Dynamic economic load dispatching is one of the optimization problems in power system operation. Since an optimization is required under severe constraints, all constraints cannot be taken into account. In this paper, the dynamic economic load dispatching is formulated using an artificial neural network as against a formulation by which a solution had to be obtained by nonlinear programming. The present method uses a probabilistic artificial neural network and effectively handles constraints by a heuristic method. It outputs a suboptimal and feasible result by applying load patterns simulating a real load to a reduced 3 thermal generating unit system.<>
{"title":"An application of artificial neural network to dynamic economic load dispatching","authors":"Y. Fukuyama, Y. Ueki","doi":"10.1109/ANN.1991.213466","DOIUrl":"https://doi.org/10.1109/ANN.1991.213466","url":null,"abstract":"Dynamic economic load dispatching is one of the optimization problems in power system operation. Since an optimization is required under severe constraints, all constraints cannot be taken into account. In this paper, the dynamic economic load dispatching is formulated using an artificial neural network as against a formulation by which a solution had to be obtained by nonlinear programming. The present method uses a probabilistic artificial neural network and effectively handles constraints by a heuristic method. It outputs a suboptimal and feasible result by applying load patterns simulating a real load to a reduced 3 thermal generating unit system.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123921376","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. B. R. Kumar, A. Ipakchi, Vladimir Brandwajn, M. El-Sharkawi, Gerald W. Cauley
The computational requirements associated with dynamic security assessment (DSA) by conventional methods are two or three orders of magnitude more than the requirements for static security assessment. Therefore comprehensive on-line DSA is infeasible in present power system control centers. The exploitation of novel techniques to solve the problems of DSA is essential for on-line implementation. The authors set forth the requirements of DSA for a large-scale power system, followed by a description of the capabilities and limitations of neural network methods in meeting these requirements.<>
{"title":"Neural networks for dynamic security assessment of large-scale power systems: requirements overview","authors":"A. B. R. Kumar, A. Ipakchi, Vladimir Brandwajn, M. El-Sharkawi, Gerald W. Cauley","doi":"10.1109/ANN.1991.213499","DOIUrl":"https://doi.org/10.1109/ANN.1991.213499","url":null,"abstract":"The computational requirements associated with dynamic security assessment (DSA) by conventional methods are two or three orders of magnitude more than the requirements for static security assessment. Therefore comprehensive on-line DSA is infeasible in present power system control centers. The exploitation of novel techniques to solve the problems of DSA is essential for on-line implementation. The authors set forth the requirements of DSA for a large-scale power system, followed by a description of the capabilities and limitations of neural network methods in meeting these requirements.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127643007","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}
Environmental regulations require Ontario Hydro to conduct a series of aquatic surveys to monitor fish population in the neighbourhoods of the generating stations. Studies are currently under way in an attempt to replace the current netting methods used for the survey with sonar based methods which will be nonconsumptive as well as less expensive. The authors look at the use of multi-layer perceptrons to identify the fish from their sonar echoes. The current phase of the work investigates the impact of preprocessing techniques and the use of networks in parallel on the generalization properties. It is found that significant improvements are possible using simple combinations of three-layer perceptrons which have been trained using outputs from different preprocessors. In the test case studied, over 93 percent of the targets were identified correctly by the network.<>
{"title":"Fish identification from sonar echoes-preprocessing and parallel networks","authors":"N. Ramani, W.G. Hanson, P. Patrick, H. Anderson","doi":"10.1109/ANN.1991.213481","DOIUrl":"https://doi.org/10.1109/ANN.1991.213481","url":null,"abstract":"Environmental regulations require Ontario Hydro to conduct a series of aquatic surveys to monitor fish population in the neighbourhoods of the generating stations. Studies are currently under way in an attempt to replace the current netting methods used for the survey with sonar based methods which will be nonconsumptive as well as less expensive. The authors look at the use of multi-layer perceptrons to identify the fish from their sonar echoes. The current phase of the work investigates the impact of preprocessing techniques and the use of networks in parallel on the generalization properties. It is found that significant improvements are possible using simple combinations of three-layer perceptrons which have been trained using outputs from different preprocessors. In the test case studied, over 93 percent of the targets were identified correctly by the network.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134331907","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 new fast method for supplying preventive measures to avoid the failure of electromagnetic voltage transformers (EMVT) due to sustained overvoltage on switch-off is proposed. This method makes full use of the characteristics of artificial neural networks and utilizes the Kohonen network model to design a classifier which can fast supply a satisfactory solution to prevent EMVT damage due to a sustained overvoltage on switch-off. Tests on a 110 kV EMVT show that the fast method has improved protection performance.<>
{"title":"A new fast method for supplying measures to avoid the high voltage mode of electromagnetic voltage transformer","authors":"Y. Jilai, Guo Zhizhong, L. Zhuo","doi":"10.1109/ANN.1991.213460","DOIUrl":"https://doi.org/10.1109/ANN.1991.213460","url":null,"abstract":"A new fast method for supplying preventive measures to avoid the failure of electromagnetic voltage transformers (EMVT) due to sustained overvoltage on switch-off is proposed. This method makes full use of the characteristics of artificial neural networks and utilizes the Kohonen network model to design a classifier which can fast supply a satisfactory solution to prevent EMVT damage due to a sustained overvoltage on switch-off. Tests on a 110 kV EMVT show that the fast method has improved protection performance.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124867279","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 present an application of fuzzy control to a synchronous machine in a power system using the neural network theory. In this method, the membership function is determined by using the learning process of the neural network. For the RHS (right hand side) of fuzzy rules, they propose to use the optimal controls so that they can control the system even if the system is operated at some other operating points than the linearized point. The machine power output is considered as the change of operating points. Although the control using the proposed method is not so good as the control using the optimal control method at the linearized point, one can control the power system by the proposed method at wider ranges than the optimal control method.<>
