Поиск по сайту


   
Дополнительные параметры поиска

Результаты поиска ( Отсортировано по релевантности | Сортировать по дате )


Voltage/VAR Control and Optimization: AI approach

Tomin N., Kurbatsky V., Panasetsky D., Sidorov D., Zhukov A. Voltage/VAR Control and Optimization: AI approach // IFAC-PapersOnLine. Vol.51. No.28. 2018. P.103-108. DOI: 10.1016/j.ifacol.2018.11.685 Volt-VAr control systems provide the optimal solution with remote automatic or manual control of the capacitor banks and tap positions on the voltage regulators. However, such control possesses inherent characteristics of complexity, nonlinearity, inaccuracy and high requirement for control speed, parts...

Теги: machine learning , multi-agent system , power system , random forest , security , volt-var control , decision trees , intelligent agents , learning systems , value engineering , voltage regulators , inherent characteristics , optimal solutions , random forests , tradit
Раздел: ИСЭМ СО РАН
Selecting the key control parameters for the ionospheric total electron content nowcasting

... with some lag, such as the vertical TEC with 12 hours lag, F10.7 with 3 and 15 days lags. The proposed empirical nowcasting models are based on parameters selected by recursive selection of characteristics with determination of their significance using random forest and support vectors methods. Using these key parameters, the linear regression model allows obtaining an estimate on the interval of 4-7 hours with RMS ~4.5 TECU. The machine learning methods such as random forest, support vector method ...

Теги: absolute total electron content , gradient boosting , machine learning , nowcasting , random forest , support vector machine
Раздел: ИСЭМ СО РАН
Machine learning in electric power systems adequacy assessment using Monte-Carlo method

... adequacy assessment using Monte-Carlo method. To attack this problem the novel method is suggested to reduce number of random states to be analyzed. The machine learning methods are employed for electric power system states precalculated classification. Random forest and support vector machine methods are proposed to use for solving this problem. Efficiency of proposed approach is demonstrated on test scheme. © 2017 IEEE. входит

Теги: adequacy assessment , electric power systems , machine learning , monte carlo method , random forest , support vector machine , artificial intelligence , computational efficiency , decision trees , efficiency , learning systems , problem solving , support vector mach
Раздел: ИСЭМ СО РАН
Development of Automatic Intelligent System for On-Line Voltage Security Control of Power Systems

... algorithms enabling security assessment in real time have been proposed over the last years. The paper presents an automatic intelligent system for on-line voltage security control, which is based on the model of decision trees Proximity Driven Streaming Random Forest (PDSRF). In this case, the combination of original properties of PDSRF and capabilities of L-index as a target vector makes it possible to provide the functions of dispatcher warning, localization of critical nodes, and ensure direct interaction ...

Теги: power system , voltage security , control , random forest , security assessment , l-index , stability
Раздел: ИСЭМ СО РАН
Random forest based approach for concept drift handling

Zhukov A.V., Sidorov D.N., Foley A.M. Random forest based approach for concept drift handling // Communications in Computer and Information Science. Vol.661. 2017. P.69-77. ISBN (print): 978-3-319-52920-2; 978-3-319-52919-6. DOI: 10.1007/978-3-319-52920-2_7 Concept drift has potential in ...

Теги: machine learning , decision tree , concept drift , ensemble learning , classification , random forest , classification (of information) , decision trees , image analysis , learning algorithms , learning systems , wind power , aggregation rules , concept drifts , empiri
Раздел: ИСЭМ СО РАН


Телефоны

основной    +7(3952) 500-646
приемная    +7(3952) 42-47-00
факс     +7(3952) 42-67-96
Смотреть справочник