48 results about "Transient stability assessment" patented technology

The invention provides a method for transient stability assessment and real-time control of an electric system. According to the method, technologies concerning knowledge discovery are introduced to realize the stability assessment and the control of the electric system; and on the basis of establishing a transient stability assessment model, the corresponding relation between the system running condition and the overall stability of the electric system is found out, the inherent running discipline of the electric system are grasped, and the fast assessment of the stable running state of the electric system is realized, therefore, the actual running management of the electric system can be guided. The method has the advantages that timely and effective stability control scheme can be established for the running state which loses stability after great disturbance, and the safe and the stable running of the system can be ensured at lowest price.

The invention relates to a power system transient stability assessment method based on convolution neural network CNN, in particular to power system transient voltage stability online assessment. In order to solve the problem that the traditional transient voltage assessment methods cannot meet the accuracy and rapidity, CNN is introduced into the transient stability assessment of power system. The technical scheme is mainly divided into two parts. The first step is off-line training: pre-processing based on simulation data, obtaining 36-dimensional input feature quantities, forming training set and test set and inputting them into CNN, optimizing the structure and parameters of CNN truss, and generating off-line transient stability assessment model; the second step is to obtain the post-fault PMU measurement data and construct the 36-dimensional feature quantities, input the trained off-line transient stability assessment model, and evaluate the transient voltage online stability state. At present, the traditional transient voltage evaluation method cannot meet the problem of accuracy and rapidity, the error rate is low, and the test time is short.

The invention discloses a rapid screening method of expected failure sets in electric power system transient stability assessment, and belongs to the technical field of an electric power system and the automation thereof. The rapid screening method is based on an extended equal-area criterion (EEAC), adopts a researched calculation example time-varying degree and the transient stability margin, which are reflected by transient stability analysis algorithms with different simplification degrees, as indexes, and combines researched calculation example failure information so as to match and combine into different screening criteria. Expected failure subsets satisfying the screening criteria are screened out in a layered mode from an expected failure universal set, thereby greatly reducing the number of expected failures requiring detailed transient stability analysis. The rapid screening method disclosed by the invention can improve the rapidity of the transient stability assessment under the premise of guaranteeing the accuracy of the transient stability assessment, thereby appropriately coordinating the accuracy and the speed of the transient stability assessment.

The invention discloses a power system transient stability assessment method based on big data, and the method comprises two stages: sample training and result evaluation. The sample training stage comprises the steps: carrying out the centralized training and learning of ELMs through employing big data of a power system, and also completing the confirmation of each transient stability characteristic quantity weight parameter. The result evaluation stage comprises the steps: firstly building a transient stability key characteristic library; secondly extracting key characteristics in current real-time data, and transmitting the key characteristics to a trained EMLs; finally carrying out the comprehensive analysis of the output result of the EMLs through a decision evaluation module, and giving a transient stability assessment result and the confidence of the current result. The method takes big data as the background, is based on the reasonable dimension reduction and complete use of mass data of a power grid, is based on a learning machine cluster, and meets the requirements of complete and real-time safety early warning of an intelligent power grid.

The invention discloses a transient stability assessment method and system based on depth learning, which comprises the following steps: constructing an original feature set of transient stability assessment; establishing an off-line expected accident set; based on mutual information theory, a feature extraction model of a stack denoising automatic encoder being established adaptively, and the multi-layer feature extraction of original input being realized; a support vector machine (SVM) integrated regression model being established to judge the transient stability margin of various operationmodes under fixed expected accidents; generating a plurality of future operation modes and an on-line predicted accident set; the support vector machine integrated regression model corresponding to each expected accident being used to predict the index of transient stability margin, and the severity of the transient stability of the system under different operating modes being classified. Combinedwith the prior distributed parallel computing technology, the invention finally realizes the optimal network structure of the depth learning model with a large number of network nodes and a pluralityof hidden layers adaptively, and can quickly and accurately evaluate the transient stability degree of the power system, so as to meet the online application requirements.

