{"title":"Using Convolutional Neural Network for Fault Identification and Location in a Power System","authors":"Sheng-Kuan Wang, Chin Chang, V. Shen","doi":"10.1109/icet55676.2022.9824851","DOIUrl":"https://doi.org/10.1109/icet55676.2022.9824851","url":null,"abstract":"In this work, Convolutional Neural Network (CNN) is applied to the fault identification and location in a small power system. The phasor measurement units are assumed installation on all load buses to measure the bus voltage magnitudes and the active powers of the transmission lines in the time domain. Those records of the measured values are used as the input data of CNN, and these records are split into the training and testing groups. A4-machine 8-bus power system is used to evaluate the performances of CNN in this work. Three fault types of three-phase fault, single line to ground fault, and line break fault are simulated in the power system for evaluating the CNN-based identifying ability of the fault type. Two major fault scenarios of the single fault and two different faults occurrence at the same time are simulated for training CNN model. The accuracy rate of the fault identification is used to evaluate the performance of the proposed method in this paper. The simulation results have shown that the accuracy rate is 100% when all records are in the training group. The accuracy rate for the other cases is above 80%.","PeriodicalId":166358,"journal":{"name":"2022 IEEE 5th International Conference on Electronics Technology (ICET)","volume":"37 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132624557","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}
{"title":"A Real-Time Data Acquisition System for Coherent Lidar","authors":"Baolin Chen, Ge Jin, Lian Chen","doi":"10.1109/icet55676.2022.9824650","DOIUrl":"https://doi.org/10.1109/icet55676.2022.9824650","url":null,"abstract":"This paper presents a data acquisition system used for lidar signal receiving. To satisfy the need of lidar receiver system, a data acquisition system needs to be capable of sampling signal stably in a large magnitude range and can work in real time. To realize stable sampling in high speed, a new method using tap tuning for phase margin adjustment is proposed, which shows a good result in verification. Furthermore, automation method of error correction is introduced in this paper, which can accelerate the process of product development. In actual test, the DAQ can satisfy the need of lidar signal receiving and has a good performance.","PeriodicalId":166358,"journal":{"name":"2022 IEEE 5th International Conference on Electronics Technology (ICET)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131507624","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}
Zhaohui Li, Jianqin Liu, Siwei Liu, Zun Guo, M. Zhou
{"title":"Unit Commitment Considering Inertia Supply of Both Source and Demand Sides","authors":"Zhaohui Li, Jianqin Liu, Siwei Liu, Zun Guo, M. Zhou","doi":"10.1109/icet55676.2022.9824210","DOIUrl":"https://doi.org/10.1109/icet55676.2022.9824210","url":null,"abstract":"With the large-scale access of new energy to the power system, the system inertia continues to decline. The frequency security problem caused by insufficient system inertia seriously threatens the safe operation of the system. Therefore, inertia demand and inertia supply capacity need to be considered when making dispatching plans. However, the inertia supply capacity of demand side has not been fully investigated. In this context, this paper first establishes the inertia supply capacity model of both source and demand sides. On the source side, the inertia supply capacity of synchronous generators and wind turbine virtual synchronous machines(VSM) is considered comprehensively; on the demand side, a new evaluation method for inertia is proposed to find the inertia supply capacity of load. Then, based on the system dynamic frequency response, the inertia demand constraints based on the rate of change of frequency(RoCoF) and the frequency nadir are constructed. Finally, a unit commitment(UC) model considering inertia demand constraints is established, and the established model is tested in the modified IEEE-39 system. The results verify the effectiveness of the proposed inertia evaluation method; the proposed UC model can effectively improve the economy of the dispatching scheme while ensuring the system frequency safety.","PeriodicalId":166358,"journal":{"name":"2022 IEEE 5th International Conference on Electronics Technology (ICET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130627966","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}
