Pub Date : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030677
Qilei Dong, Jun Li
For optimal utilization of wind energy resources, wind power forecasting (WPF) is critical in balancing the electricity supply and demand in a power distribution network. Continuously forecasting wind power generation enables one country or region to operate its grid smoothly around the clock. In this article, a combined method is developed for the short-term WPF, which is comprised of discrete wavelet transform (DWT), self-organizing map (SOM) and multi-layer ensemble evolving fuzzy inference system (MEEFIS). Firstly, the row wind power sequences in the time domain are decomposed into several components in the frequency domain by using DWT, which are further selected as the features for wind power clustering. Then the SOM algorithm is adopted to cluster row wind power data and divide it into different data groups with features. Afterwards, the MEEFIS model is used to predict components in all types of data group, and the prediction results of components of various groups are overlapped to generate the final wind power forecasting value. Finally, the simulation analysis is done with actual wind farm power data in one region. The results of experiments demonstrate that this method can effectively improve the wind power forecasting accuracy and brings potential applications.
{"title":"Short-term Wind Power Forecasting Through Combined DWT-SOM and MEEFIS Method","authors":"Qilei Dong, Jun Li","doi":"10.1109/CEECT55960.2022.10030677","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030677","url":null,"abstract":"For optimal utilization of wind energy resources, wind power forecasting (WPF) is critical in balancing the electricity supply and demand in a power distribution network. Continuously forecasting wind power generation enables one country or region to operate its grid smoothly around the clock. In this article, a combined method is developed for the short-term WPF, which is comprised of discrete wavelet transform (DWT), self-organizing map (SOM) and multi-layer ensemble evolving fuzzy inference system (MEEFIS). Firstly, the row wind power sequences in the time domain are decomposed into several components in the frequency domain by using DWT, which are further selected as the features for wind power clustering. Then the SOM algorithm is adopted to cluster row wind power data and divide it into different data groups with features. Afterwards, the MEEFIS model is used to predict components in all types of data group, and the prediction results of components of various groups are overlapped to generate the final wind power forecasting value. Finally, the simulation analysis is done with actual wind farm power data in one region. The results of experiments demonstrate that this method can effectively improve the wind power forecasting accuracy and brings potential applications.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133184353","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030622
Zhong Zhaobin, Zhang Qiran, Ye Qing, Yi Wei, Zhao Yongqiang, Chen Tao
Electric transmission lines are distributed in the field, which is prone to abnormal discharge and even tripping accidents due to various natural factors. At present, it mainly relies on manual regular line patrol and traditional fault location device troubleshooting. There are problems such as insufficient positioning accuracy, inability to predict hidden dangers efficiently and accurately, and power failure due to insufficient power supply. Aiming at the functions of fast and accurate fault identification, location and hidden danger warning, a transmission line abnormal warning and fault location device is proposed. The intelligent device adopts distributed traveling wave measurement technology and is distributed on electric transmission line conductors. On the hardware, it combines the acquisition of power frequency signal, traveling wave signal and hidden danger signal, and the power supply mode mainly based on inductive power extraction and solar power extraction and assisted by lithium battery, which provides rich data resources and improves the power supply stability of the device. In software, the traditional threshold judgment is upgraded to the comprehensive analysis and judgment of multiple signal dynamic trend change algorithms, which effectively improves the fault recognition rate and accuracy. The device has been tested by the third party testing institution and has high fault location accuracy and hidden danger warning accuracy.