An embodiment of the invention provides an RPTSVM-based power system transient stability assessment method. By adopting an energy function index and a power system index to configure an original feature set, the number of dimensions of the feature set and redundant information can be reduced, and a new idea of sample set configuration is formed; a maximum correlation and minimum redundancy feature selection method is adopted to perform feature compression on the power system index and a projection energy function index, so as to find a power system feature sub set with high power grid transient change sensitivity, so that redundancy information can be further reduced, and number of dimensions of the feature can be reduced; after a regular term reconfigurable classifier is added to the optimization target function by the RPTSVM, power system transient stability assessment is performed, so that transient stability assessment stability can be ensured, the non-full-rank defects of a variance matrix in the transient stability assessment by the PTSVM can be avoided, and the generalization ability of the PTSVM assessment model is improved; and parameter optimization is performed by a genetic algorithm, and the population quantity is reasonably selected, so that the calculation time can be shortened under the premise of ensuring that the optimal parameter combination can be selected.

The invention relates to a power system transient stability determination method based on a support vector machine and belongs to the technical field of power system automatic analysis. The method is characterized by determining an input characteristic set of the SVM (Support Vector Machine) using optimization searching step by step, and further establishing transient stability assessment rules through the SVM. The method comprises a first step of determining an input vector alternative set, an input vector element number, a kernel function of the SVM and a training parameter; a step of generating a training sample and a testing sampling; a step of adding all alternative characteristics into the input characteristic set one by one, training the SVM, and determining a characteristic which enables the SVM classification accuracy to be highest; a step of determining whether the characteristic selection computation is completed or not and output of the input characteristic set; and a final step of training the SVM to obtain the stability rules. According to the invention, the algorithm is easy to implement and the computational complexity is low; the method can be applied to on-line safety and stability assessment of power system at different levels such as regional power systems and provincial power systems in the country; and the system safe and stable operation is effectively ensured under the background that the power grid characteristic is gradually complex.

The invention relates to a power system transient stability assessment method based on a differential evolution extreme learning machine technology. The method comprises the following steps: firstly,simulating fault data under various typical operation modes by using electric power system simulation software; extracting electrical quantity feature from the simulation data, and then inputting theoptimal feature set into the differential evolution limit learning machine for transient stability evaluation. According to the invention, compared with other types of extreme learning machine models,the method has the advantages that the evaluation accuracy is higher, and the method is of great significance to online safety and stability evaluation of the power system.

Embodiments of the invention provide an electric power system transient stability assessment method and device. The method comprises the following steps of: obtaining a feature vector of a to-be-assessed point of an electric power system according to a pre-screened key state variable; respectively calculating a mahalanobis distance between the feature vector of the to-be-assessed point and a feature vector of each sample point in a sample set, and searching sample points adjacent to the to-be-assessed point according to the mahalanobis distances; and obtaining an assessment result of the to-be-assessed point according to a classification decision rule and the adjacent sample points. According to the method and device, the mahalanobis distances between the feature vector of the to-be-assessed point and the feature vectors of the sample points are calculated, and the mahalanobis distances sufficiently consider the relevancy between key state variables in the feature vectors, so that thedistance calculation is more correct, the adjacent sample points of the to-be-assessed points can be correctly searched, and the correctness of the assessment result is further improved.

The invention discloses a transient stability risk assessment method considering the uncertainty of a new energy unit, which generates a predicted fault based on the current operation state of a powernetwork and performs transient stability assessment, and identifies a transient stability key transmission section corresponding to the fault. According to the short-term wind and light intensity forecasting results, the output interval probabilities of each new energy power plant are obtained, and the power intervals and their probabilities of the key transmission sections are calculated by probabilistic tidal current calculation. In order to increase the output of new energy units and evaluate the severity of the fault, the section power interval operating risk is accumulated as a fault risk index. If the risk index of the fault is greater than the threshold value, the measures to reduce the output of the conventional unit shall be taken first under the premise of giving priority to ensure the output of the new energy power plant, and if the requirements are not met, the risk index shall be ensured to be less than the threshold value by limiting the output of the new energy power plant. The method of the invention can comprehensively reflect the operating conditions of the system and discover potential risks and fragile points in the system, thereby exerting the operating potential of the power grid.

