Interlocks have been in use ever since protective relaying schemes were implemented for power devices like generators, transformers, transmission lines, etc. Although the science of protective relaying has undergone marked changes and improvements, the interlocking philosophy has not changed much. Recently with the availability of programmable logic controllers (PLCs), interlocking schemes have been implemented by means of these devices with basic philosophy of logic remaining the same. This paper suggests the implementation of interlocking schemes with artificial neural networks employing threshold logic unit (TLU) elements. It is demonstrated that while the basic hardware required is same as that of any common PLC, the suggested system will have added flexibility, adaptability to various switchyard modifications, electrical topology changes and equipment/switchyard conditions as well as network complexity.<>
{"title":"Application of artificial neural networks in adaptive interlocking systems","authors":"S. Agarwal, V. N. Prabhu","doi":"10.1109/ANN.1993.264306","DOIUrl":"https://doi.org/10.1109/ANN.1993.264306","url":null,"abstract":"Interlocks have been in use ever since protective relaying schemes were implemented for power devices like generators, transformers, transmission lines, etc. Although the science of protective relaying has undergone marked changes and improvements, the interlocking philosophy has not changed much. Recently with the availability of programmable logic controllers (PLCs), interlocking schemes have been implemented by means of these devices with basic philosophy of logic remaining the same. This paper suggests the implementation of interlocking schemes with artificial neural networks employing threshold logic unit (TLU) elements. It is demonstrated that while the basic hardware required is same as that of any common PLC, the suggested system will have added flexibility, adaptability to various switchyard modifications, electrical topology changes and equipment/switchyard conditions as well as network complexity.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"1 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":"128746689","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}
Adaptive relaying has the validity for a wide variety of applications. Here a typical problem of maloperation is considered. The application of the modified multilayer perceptron (MLP) mode can successfully avoid the maloperation of a relay. For the cases considered, it shows encouraging results. The advantage associated with the presented MLP model is that the modified characteristic can be defined in the absence of a definite analytical model since the artificial neural network (ANN) can learn it through input-output patterns. The methodology can be extended to many adaptive protective schemes. This report just opens new vistas for the exploration of the application of ANNs in adaptive protective schemes, and further investigations could lead to increased confidence.<>
{"title":"Adaptive relaying using artificial neural network","authors":"S. Khaparde, N. Warke, S. Agarwal","doi":"10.1109/ANN.1993.264307","DOIUrl":"https://doi.org/10.1109/ANN.1993.264307","url":null,"abstract":"Adaptive relaying has the validity for a wide variety of applications. Here a typical problem of maloperation is considered. The application of the modified multilayer perceptron (MLP) mode can successfully avoid the maloperation of a relay. For the cases considered, it shows encouraging results. The advantage associated with the presented MLP model is that the modified characteristic can be defined in the absence of a definite analytical model since the artificial neural network (ANN) can learn it through input-output patterns. The methodology can be extended to many adaptive protective schemes. This report just opens new vistas for the exploration of the application of ANNs in adaptive protective schemes, and further investigations could lead to increased confidence.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"8 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":"132712070","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}
A. Ishigame, Y. Takagi, S. Kawamoto, T. Taniguchi, H. Tanaka
This paper presents a method of structural control of electric power networks for improving their stability. The method is based on the FACTS concept, a genetic algorithm and neural network. FACTS equipment will provide some new ways for improving stability by controlling the reactance of transmission lines in terms of structure control of the power network. A case study with a multimachine power system is presented and discussed.<>
{"title":"Structural control based on genetic algorithm and neural network for electric power systems","authors":"A. Ishigame, Y. Takagi, S. Kawamoto, T. Taniguchi, H. Tanaka","doi":"10.1109/ANN.1993.264295","DOIUrl":"https://doi.org/10.1109/ANN.1993.264295","url":null,"abstract":"This paper presents a method of structural control of electric power networks for improving their stability. The method is based on the FACTS concept, a genetic algorithm and neural network. FACTS equipment will provide some new ways for improving stability by controlling the reactance of transmission lines in terms of structure control of the power network. A case study with a multimachine power system is presented and discussed.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"6 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":"128624570","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 an experimental study of the discrimination of partial discharge (PD) signals from external noise in a cross-linked polyethylene (XLPE) power cable by using a neural network (NN) system. Measurement of PD signal and external noise was carried out with a PD pulse recorder for a 66 kV XLPE cable with an artificial defect and a drill. The NN was a three-layer artificial neural system with feedforward connections, and its learning method was a backpropagation algorithm. Its input information was a combination of the discharge magnitude, the number of pulse counts, and the phase angle of applied voltage.<>
