This paper presents a short-term load forecasting technique for summer using an artificial neural network (ANN). The purpose of this study is to forecast accurately daily peak load for a target period using actual data from the same period of the previous several years as training data. This paper describes two methods. In one method, the actual data of each year for the several years earlier are used for each ANN. The other method uses the collective data of several years for the training of the ANN. With the proposed method, the mean absolute forecasting error was below 2%.<>
{"title":"Short-term load forecasting by artificial neural networks using individual and collective data of preceding years","authors":"T. Matsumoto, S. Kitamura, Y. Ueki, T. Matsui","doi":"10.1109/ANN.1993.264283","DOIUrl":"https://doi.org/10.1109/ANN.1993.264283","url":null,"abstract":"This paper presents a short-term load forecasting technique for summer using an artificial neural network (ANN). The purpose of this study is to forecast accurately daily peak load for a target period using actual data from the same period of the previous several years as training data. This paper describes two methods. In one method, the actual data of each year for the several years earlier are used for each ANN. The other method uses the collective data of several years for the training of the ANN. With the proposed method, the mean absolute forecasting error was below 2%.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121978069","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}
The design and evaluation by simulation of an automatically-tuned fuzzy logic controller is presented. A method to automate the tuning process using a simplified Kalman filter approach is presented for the fuzzy logic controller to track a suitable reference trajectory. An optimal controller's response is used as a reference trajectory to determine automatically the rules for the fuzzy logic controller. To demonstrate the robustness of this design approach, a nonlinear six delayed neutron group plant is controlled using a fuzzy logic controller that utilizes estimated reactor temperatures from a one delayed neutron group observer. The fuzzy logic controller displayed good stability and performance robustness characteristics for a wide range of operation.<>
{"title":"Fuzzy logic controller for nuclear power plant","authors":"P. Ramaswamy, R. Edwards, K.Y. Lee","doi":"10.1109/ANN.1993.264354","DOIUrl":"https://doi.org/10.1109/ANN.1993.264354","url":null,"abstract":"The design and evaluation by simulation of an automatically-tuned fuzzy logic controller is presented. A method to automate the tuning process using a simplified Kalman filter approach is presented for the fuzzy logic controller to track a suitable reference trajectory. An optimal controller's response is used as a reference trajectory to determine automatically the rules for the fuzzy logic controller. To demonstrate the robustness of this design approach, a nonlinear six delayed neutron group plant is controlled using a fuzzy logic controller that utilizes estimated reactor temperatures from a one delayed neutron group observer. The fuzzy logic controller displayed good stability and performance robustness characteristics for a wide range of operation.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"13 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125823836","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}
Static security assessment of power systems is a time-intensive task involving repetitive solutions of power flow equations. The issue addressed in this paper is how to substantially reduce the amount of offline security assessment simulations used for neural net training. A Kohonen-based classifier is developed for this purpose. With the proposed scheme, the status of the system security is not needed for all training patterns. Only a selected sample of the training patterns needs to be assessed through simulations. Once the network is adequately trained, neurons that respond to secure or insecure states are self organized in clusters. In the testing stage, the pattern security states is determined by correlating the test pattern with a cluster of a known security status. The proposed scheme also provides information on the degree of system insecurity, and the range of the operation violation.<>
{"title":"Static security assessment of power system using Kohonen neural network","authors":"Mohamed A. El-Sharkawi, R. Atteri","doi":"10.1109/ANN.1993.264319","DOIUrl":"https://doi.org/10.1109/ANN.1993.264319","url":null,"abstract":"Static security assessment of power systems is a time-intensive task involving repetitive solutions of power flow equations. The issue addressed in this paper is how to substantially reduce the amount of offline security assessment simulations used for neural net training. A Kohonen-based classifier is developed for this purpose. With the proposed scheme, the status of the system security is not needed for all training patterns. Only a selected sample of the training patterns needs to be assessed through simulations. Once the network is adequately trained, neurons that respond to secure or insecure states are self organized in clusters. In the testing stage, the pattern security states is determined by correlating the test pattern with a cluster of a known security status. The proposed scheme also provides information on the degree of system insecurity, and the range of the operation violation.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126716974","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}