The invention discloses a power system transient stability evaluation method. The method comprises the steps of S1, establishing an initial sample set through a short-term disturbance track of a generator obtained through offline simulation, and randomly dividing the initial sample set into a training set and a test set; S2, inputting the training set into a capsule neural network, arranging eachelectrical quantity in a regional manner, sorting according to the disturbed degree of the generator at an initial stage of a fault, setting different network parameters, and training to obtain an optimal capsule neural network on the basis of comprehensive indexes; and S3, performing online transient stability evaluation on the test set sample by using the trained optimal capsule neural network.The method can realize rapid prediction of transient stability, and has the advantages of ''rapid measurement, rapid resolution, rapid control'' and the like.

The present invention relates to a transient stability assessment input characteristic validity analysis method based on improved Sammon mapping. The method comprises removing redundant data in power grid operation sample data by using a fuzzy C-means clustering algorithm; obtaining three-dimensional data having the maximum contribution rate in the power grid operation sample data by using a principal component analysis method as initial values of a low-dimensional space mapping point coordinate vector of the power grid operation sample data; correcting the initial values of the low-dimensional space mapping point coordinate vector of the power grid operation sample data by using an iteration correction method, and obtaining the low-dimensional space mapping point coordinate vector of the power grid operation sample data; and judging validity of the power grid operation sample data according to the low-dimensional space mapping point coordinate vector of the power grid operation sample data. According to the method, when transient stability assessment is performed on a power system, the initial values are provided for iteration by using the principal component analysis method to stabilize a mapping result, low-dimensional space mapping point coordinates are solved by using the iteration correction method, and the solving speed is accelerated.

The invention relates to a rapid assessment method for transient stability of a super-large urban power grid based on dynamic security domains, and the technical feature thereof is that the method comprises the following steps: step 1, determine system data in a potential operation mode of the system to form a system differential algebraic equation; step 2, according to the system flow section under the large operation mode, screening heavy-duty lines and substations, and supplementing high-power nodes to solve the pre-fault equilibrium point and form a large disturbance expected accident set;step 3, after generating a transient stability assessment scene set, numbering the assessment scenes and starting the assessment of the dynamic security domains; step 4, determining the measures andfault response time for the expected accidents, searching for a transient stability critical equilibrium point, and calculating the dynamic security domains for each transient stability assessment scene; and step 5, assessing the transient stability of the power grid after the occurrence of the expected accident on the system, and calculating the stability margin. The method can shorten the assessment time of the transient stability of the system and can give a stability margin.

The invention discloses an intelligent transient stability evaluation system for a power grid. The system mainly comprises a phasor measurement unit, a preprocessing unit, a stability classification module, a key generator module, a stability classification simple logic processing unit, a key generator simple logic processing unit and an auxiliary decision module. According to the evaluation system provided by the invention, the same PMU samples are used as input, transient stability classification and key generator identification are respectively used as output, a double-task stability evaluation model is established, and the stability classification and key generator identification given by the double-task stability evaluation model are subjected to simple logic processing and then are used as input of an auxiliary decision-making system, dual-task interaction verification discrimination logic is adopted, mutual check of prediction results is realized, and a final stability discrimination result and a key generator set are obtained; meanwhile, uncertain samples difficult to discriminate are screened out, so the prediction accuracy of intelligent transient stability assessment andthe reliability of the results can be remarkably improved, and safe operation and risk regulation of a power grid are facilitated.