{"title":"The Power Allocation in Cell-free Massive MIMO with Spatial Correlation and Access Points Selection","authors":"Xingyu He, Yang Liu","doi":"10.1109/icet55676.2022.9824132","DOIUrl":"https://doi.org/10.1109/icet55676.2022.9824132","url":null,"abstract":"In this paper, we propose two power allocations in the downlink of cell-free massive multiple-input multiple-output (MIMO) system with spatial correlation channel and access points (APs) selection. two power allocations are mainly to solve two fundamental problems, namely (i) to maximize the sum of spectral efficiency (max), and (ii) maximize the minimum spectral efficiency (max-min). We study the max and max-min problems based on closed expressions for maximum ratio transmission (MRT) precoding, analyze the constraints under the transmission power constraints, and establish the maximum and minimum objective functions based on the constraints. In the solution of max nonconvex problem, firstly, it is transformed into the equivalent problem of minimum weighted minimum mean square error (MMSE) to be solved. In the max-min nonconvex problem, second-order cone programming is formed by relaxed expression, and the bisection method help us to solve the max-min nonconvex problem. We show that max power allocation can get higher sum of spectral efficiency (SE), while max-min one reduces the spectral efficiency gap between system users and makes services fairer.","PeriodicalId":166358,"journal":{"name":"2022 IEEE 5th International Conference on Electronics Technology (ICET)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125354870","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}
{"title":"A Double gm Stages Up-Conversion CMOS Mixer for Ka-Band Applications","authors":"Tong Lingyun, Zhao Minghua","doi":"10.1109/icet55676.2022.9825400","DOIUrl":"https://doi.org/10.1109/icet55676.2022.9825400","url":null,"abstract":"This paper presents a Ka-band Gilbert up-conversion mixer, which is manufactured in the standard 55-nm CMOS process. The up-conversion mixer adopts a double balanced Gilbert cell and a double transconductance stage which are used to enhance the mixer linearity. To achieve a compact layout, the transformer is used for serving as inductive load stage, balun, and output matching network. The mixer achieves IF-port reflection coefficient less than -15 dB for frequency 8-12 GHz, and RF-port input reflection coefficient less than -15 dB for 36-40 GHz. The mixer realizes an output 1 dB compression point is 2.1 dBm at 38 GHz, whiling consuming 17mW from 1.2V supply.","PeriodicalId":166358,"journal":{"name":"2022 IEEE 5th International Conference on Electronics Technology (ICET)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126539316","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}
{"title":"Research on Tanks Combat Automatic Decision Using Multi-agent A2C Algorithm","authors":"Haoluo Jin","doi":"10.1109/icet55676.2022.9824741","DOIUrl":"https://doi.org/10.1109/icet55676.2022.9824741","url":null,"abstract":"As unmanned combat becomes certainly common in Land Warfare System (LWS), research on multi-tanks combat automatic decision is very crucial. In the light of the battle-field’s high dynamic and combatants’ indeterminacy, multi-agent reinforcement Learning (MARL) can achieve better automatic decision than traditional methods. In this paper, we propose a concept of Global states for training-Local observations for executing to expand advantage actor-critic (A2C) algorithm for matching multi-agent problems, meanwhile, we design different kinds of reward functions to encourage tanks to reach battle goals. In our algorithm (GLM-A2C), each agent can only receive its local observations and execute an action based on it, but global states are used for evaluating how the influence of joint actions is. Then, a multi-tank combat environment is built for proofing the effectiveness of GLM-A2C. Compared with existing MARL algorithms such as ES-A2C and MADDQN, GLM-A2C performs faster convergence, better-learned strategy, and higher success rate.","PeriodicalId":166358,"journal":{"name":"2022 IEEE 5th International Conference on Electronics Technology (ICET)","volume":"20 17","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113941734","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}