{"title":"Discrimination of partial discharge from noise in XLPE cable lines using a neural network","authors":"G. Katsuta, H. Suzuki, H. Eshima, T. Endoh","doi":"10.1109/ANN.1993.264291","DOIUrl":"https://doi.org/10.1109/ANN.1993.264291","url":null,"abstract":"This paper describes an experimental study of the discrimination of partial discharge (PD) signals from external noise in a cross-linked polyethylene (XLPE) power cable by using a neural network (NN) system. Measurement of PD signal and external noise was carried out with a PD pulse recorder for a 66 kV XLPE cable with an artificial defect and a drill. The NN was a three-layer artificial neural system with feedforward connections, and its learning method was a backpropagation algorithm. Its input information was a combination of the discharge magnitude, the number of pulse counts, and the phase angle of applied voltage.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"120 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114057985","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 systematic method to find several local minima for general nonlinear optimizatioin problems. They develop some analytical results for a quasi-gradient system and reflected gradient system and apply them to explore the topological aspects of the critical points of the objective function. By properly switching between a quasi-gradient system and a reflected gradient system, the proposed method can obtain a set of local minima.<>
{"title":"A systematic search method for obtaining multiple local optimal solutions of nonlinear programming problems","authors":"H. Chiang, C. Chu","doi":"10.1109/ANN.1993.264304","DOIUrl":"https://doi.org/10.1109/ANN.1993.264304","url":null,"abstract":"The authors propose a systematic method to find several local minima for general nonlinear optimizatioin problems. They develop some analytical results for a quasi-gradient system and reflected gradient system and apply them to explore the topological aspects of the critical points of the objective function. By properly switching between a quasi-gradient system and a reflected gradient system, the proposed method can obtain a set of local minima.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"54 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":"115176024","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 new approach for short term load forecasting using a diagonal recurrent neural network with an adaptive learning rate. The fully connected recurrent neural network (FRNN), where all neurons are coupled to one another, is difficult to train and to converge in a short time. The DRNN is a modified model of FRNN. It requires fewer weights than FRNN and rapid convergence has been demonstrated. A dynamic backpropagation algorithm coupled with an adaptive learning rate guarantees even faster convergence. To consider the effect of seasonal load variation on the accuracy of the proposed forecasting model, forecasting accuracy is evaluated throughout a whole year. Simulation results show that the forecast accuracy is improved.<>
{"title":"Short-term load forecasting using diagonal recurrent neural network","authors":"K.Y. Lee, T. Choi, C. Ku, J.H. Park","doi":"10.1109/ANN.1993.264286","DOIUrl":"https://doi.org/10.1109/ANN.1993.264286","url":null,"abstract":"This paper presents a new approach for short term load forecasting using a diagonal recurrent neural network with an adaptive learning rate. The fully connected recurrent neural network (FRNN), where all neurons are coupled to one another, is difficult to train and to converge in a short time. The DRNN is a modified model of FRNN. It requires fewer weights than FRNN and rapid convergence has been demonstrated. A dynamic backpropagation algorithm coupled with an adaptive learning rate guarantees even faster convergence. To consider the effect of seasonal load variation on the accuracy of the proposed forecasting model, forecasting accuracy is evaluated throughout a whole year. Simulation results show that the forecast accuracy is improved.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"15 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":"122245132","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}
B. Kermanshahi, C.H. Poskar, G. Swift, P. McLaren, W. Pedrycz, W. Buhr, A. Silk
This paper describes the application of an artificial neural network to short term load forecasting. One of the most popular artificial neural network models, the 3-layer backpropagation model, is used to learn the relationship between 86 inputs, which are believed to have significant effects on the loads, and 24 outputs: one for each hourly load of the day. Historical data collected over a period of 2 years (e.g. calendar years 1989 and 1990) is used to train the proposed ANN network. The results of the proposed ANN networks have been compared to those of the present system (multiple linear regression) and show an improved forecast capability.<>
{"title":"Artificial neural network for forecasting daily loads of a Canadian electric utility","authors":"B. Kermanshahi, C.H. Poskar, G. Swift, P. McLaren, W. Pedrycz, W. Buhr, A. Silk","doi":"10.1109/ANN.1993.264330","DOIUrl":"https://doi.org/10.1109/ANN.1993.264330","url":null,"abstract":"This paper describes the application of an artificial neural network to short term load forecasting. One of the most popular artificial neural network models, the 3-layer backpropagation model, is used to learn the relationship between 86 inputs, which are believed to have significant effects on the loads, and 24 outputs: one for each hourly load of the day. Historical data collected over a period of 2 years (e.g. calendar years 1989 and 1990) is used to train the proposed ANN network. The results of the proposed ANN networks have been compared to those of the present system (multiple linear regression) and show an improved forecast capability.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"8 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":"134278471","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 method for controlling the voltage total harmonic distortion (THD) with a parallel simulated annealing technique. The nonlinear relationship between voltage harmonics and the voltage THD is identified using the revised group method of data handling (RGMDH) based on the self-organization technique. The voltage THD is controlled by some feature variables to decrease harmonic distortion. A simulated annealing (SA) technique is applied to minimize the voltage distortion factor. SA is a stochastic optimization method based on a physical annealing phenomenon. In order to obtain better solutions, this paper proposes a parallel simulated annealing (PSA) technique. PSA is a useful method because of the multi-point search. The effectiveness of the proposed method is demonstrated with test data.<>