{"title":"Application of neural network based fuzzy control to power system generator","authors":"K. Saitoh, S. Iwamoto","doi":"10.1109/ANN.1991.213485","DOIUrl":"https://doi.org/10.1109/ANN.1991.213485","url":null,"abstract":"The authors present an application of fuzzy control to a synchronous machine in a power system using the neural network theory. In this method, the membership function is determined by using the learning process of the neural network. For the RHS (right hand side) of fuzzy rules, they propose to use the optimal controls so that they can control the system even if the system is operated at some other operating points than the linearized point. The machine power output is considered as the change of operating points. Although the control using the proposed method is not so good as the control using the optimal control method at the linearized point, one can control the power system by the proposed method at wider ranges than the optimal control method.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130160062","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 examine the usefulness of the feedforward neural network as a controller. For illustrative purposes, the authors consider the case of controlling two-dimensional linear systems. Observations are then made which generalize to higher dimensions and nonlinear systems. Examples are provided to verify the results. In particular, a classical power system stabilizer is examined to demonstrate the feasibility of using a neural controller.<>
{"title":"Dynamical implications of using neural networks as controllers","authors":"R. J. Thomas, E. Sakk","doi":"10.1109/ANN.1991.213511","DOIUrl":"https://doi.org/10.1109/ANN.1991.213511","url":null,"abstract":"The authors examine the usefulness of the feedforward neural network as a controller. For illustrative purposes, the authors consider the case of controlling two-dimensional linear systems. Observations are then made which generalize to higher dimensions and nonlinear systems. Examples are provided to verify the results. In particular, a classical power system stabilizer is examined to demonstrate the feasibility of using a neural controller.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127172669","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 author presents a method for determining power system topological observability with a stochastic neural network. The proposed method is based on the Boltzmann machine that can cope with stochastic behavior of neurons. The Boltzmann machine is useful for solving combinatorial problems since it can avoid local minima. In this paper, a revised Boltzmann machine is proposed to improve the convergence characteristics. A squashing function is utilized to decrease the number of neurons in handling the inequality constraints of the topological observability problem.<>
{"title":"Application of a revised Boltzmann machine to topological observability analysis","authors":"H. Mori","doi":"10.1109/ANN.1991.213462","DOIUrl":"https://doi.org/10.1109/ANN.1991.213462","url":null,"abstract":"The author presents a method for determining power system topological observability with a stochastic neural network. The proposed method is based on the Boltzmann machine that can cope with stochastic behavior of neurons. The Boltzmann machine is useful for solving combinatorial problems since it can avoid local minima. In this paper, a revised Boltzmann machine is proposed to improve the convergence characteristics. A squashing function is utilized to decrease the number of neurons in handling the inequality constraints of the topological observability problem.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126404061","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 author presents an artificial neural net based method for evaluating power system dynamic stability. An adaptive pattern recognition technique is utilized to estimate an index for power system dynamic stability so that computational efforts are reduced and numerical instability problems are avoided. The proposed method is based on a multi-layer feedforward perceptron.<>
{"title":"An artificial neural-net based method for estimating power system dynamic stability index","authors":"H. Mori","doi":"10.1109/ANN.1991.213510","DOIUrl":"https://doi.org/10.1109/ANN.1991.213510","url":null,"abstract":"The author presents an artificial neural net based method for evaluating power system dynamic stability. An adaptive pattern recognition technique is utilized to estimate an index for power system dynamic stability so that computational efforts are reduced and numerical instability problems are avoided. The proposed method is based on a multi-layer feedforward perceptron.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120968382","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}
Stochastically perturbed feature data is said to be jittered. Jittered data has a convolutional smoothing effect in the classification (or regression) space. Parametric knowledge of the jitter can be used to perturb the training cost function of the neural network so that more efficient training can be performed. The improvement is more striking when the addended cost function is used in a query based learning procedure.<>
{"title":"Query based learning in a multilayered perceptron in the presence of data jitter","authors":"Seho Oh, R. Marks, M. El-Sharkawi","doi":"10.1109/ANN.1991.213500","DOIUrl":"https://doi.org/10.1109/ANN.1991.213500","url":null,"abstract":"Stochastically perturbed feature data is said to be jittered. Jittered data has a convolutional smoothing effect in the classification (or regression) space. Parametric knowledge of the jitter can be used to perturb the training cost function of the neural network so that more efficient training can be performed. The improvement is more striking when the addended cost function is used in a query based learning procedure.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123303827","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. Jayaraman, K. Ashenayi, M. O. Durham, R. Strattan
The correction of these power system distortions using neural networks is presented. A multi-layer neural network is trained (using error back propagation) to correct the distorted current waves. Based on the results obtained artificial neural network seems to offer a good solution for the important problem of correcting power system harmonic distortion.<>
{"title":"Neural net based correction of power system distortion caused by switching power supplies","authors":"B. Jayaraman, K. Ashenayi, M. O. Durham, R. Strattan","doi":"10.1109/ANN.1991.213478","DOIUrl":"https://doi.org/10.1109/ANN.1991.213478","url":null,"abstract":"The correction of these power system distortions using neural networks is presented. A multi-layer neural network is trained (using error back propagation) to correct the distorted current waves. Based on the results obtained artificial neural network seems to offer a good solution for the important problem of correcting power system harmonic distortion.<<ETX>>","PeriodicalId":119713,"journal":{"name":"Proceedings of the First International Forum on Applications of Neural Networks to Power Systems","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1991-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129140081","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：