This paper describes a method of solving the maintenance scheduling problem of thermal power station units by making use of artificial neural networks, which can handle inequality constraints effectively. In the problem formulation, different classes of maintenance works and several consecutive years are considered to obtain a more realistic solution. The problem has been mapped on artificial neural networks and solved by a network simulator.<>
{"title":"A solution of maintenance scheduling covering several consecutive years by artificial neural networks","authors":"H. Sasaki, H. Choshi, Y. Takiuchi, J. Kubokawa","doi":"10.1109/ANN.1993.264326","DOIUrl":"https://doi.org/10.1109/ANN.1993.264326","url":null,"abstract":"This paper describes a method of solving the maintenance scheduling problem of thermal power station units by making use of artificial neural networks, which can handle inequality constraints effectively. In the problem formulation, different classes of maintenance works and several consecutive years are considered to obtain a more realistic solution. The problem has been mapped on artificial neural networks and solved by a network simulator.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"113 4 Suppl 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130420780","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}
This paper proposes a neural network approach to determining the contractual parameters of incentive power contracts. It describes the incentive power contract for a market in which the electricity supply industry has been largely privatized and suppliers compete to build plant and provide power supply. Since it is difficult to formulate and link practical decision factors such as management and technical factors with the parameters in terms of which a financial contract is usually formulated, neural networks appear to be a natural choice to solve the problem. A network is set up and trained to solve this problem and to work out contractual parameters.<>
{"title":"A neural network approach to evaluate contractual parameters of incentive power contracts","authors":"K. Wong, A. David","doi":"10.1109/ANN.1993.264335","DOIUrl":"https://doi.org/10.1109/ANN.1993.264335","url":null,"abstract":"This paper proposes a neural network approach to determining the contractual parameters of incentive power contracts. It describes the incentive power contract for a market in which the electricity supply industry has been largely privatized and suppliers compete to build plant and provide power supply. Since it is difficult to formulate and link practical decision factors such as management and technical factors with the parameters in terms of which a financial contract is usually formulated, neural networks appear to be a natural choice to solve the problem. A network is set up and trained to solve this problem and to work out contractual parameters.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122663432","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}
This paper presents a method of next day's peak load forecasting using an artificial neural network (ANN). The authors combine the DSC search method (Davis, Swann, Campey search method) with the backpropagation learning algorithm (Bp) to reduce the training time and avoid converging at local minima. The forecasting results by the ANN is as good as human experts' results and is better than the forecasting results by the regression model. The mean absolute percentage error (MAPE) of next day's peak load forecasts using this method on actual utility data is shown to be 2.67% in the summer period and 1.52% in the winter period. The MAPE of forecasts using human experts' experience is shown to be 2.86% and 1.59% in each period. The MAPE of forecasts using the regression model is shown to be 3.09% and 1.74% in each period.<>
{"title":"Next day's peak load forecasting using an artificial neural network","authors":"T. Onoda","doi":"10.1109/ANN.1993.264333","DOIUrl":"https://doi.org/10.1109/ANN.1993.264333","url":null,"abstract":"This paper presents a method of next day's peak load forecasting using an artificial neural network (ANN). The authors combine the DSC search method (Davis, Swann, Campey search method) with the backpropagation learning algorithm (Bp) to reduce the training time and avoid converging at local minima. The forecasting results by the ANN is as good as human experts' results and is better than the forecasting results by the regression model. The mean absolute percentage error (MAPE) of next day's peak load forecasts using this method on actual utility data is shown to be 2.67% in the summer period and 1.52% in the winter period. The MAPE of forecasts using human experts' experience is shown to be 2.86% and 1.59% in each period. The MAPE of forecasts using the regression model is shown to be 3.09% and 1.74% in each period.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116647106","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}
D. Klapper, H. Othman, Y. Akimoto, H. Tanaka, J. Yoshizawa
The feasibility of designing neural networks capable of computing the critical clearing times of power system faults is explored. Two distinct approaches are investigated, the patter recognition approach and the optimization approach. The theory of direct stability analysis of power systems is utilized is designing he input features of the pattern recognition approach, and the structure of the Hopfield optimization approach.<>
