2012 · 16 citations · 1 references
ComputingComputer ScienceArtificial IntelligenceForecastingMachine LearningLoad ForecastingShort-term ForecastingTime Series ForecastingTime Series PredictionHybrid Load ForecastingInput-output ModelingLoad Pattern AnalysisMemory SpaceNeural ForecastingNeural Time Series ForecastingShort-term Load ForecastingTraining Time
This paper represents comparison of two artificial intelligence based hybrid models for short term load forecasting (STLF). Models have the same input/output architecture and are built on SVM and ANN technologies, respectively. Algorithm consists of two modules connected in a sequence, and output from first module is connected as additional input to second module. First module acts as a predictor of maximal load of forecasting day and second acts as hourly load predictor. Models are part of large STLF solution and in respect to computational and memory limitations simple input space is designed. This architecture enables short training time which is targeted for frequent re-training needs in modern utilities due to frequent change in customer number and behavior.
1
Frequency Responses of MV voltage transformers in the range of 50 Hz to 10 kHz