every load. Specifically, the features are obtained via time and frequency domain analysis. In time domain, energy ratio is calculated to detect the events during the operation of loads. Besides, active and reactive power, power factor and current peak coefficient are also calculated. To identify the load with current peak distortion, we innovatively propose a position ratio, defined as the ratio of the ramp-off time over the ramp-up time for a period of current waveform. In frequency domain, harmonic and total harmonic current distortion are extracted. Apart from this, the harmonic ratio such as the ratio of third harmonic to fundamental wave is proposed for load identification. It can be seen that, for resistive load such as heating kettle, the harmonic ratio is quite close to zero; for inductive load such as washing machine, the harmonic ratio is close to 1.","PeriodicalId":127882,"journal":{"name":"2021 6th Asia Conference on Power and Electrical Engineering (ACPEE)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130067087","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：