Application of artificial neural networks for online \nvoltage stability monitoring and enhancement of an \nelectric power system
Bibliographic record
Abstract
Due to economic reasons arising out of deregulation and open market of electricity, \nmodem day power systems are being operated closer to their stability limits. When a fault \noccurs, there is a great possibility of occurrence of cascading outages, as observed in the \nAugust 2003 Blackout in the North-East USA and Canada. Power system voltage \nstability is one of the challenging problems faced by the utilities. Innovative methods and \nsolutions are required to evaluate the voltage stability of a power system and implement \nsuitable strategies to enhance the robustness of the power system against voltage stability \nproblems. This is the motivation behind the research carried out as a part of the PhD \nprogram and presented in this dissertation. \nArtificial neural networks (ANNs) have gained widespread attention from \nresearchers in recent years as a tool for online voltage stability assessment. Two major \nareas requiring investigation are identified after doing a thorough survey of the existing \nliterature on online voltage stability monitoring using ANN. The first one is the effective \nmethod of selecting important features among numerous possible measurable parameters \nas potential inputs to the ANN. The second one is the feasibility of using a single ANN \nfor monitoring voltage stability for multiple contingencies. In the first phase of the \nresearch, a regression-based method of computing sensitivities of the voltage stability \nmargin with respect to different parameters is proposed. Using the sensitivity \ninformation, important features are chosen selectively to train separate Multilayer \nPerceptron Networks (MLP) to monitor voltage stability for different contingencies. \nIn the second phase of the research, an enhanced Radial Basis Function Network \n(RBFN) is proposed for online voltage stability monitoring. Important features of the \nproposed RBFN are: (1) the same network is trained for multiple contingencies, thus \neliminating the need for training different ANNs for different contingencies, (2) the \nnumber of neurons in the hidden layers is decided automatically using a sequential \nlearning strategy, (3) the RBFN can be adapted online, with changing operating scenario, \n(4) a network pruning strategy is used to limit the growth of the network size as a result \nof the adaptation process. \nIn the next phase of the research, a sensitivity-based voltage stability \nenhancement method is proposed, considering multiple contingencies. Considering the \nlimitations of the existing analytical methods, the sensitivities of the voltage stability \nmargin with respect to parameters are found by using the RBFN proposed in the second \nphase of the research. Using the sensitivity information, correct amounts of generation \nrescheduling are found by using linear optimization. Case studies are presented \nthroughout different sections of the thesis to illustrate the application of the proposed \nmethods.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".