{"title":"Control of harmonic voltage distortion with parallel simulated annealing","authors":"H. Mori, K. Takeda","doi":"10.1109/ANN.1993.264328","DOIUrl":"https://doi.org/10.1109/ANN.1993.264328","url":null,"abstract":"This paper proposes a method for controlling the voltage total harmonic distortion (THD) with a parallel simulated annealing technique. The nonlinear relationship between voltage harmonics and the voltage THD is identified using the revised group method of data handling (RGMDH) based on the self-organization technique. The voltage THD is controlled by some feature variables to decrease harmonic distortion. A simulated annealing (SA) technique is applied to minimize the voltage distortion factor. SA is a stochastic optimization method based on a physical annealing phenomenon. In order to obtain better solutions, this paper proposes a parallel simulated annealing (PSA) technique. PSA is a useful method because of the multi-point search. The effectiveness of the proposed method is demonstrated with test data.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"60 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":"132317119","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 multi-layered perceptron (MLP) artificial neural network has been shown to be an effective tool for load forecasting. Little attention, though, has been paid to the manner in which data is partitioned prior to training. The manner in which the data is partitioned dictates much of the structure of the corresponding neural network. In many neural network forecasters, a different neural network is used for each day. The authors compare the performance of a daily partitioned neural network and hourly partitioned neural network. In the experiments, the hourly partitioned neural network forecaster has better performance than the daily partitioned neural network forecaster.<>
{"title":"Data partitioning for training a layered perceptron to forecast electric load","authors":"M. El-Sharkawi, R. Marks, S. Oh, C.M. Brace","doi":"10.1109/ANN.1993.264348","DOIUrl":"https://doi.org/10.1109/ANN.1993.264348","url":null,"abstract":"The multi-layered perceptron (MLP) artificial neural network has been shown to be an effective tool for load forecasting. Little attention, though, has been paid to the manner in which data is partitioned prior to training. The manner in which the data is partitioned dictates much of the structure of the corresponding neural network. In many neural network forecasters, a different neural network is used for each day. The authors compare the performance of a daily partitioned neural network and hourly partitioned neural network. In the experiments, the hourly partitioned neural network forecaster has better performance than the daily partitioned neural network forecaster.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"29 4 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":"133587228","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 introduces a chaotic neural net model to calculate the multiple load flow solutions, especially the lower voltage solution for power system voltage stability monitoring. Chaos is now understood to be an inherent feature of many nonlinear systems. Unlike Lyapunov dynamics, the proposed neural net aimed at dealing with global optimization problems, is based on the chaotic dynamics regime which allows neural networks to be temporarily unstable, keeping stability due to convergent dynamics. Therefore, by converting the load flow problem into an energy-minimum problem and taking advantage of 'chaotic itinerary', multiple load flow solutions can be obtained. Numerical calculations have been undertaken in this paper, where a number of fractual structures of orbit and Poincare maps plotted with varying phases were provided to certify chaos occurrence, and a practical power system was also used to show the efficiency and effectiveness of the proposed approach.<>
{"title":"Application of chaotic simulation and self-organizing neural net to power system voltage stability monitoring","authors":"L. Chen","doi":"10.1109/ANN.1993.264320","DOIUrl":"https://doi.org/10.1109/ANN.1993.264320","url":null,"abstract":"This paper introduces a chaotic neural net model to calculate the multiple load flow solutions, especially the lower voltage solution for power system voltage stability monitoring. Chaos is now understood to be an inherent feature of many nonlinear systems. Unlike Lyapunov dynamics, the proposed neural net aimed at dealing with global optimization problems, is based on the chaotic dynamics regime which allows neural networks to be temporarily unstable, keeping stability due to convergent dynamics. Therefore, by converting the load flow problem into an energy-minimum problem and taking advantage of 'chaotic itinerary', multiple load flow solutions can be obtained. Numerical calculations have been undertaken in this paper, where a number of fractual structures of orbit and Poincare maps plotted with varying phases were provided to certify chaos occurrence, and a practical power system was also used to show the efficiency and effectiveness of the proposed approach.<<ETX>>","PeriodicalId":121897,"journal":{"name":"[1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems","volume":"40 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":"116563757","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：