{"title":"Development of Transmission Line Abnormal Warning and Fault Location Device","authors":"Zhong Zhaobin, Zhang Qiran, Ye Qing, Yi Wei, Zhao Yongqiang, Chen Tao","doi":"10.1109/CEECT55960.2022.10030622","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030622","url":null,"abstract":"Electric transmission lines are distributed in the field, which is prone to abnormal discharge and even tripping accidents due to various natural factors. At present, it mainly relies on manual regular line patrol and traditional fault location device troubleshooting. There are problems such as insufficient positioning accuracy, inability to predict hidden dangers efficiently and accurately, and power failure due to insufficient power supply. Aiming at the functions of fast and accurate fault identification, location and hidden danger warning, a transmission line abnormal warning and fault location device is proposed. The intelligent device adopts distributed traveling wave measurement technology and is distributed on electric transmission line conductors. On the hardware, it combines the acquisition of power frequency signal, traveling wave signal and hidden danger signal, and the power supply mode mainly based on inductive power extraction and solar power extraction and assisted by lithium battery, which provides rich data resources and improves the power supply stability of the device. In software, the traditional threshold judgment is upgraded to the comprehensive analysis and judgment of multiple signal dynamic trend change algorithms, which effectively improves the fault recognition rate and accuracy. The device has been tested by the third party testing institution and has high fault location accuracy and hidden danger warning accuracy.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134615194","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 the electricity heat combined system, the equipment with large capacity to store heat can improve the stability of power system operation, thereby improving the system's ability to absorb wind power. In view of the construction cost and future benefits of the thermal storage device, a cost-benefit model of the thermal storage device scheme is established, and the data of the electric heat integrated dispatching model of the power system are substituted into it to calculate the IRR of the thermal storage device for the heating configuration of the clean project. The simulation example is solved by simulation software. The simulation results show that there is an optimal allocation of resources in the heat storage system, which makes the IRR of the whole Xilingol League region in Inner Mongolia the highest; The model can effectively analyze the benefits and costs of clean energy projects including heat storage devices in Xilingol League, Inner Mongolia.
{"title":"The optimal operation and economic benefit analysis of electric heat storage considering wind power consumption","authors":"Jianfeng Liu, Jiaqi Fan, Heran Kang, Qingzhuang Lin, Tianwen Zhang","doi":"10.1109/CEECT55960.2022.10030464","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030464","url":null,"abstract":"In the electricity heat combined system, the equipment with large capacity to store heat can improve the stability of power system operation, thereby improving the system's ability to absorb wind power. In view of the construction cost and future benefits of the thermal storage device, a cost-benefit model of the thermal storage device scheme is established, and the data of the electric heat integrated dispatching model of the power system are substituted into it to calculate the IRR of the thermal storage device for the heating configuration of the clean project. The simulation example is solved by simulation software. The simulation results show that there is an optimal allocation of resources in the heat storage system, which makes the IRR of the whole Xilingol League region in Inner Mongolia the highest; The model can effectively analyze the benefits and costs of clean energy projects including heat storage devices in Xilingol League, Inner Mongolia.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131118759","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030698
Zhan Li, Lei Liu, Z. Yang, Y. Shang, Tianmu Qin, Hao Du
Considering the energy storage and fast response characteristics of flywheels, flexibility transformation of flywheel energy storage array system (FESAS) and optimal power allocation. This paper proposes a macro-consistent coordinated control strategy based on a large-capacity flywheel energy storage array. Based on the mind of reducing the times of flywheel energy storage array mobilizations and adapting to power distribution, Firstly, dynamic group selection control for flywheel array, FESAS preferentially selects power-matched array groups for charging and discharging according to power allocation instructions. Secondly, the exponential relationship between SOC and specific power function is introduced into the flywheel unit, and the SOC difference of the flywheel unit in the array is gradually reduced, making the overall flywheel energy storage array gradually become macroscopic during charging and discharging. Finally, Simulink software is adopted to build the array model to prove the feasibility and efficacy of the proposed scheme.
{"title":"A Macro-Consistent Coordinated Control Strategy Based on Large-Capacity Flywheel Energy Storage Array","authors":"Zhan Li, Lei Liu, Z. Yang, Y. Shang, Tianmu Qin, Hao Du","doi":"10.1109/CEECT55960.2022.10030698","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030698","url":null,"abstract":"Considering the energy storage and fast response characteristics of flywheels, flexibility transformation of flywheel energy storage array system (FESAS) and optimal power allocation. This paper proposes a macro-consistent coordinated control strategy based on a large-capacity flywheel energy storage array. Based on the mind of reducing the times of flywheel energy storage array mobilizations and adapting to power distribution, Firstly, dynamic group selection control for flywheel array, FESAS preferentially selects power-matched array groups for charging and discharging according to power allocation instructions. Secondly, the exponential relationship between SOC and specific power function is introduced into the flywheel unit, and the SOC difference of the flywheel unit in the array is gradually reduced, making the overall flywheel energy storage array gradually become macroscopic during charging and discharging. Finally, Simulink software is adopted to build the array model to prove the feasibility and efficacy of the proposed scheme.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133022343","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030635
Haiyan Wang, Cuimian Liu, Yingying Deng, Shengyong Ye, T. Ma, Yi Zhang, Wei Hu
With the continuous expansion of power demand, the scale of distribution network investment and construction is also growing rapidly. In order to improve the accuracy and balance of distribution network investment and further maximize the economic benefits of investment, this paper creatively proposes a distribution network investment allocation model that considers the input-output benefits and development level quality. Firstly, the comprehensive evaluation index system of distribution network is constructed from two dimensions of technology and benefit, and the index calculation model is established to realize the horizontal comparison of the development status of distribution network. Then, by introducing the two factor theory and taking into account the development status and future development needs of the distribution network, an investment allocation model is built to determine the proportion of investment allocation. Finally, the empirical analysis is carried out based on the development status of Sichuan distribution network, and the results show that the model can better meet the future development needs of various cities, and achieve accurate and efficient investment in Sichuan distribution network.