{"title":"Application of neural networks to direct stability analysis of power systems","authors":"D. Klapper, H. Othman, Y. Akimoto, H. Tanaka, J. Yoshizawa","doi":"10.1109/ANN.1993.264317","DOIUrl":"https://doi.org/10.1109/ANN.1993.264317","url":null,"abstract":"The feasibility of designing neural networks capable of computing the critical clearing times of power system faults is explored. Two distinct approaches are investigated, the patter recognition approach and the optimization approach. The theory of direct stability analysis of power systems is utilized is designing he input features of the pattern recognition approach, and the structure of the Hopfield optimization approach.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121579311","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}
The authors propose a neural network identifier to estimate the electric pollution (harmonics) contents present in the voltage and current signals of a mesh type multi terminal direct current (MTDC) system under dynamic conditions. A digital computer program has been developed to implement the neural network and a modified form of Fourier series representation which improves the accuracy of the results is discussed.<>
{"title":"Electric pollution studies in mesh type MTDC system using neural network","authors":"K. Narendra, H.S. Chandrasekharaiah","doi":"10.1109/ANN.1993.264322","DOIUrl":"https://doi.org/10.1109/ANN.1993.264322","url":null,"abstract":"The authors propose a neural network identifier to estimate the electric pollution (harmonics) contents present in the voltage and current signals of a mesh type multi terminal direct current (MTDC) system under dynamic conditions. A digital computer program has been developed to implement the neural network and a modified form of Fourier series representation which improves the accuracy of the results is discussed.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126673325","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}
T. Hara, A. Itoh, K. Yatsuka, K. Kishi, K. Hirotsu
A system of detecting corona discharges automatically with an artificial neural network is examined and a network which can distinguish between corona and noise patterns occurring in power cables is investigated. A feedforward type of a neural network with three layers, i.e. input, hidden and output layers is used. It is found that the network which learns only corona and no noise patterns does not show a good performance. This means that the network should learn both corona and noise patterns even for recognizing only corona discharges. The network which uses frequency spectra of waveforms obtained by a fast Fourier transform (FFT) method as input patterns is also investigated. The network with FFT pretreatment is found to show better performance than the one without FFT pretreatment.<>
{"title":"Application of the neural network to detecting corona discharge occurring in power cables","authors":"T. Hara, A. Itoh, K. Yatsuka, K. Kishi, K. Hirotsu","doi":"10.1109/ANN.1993.264337","DOIUrl":"https://doi.org/10.1109/ANN.1993.264337","url":null,"abstract":"A system of detecting corona discharges automatically with an artificial neural network is examined and a network which can distinguish between corona and noise patterns occurring in power cables is investigated. A feedforward type of a neural network with three layers, i.e. input, hidden and output layers is used. It is found that the network which learns only corona and no noise patterns does not show a good performance. This means that the network should learn both corona and noise patterns even for recognizing only corona discharges. The network which uses frequency spectra of waveforms obtained by a fast Fourier transform (FFT) method as input patterns is also investigated. The network with FFT pretreatment is found to show better performance than the one without FFT pretreatment.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124673454","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}
An electric power system requires voltage and reactive power control (VQ control) to avoid voltage collapse. The conventional VQ control, however, does not meet this requirement because of approximated control. The authors propose a new algorithm for VQ control using recurrent neural networks which have the ability to treat system dynamics. Firstly, they propose the learning algorithm for dynamics and inverse dynamics of the controlled target. Secondly, they apply this algorithm to the VQ control. The authors call this controller 'neuro VQC'. Finally, the usefulness of the neuro VQC is shown in comparison with the conventional VQ controller.<>
{"title":"Voltage controller with recurrent neural networks","authors":"Y. Kojima, Y. Izui, S. Kyomoto, T. Goda","doi":"10.1109/ANN.1993.264345","DOIUrl":"https://doi.org/10.1109/ANN.1993.264345","url":null,"abstract":"An electric power system requires voltage and reactive power control (VQ control) to avoid voltage collapse. The conventional VQ control, however, does not meet this requirement because of approximated control. The authors propose a new algorithm for VQ control using recurrent neural networks which have the ability to treat system dynamics. Firstly, they propose the learning algorithm for dynamics and inverse dynamics of the controlled target. Secondly, they apply this algorithm to the VQ control. The authors call this controller 'neuro VQC'. Finally, the usefulness of the neuro VQC is shown in comparison with the conventional VQ controller.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130722007","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：