The present invention proposes a simple and effective method for evaluating transient stability probability in the field of power system transient stability assessment for a power system considering wind farm uncertainty and correlation. An extended dynamic security domain method is used, and linear combination of node injection vectors is used to represent transient stability data in a given fault condition. The three-point estimation method and the Cornish-Fisher expansion method are improved to deal with uncertainty and correlation between different wind farms. A large number of simulationcalculations are performed on an improved New England system, and a result shows that calculation efficiency of the method of the present invention is significantly higher than that of a Monte Carlo method, and precision is high.

A method for selecting key features of power system transient stability considering class imbalance includes the following steps: S1, constructing original feature set of transient stability assessment by using time dimension statistics of electrical state; S2, generating a preset number of sample sets; 3, define a weighted accuracy rate CWA of a comprehensive evaluation index category according to an evaluation criterion selecte from transient stability evaluation characteristics; S4, the key features of transient stability assessment are screened by using the encapsulation method which combines forward search and transfinite learning machine. Aiming at the unbalanced characteristics of the transient stability of the power system, the invention proposes two criteria to be satisfied for the selection of the key features, and on the basis of the two criteria, a class weighted accuracy index is proposed as an evaluation index for the selection of the key features. Taking the new evaluation index as the feature selection standard, the key features of transient stability are searched by using the encapsulation method of forward search and transfinite learning machine, and the key features of instability class with higher identification degree are excavated, which meets the actual requirements of power network security and stability analysis.

The embodiment of the invention provides a transient stability assessment method and system based on a power flow vector Minkoff base distance. According to the method, on the basis of a transient stability assessment method based on the clustering of the operation conditions, an integrated transient stability assessment method based on a power flow vector Minkoff-based distance is designed by combining a design idea of a current transient stability assessment integrated model. According to the method, the difference of the system transient stability under different working conditions is considered, and a plurality of sub-evaluation models are weighted and integrated according to the similarity of the working conditions, so that the higher the matching degree of the system transient stability is, the larger the influence of the sub-evaluation models on the total evaluation result is. Compared with a single evaluation model, the method has higher generalization, and the evaluation reliability and generalization are improved. In addition, the output of the base model is directly utilized by the integrated model, more information is reserved when the final output is obtained through integration, and the accuracy is improved.

The invention discloses a method of evaluating the transient stability of a wind farm system considering the influence of a random wind speed. First, an energy function model of the wind farm system is established, a wind speed random process model is then constructed, the wind speed is expressed as a Wiener process, N trajectories of the wind speeds are solved by using a random Euler method, theN trajectories are used as input of system state equations, the N trajectories of each input amount in the energy function are obtained, all input amount trajectories corresponding to each wind speedtrajectory are used as a group, the energy function trajectory corresponding to the wind speed trajectory is calculated according to the energy function model, and finally, the energy margin of the wind farm system under a transient condition is solved by adopting a potential energy boundary method, and transient stability assessment of the wind farm system is completed. The energy function is combined with the random fluctuation of the wind speed in a time domain for constructing the transient stability evaluation index of the wind farm system, and the system transient stability under the random fluctuation of the wind speed is quantitatively analyzed.

The invention provides a transient stability evaluation method and device for a power system, electronic equipment and a storage medium. The method comprises the following steps: acquiring power flow information and topological information of the power system; determining a power system power flow characteristic graph according to the power system power flow information and the power system topology information; inputting node features and topological features of the power flow feature graph of the power system into a transient stability evaluation model to obtain transient stability and transient stability indexes of the power system after each anticipated fault in an anticipated fault set output by the transient stability evaluation model occurs; wherein the transient stability evaluation model is used for carrying out feature learning on the power flow feature map of the power system and carrying out coupling analysis on the transient stability and transient stability indexes of the power system. According to the method, the device, the electronic equipment and the storage medium provided by the invention, the transient stability and the transient stability index of the power system can be quickly evaluated and predicted after each anticipated fault in the anticipated fault set occurs.