{"title":"Distribution Network Investment Allocation Model Considering Input-Output and Development Level","authors":"Haiyan Wang, Cuimian Liu, Yingying Deng, Shengyong Ye, T. Ma, Yi Zhang, Wei Hu","doi":"10.1109/CEECT55960.2022.10030635","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030635","url":null,"abstract":"With the continuous expansion of power demand, the scale of distribution network investment and construction is also growing rapidly. In order to improve the accuracy and balance of distribution network investment and further maximize the economic benefits of investment, this paper creatively proposes a distribution network investment allocation model that considers the input-output benefits and development level quality. Firstly, the comprehensive evaluation index system of distribution network is constructed from two dimensions of technology and benefit, and the index calculation model is established to realize the horizontal comparison of the development status of distribution network. Then, by introducing the two factor theory and taking into account the development status and future development needs of the distribution network, an investment allocation model is built to determine the proportion of investment allocation. Finally, the empirical analysis is carried out based on the development status of Sichuan distribution network, and the results show that the model can better meet the future development needs of various cities, and achieve accurate and efficient investment in Sichuan distribution network.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132707604","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}
Transformer's stable operation is necessary for safety of power network. Although the dielectric response technology can evaluate the aging state of transformer, there is little equivalent model for evaluating. This paper tests the polarization and depolarization current(PDC) of the oil-paper insulation model of the transformer under variable temperature and calculates its isothermal relaxation current curve correspondingly. For the calculation results, it's found that with the raise of test temperature, the relaxation period of the isothermal relaxation current decreases. Also, the dielectric spectrum calculated according to the current curve shows that with the test temperature rises and the aging degree increases. The peak position of time-domain dielectric spectrum curve of the isothermal relaxation current gradually shifts to the right, and the main relaxation peak and relaxation time constant gradually increase. Thus, this paper establishes the calculation equation of main peak relaxation time and cellulose oil-impregnated paperboard cellulose, which can reasonably evaluate the aging degree of the oil-paper insulation system.
{"title":"Evaluation Method of Aging State of Oil-Paper Insulation Based on Time Domain Dielectric Response","authors":"Heqian Liu, Shiyu Chen, Zhong-Yuan Li, Hongda Yang, Peng Zhang, Jianquan Liang","doi":"10.1109/CEECT55960.2022.10030605","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030605","url":null,"abstract":"Transformer's stable operation is necessary for safety of power network. Although the dielectric response technology can evaluate the aging state of transformer, there is little equivalent model for evaluating. This paper tests the polarization and depolarization current(PDC) of the oil-paper insulation model of the transformer under variable temperature and calculates its isothermal relaxation current curve correspondingly. For the calculation results, it's found that with the raise of test temperature, the relaxation period of the isothermal relaxation current decreases. Also, the dielectric spectrum calculated according to the current curve shows that with the test temperature rises and the aging degree increases. The peak position of time-domain dielectric spectrum curve of the isothermal relaxation current gradually shifts to the right, and the main relaxation peak and relaxation time constant gradually increase. Thus, this paper establishes the calculation equation of main peak relaxation time and cellulose oil-impregnated paperboard cellulose, which can reasonably evaluate the aging degree of the oil-paper insulation system.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"233 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113996672","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030349
Xuexue Wei, Xikui Liu, Yan Li
Using the T-S model, this article discusses the dynamic output feedback (DOF) finite-time $H$∞ control (FTHC) problem for a category of discrete-time stochastic systems (DTSSs) with time-varying norm bounded uncertain terms. Initially, the notion of finite-time $H$∞ boundedness is given. Then, by the method of Lyapunov functional, sufficient criteria are introduced for the obtaining closed-loop system (CLS) to be finite-time bounded and the influence of disturbing input on the controlled output to be restrained within a certain level. Furthermore, sufficient conditions on finite-time $H$∞ bounded (FTHB) for the CLS utilizing a DOF controller are presented, and the DOF control gain can be obtained by solving the optimization problem for linear matrix inequalities (LMIs). Finally, the validity of the proposed approach is illustrated by a simulation example.