{"title":"The First-Degree Stochastic Dominance Rule of Comparing Pattern Recognition Algorithms with Accuracy Metric","authors":"Jun He, Rui-Gang Fu","doi":"10.1109/icet55676.2022.9824473","DOIUrl":"https://doi.org/10.1109/icet55676.2022.9824473","url":null,"abstract":"Accuracy of pattern recognition algorithm is an uncertain metric and should be transformed to utility value for better understanding of the performance of recognition algorithm. According to the uncertainty of accuracy and its utility transforming demands, we use stochastic dominance to compare two recognition algorithms. The first-degree dominance (FSD) rule is checked and proved to be unaffected by any non-diminishing utility transformation. The sufficient and necessary condition of the FSD rule is not always satisfied in the whole value range of accuracy, so we analyze its establishing condition firstly. The existing scope of the FSD rule is given by explicit expression and then some simplified cases are discussed. Both theorical analysis and numerical examples show that the FSD rule can be applied directly in the conditions of using the same test set to compare two recognition algorithms. While in the other conditions of using different test sets, the FSD rule is still useful in most cases. The FSD rule gives us much flexibility in preparing test data and more confidence about the comparison results.","PeriodicalId":166358,"journal":{"name":"2022 IEEE 5th International Conference on Electronics Technology (ICET)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114388591","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}
{"title":"Typical Commercial User Adjustable Potential Assessment Method","authors":"Yu Ming, Bin Li, Ke Chen, Weidong Wang, Yajie Wu","doi":"10.1109/icet55676.2022.9824448","DOIUrl":"https://doi.org/10.1109/icet55676.2022.9824448","url":null,"abstract":"At present, with the advancement of energy consumption revolution and energy transformation in various places, the traditional single energy consumption mode has been unable to adapt to the diversified market environment. The continuous promotion and application of new technologies such as artificial intelligence has spawned a new energy supply and demand model in which the demand side participates in grid regulation. This paper mainly studies the potential evaluation of commercial load participating in demand response, combined with the physical modeling of commercial load, studies the influencing factors of commercial load adjustment potential, and predicts and evaluates the adjustable potential of commercial load based on the TCN-LSTM neural network model.","PeriodicalId":166358,"journal":{"name":"2022 IEEE 5th International Conference on Electronics Technology (ICET)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114723093","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}
{"title":"Research on Load Forecasting Based on CNN-LSTM Hybrid Deep Learning Model","authors":"Fang Xu, Guoqing Weng, Qingquan Ye, Qinqin Xia","doi":"10.1109/icet55676.2022.9824615","DOIUrl":"https://doi.org/10.1109/icet55676.2022.9824615","url":null,"abstract":"A power load forecasting method based on convolutional neural network (CNN) and long short-term memory (LSTM) networks is proposed. On the premise of completing data preprocessing including normalization processing and K-means clustering, first use the CNN network to extract the feature vector of the continuous feature map constructed by the load influencing factors, and then use the extracted feature vector to establish an LSTM model for load predict. Finally, through a variety of different types of load data calculation examples, the analysis verifies that the proposed CNN-LSTM hybrid network model has better load prediction performance than the BP neural network, the CNN model alone or the LSTM model alone.","PeriodicalId":166358,"journal":{"name":"2022 IEEE 5th International Conference on Electronics Technology (ICET)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121910098","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}
{"title":"Design of a Dual Polarized Ku-Band Small Reflector Antenna with Low Sidelobe","authors":"Pei Qian, Jianmin Zhang, Botao Ye","doi":"10.1109/icet55676.2022.9825443","DOIUrl":"https://doi.org/10.1109/icet55676.2022.9825443","url":null,"abstract":"In order to monitor the ocean waves in real time, a small reflector antenna needs to be designed as the monitoring equipment. In this paper, the corrugated horn is used as the offset feed of the reflector antenna, and part of the rotating paraboloid is selected as the reflector of the small antenna. Through simulation and optimization design, good beam width, sidelobe level and VSWR are obtained. The physical measurement results show that the measured values are consistent with the theoretical values and meet the requirements of the preset indicators.","PeriodicalId":166358,"journal":{"name":"2022 IEEE 5th International Conference on Electronics Technology (ICET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116608513","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}