{"title":"Dynamic Output Feedback Finite-Time H∞ Control for Discrete-Time T-S Fuzzy Stochastic Uncertain Systems","authors":"Xuexue Wei, Xikui Liu, Yan Li","doi":"10.1109/CEECT55960.2022.10030349","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030349","url":null,"abstract":"Using the T-S model, this article discusses the dynamic output feedback (DOF) finite-time $H$∞ control (FTHC) problem for a category of discrete-time stochastic systems (DTSSs) with time-varying norm bounded uncertain terms. Initially, the notion of finite-time $H$∞ boundedness is given. Then, by the method of Lyapunov functional, sufficient criteria are introduced for the obtaining closed-loop system (CLS) to be finite-time bounded and the influence of disturbing input on the controlled output to be restrained within a certain level. Furthermore, sufficient conditions on finite-time $H$∞ bounded (FTHB) for the CLS utilizing a DOF controller are presented, and the DOF control gain can be obtained by solving the optimization problem for linear matrix inequalities (LMIs). Finally, the validity of the proposed approach is illustrated by a simulation example.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116453544","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030427
Zheng Li, Rong Sun, Xinyao Zhu, Yong-yong Jia, Wenbo Li, Yuqiao Jia, Dajiang Wang
The fault of the receiving-end AC power grid of the high voltage direct current (HVDC) transmission system may cause the HVDC subsequent commutation failures. In order to dynamically adjust the DC current command during the recovery process of the first HVDC commutation failure to achieve the purpose of suppressing the HVDC subsequent commutation failures, a new method is proposed based on improved genetic algorithm (IGA) of the voltage dependent current order limiter (VDCOL) link optimization method. This paper analyzes the influencing factors of HVDC subsequent commutation failures and the reactive power interaction between the inverter converter station and the external power grid. Taking VDCOL as the research object, the work principle and limitations of conventional VDCOL are introduced. In order to overcome the single linear defect of the conventional VDCOL link, an IGA was used to optimize the parameters of the multi-segment inflection point of the VDCOL link, which realized the dynamic reactive power demand adjustment of the inverter side converter station when the receiving-end AC power grid was faulty, and then suppress the HVDC subsequent commutation failures. Finally, the simulation results demonstrate the effectiveness of the proposed method.
{"title":"VDCOL link optimization of HVDC system based on improved genetic algorithm","authors":"Zheng Li, Rong Sun, Xinyao Zhu, Yong-yong Jia, Wenbo Li, Yuqiao Jia, Dajiang Wang","doi":"10.1109/CEECT55960.2022.10030427","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030427","url":null,"abstract":"The fault of the receiving-end AC power grid of the high voltage direct current (HVDC) transmission system may cause the HVDC subsequent commutation failures. In order to dynamically adjust the DC current command during the recovery process of the first HVDC commutation failure to achieve the purpose of suppressing the HVDC subsequent commutation failures, a new method is proposed based on improved genetic algorithm (IGA) of the voltage dependent current order limiter (VDCOL) link optimization method. This paper analyzes the influencing factors of HVDC subsequent commutation failures and the reactive power interaction between the inverter converter station and the external power grid. Taking VDCOL as the research object, the work principle and limitations of conventional VDCOL are introduced. In order to overcome the single linear defect of the conventional VDCOL link, an IGA was used to optimize the parameters of the multi-segment inflection point of the VDCOL link, which realized the dynamic reactive power demand adjustment of the inverter side converter station when the receiving-end AC power grid was faulty, and then suppress the HVDC subsequent commutation failures. Finally, the simulation results demonstrate the effectiveness of the proposed method.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131855644","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030700
Shang Erzhen, Pan Tingyi, Wang Jiafeng, Xie Bo, Guan Jinglin, Huan He, Zhao Shuang
Aiming at the problems that are difficult to analyze due to the diverse load characteristics of distribution network users, considering the behavior characteristics of distribution terminal users, define user power consumption characteristics indicators, and study and establish a new distribution terminal load power consumption habit index system. Aiming at the problem that due to the diverse composition of end users and the randomness of user behavior, which reduces the accuracy of the analysis model of electricity consumption habits, considering the influencing factors such as user electricity consumption behavior, holidays and emergencies, a clustering algorithm based on data mining theory is used to The power distribution terminal user data is preprocessed to eliminate data noise interference, extract the feature quantities of the influencing factors of user behavior, and improve the accuracy of the analysis model. Finally, a portrait of the electricity consumption behavior of power distribution terminal users is formed, and according to the analysis results, it has a certain load forecasting ability for users.
{"title":"A Consumption Habits Clustering Modeling of Distribution Terminal Loads Based on Multi-Source Data Fusion","authors":"Shang Erzhen, Pan Tingyi, Wang Jiafeng, Xie Bo, Guan Jinglin, Huan He, Zhao Shuang","doi":"10.1109/CEECT55960.2022.10030700","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030700","url":null,"abstract":"Aiming at the problems that are difficult to analyze due to the diverse load characteristics of distribution network users, considering the behavior characteristics of distribution terminal users, define user power consumption characteristics indicators, and study and establish a new distribution terminal load power consumption habit index system. Aiming at the problem that due to the diverse composition of end users and the randomness of user behavior, which reduces the accuracy of the analysis model of electricity consumption habits, considering the influencing factors such as user electricity consumption behavior, holidays and emergencies, a clustering algorithm based on data mining theory is used to The power distribution terminal user data is preprocessed to eliminate data noise interference, extract the feature quantities of the influencing factors of user behavior, and improve the accuracy of the analysis model. Finally, a portrait of the electricity consumption behavior of power distribution terminal users is formed, and according to the analysis results, it has a certain load forecasting ability for users.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"379 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132830173","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 : 2022-12-01DOI: 10.1109/CEECT55960.2022.10030255
Haiwei Wu, Lin Lin, Jianan Wang, Song Yuan, Yunyi Huang
In order to deeply mine the behavior characteristics of power demand-side users and strengthen the accurate interaction between source, grid and load, it is of great significance to identify and analyze load patterns based on massive user load data. In order to solve the problem that the traditional k-means algorithm is sensitive to the initial clustering center and it is difficult to quantify the number of clusters, this paper uses the improved K-means clustering algorithm to cluster the massive user load data. In the data preprocessing stage, t-SNE dimension reduction technology is introduced, and then the GSA-elbow judgment is used to determine the number of clusters. The Huffman tree is constructed based on the density characteristics and dissimilarity attributes of the data to obtain the initial clustering center and obtain the stable clustering result. Based on load clustering, this paper uses SVM classifier for load pattern recognition to extract user load features, and realizes the pattern recognition of unknown user load data.
{"title":"Power Load Pattern Recognition based on Improved K-Means and SVM Classifier","authors":"Haiwei Wu, Lin Lin, Jianan Wang, Song Yuan, Yunyi Huang","doi":"10.1109/CEECT55960.2022.10030255","DOIUrl":"https://doi.org/10.1109/CEECT55960.2022.10030255","url":null,"abstract":"In order to deeply mine the behavior characteristics of power demand-side users and strengthen the accurate interaction between source, grid and load, it is of great significance to identify and analyze load patterns based on massive user load data. In order to solve the problem that the traditional k-means algorithm is sensitive to the initial clustering center and it is difficult to quantify the number of clusters, this paper uses the improved K-means clustering algorithm to cluster the massive user load data. In the data preprocessing stage, t-SNE dimension reduction technology is introduced, and then the GSA-elbow judgment is used to determine the number of clusters. The Huffman tree is constructed based on the density characteristics and dissimilarity attributes of the data to obtain the initial clustering center and obtain the stable clustering result. Based on load clustering, this paper uses SVM classifier for load pattern recognition to extract user load features, and realizes the pattern recognition of unknown user load data.","PeriodicalId":187017,"journal":{"name":"2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116115642","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：