In recent years, advances in sensor technologies and expansion of smart meters have resulted in m... more In recent years, advances in sensor technologies and expansion of smart meters have resulted in massive growth of energy data sets. These Big Data have created new opportunities for energy prediction, but at the same time, they impose new challenges for traditional technologies. On the other hand, new approaches for handling and processing these Big Data have emerged, such as MapReduce, Spark, Storm, and Oxdata H2O. This paper explores how findings from machine learning with Big Data can benefit energy consumption prediction. An approach based on local learning with support vector regression (SVR) is presented. Although local learning itself is not a novel concept, it has great potential in the Big Data domain because it reduces computational complexity. The local SVR approach presented here is compared to traditional SVR and to deep neural networks with an H2O machine learning platform for Big Data. Local SVR outperformed both SVR and H2O deep learning in terms of prediction accuracy and computation time. Especially significant was the reduction in training time; local SVR training was an order of magnitude faster than SVR or H2O deep learning.
Advances in sensor technologies and the proliferation of smart meters have resulted in an explosi... more Advances in sensor technologies and the proliferation of smart meters have resulted in an explosion of energy-related data sets. These Big Data have created opportunities for development of new energy services and a promise of better energy management and conservation. Sensor-based energy forecasting has been researched in the context of office buildings, schools, and residential buildings. This paper investigates sensor-based forecasting in the context of event-organizing venues, which present an especially difficult scenario due to large variations in consumption caused by the hosted events. Moreover, the significance of the data set size, specifically the impact of temporal granularity, on energy prediction accuracy is explored. Two machine-learning approaches, neural networks (NN) and support vector regression (SVR), were considered together with three data granularities: daily, hourly, and 15 minutes. The approach has been applied to a large entertainment venue located in Ontario, Canada. Daily data intervals resulted in higher consumption prediction accuracy than hourly or 15-min readings, which can be explained by the inability of the hourly and 15-min models to capture random variations. With daily data, the NN model achieved better accuracy than the SVR; however, with hourly and 15-min data, there was no definitive dominance of one approach over another. Accuracy of daily peak demand prediction was significantly higher than accuracy of consumption prediction.
Electricity price, consumption, and demand forecasting has been a topic of research interest for ... more Electricity price, consumption, and demand forecasting has been a topic of research interest for a long time. The proliferation of smart meters has created new opportunities in energy prediction. This paper investigates energy cost forecasting in the context of entertainment event-organizing venues, which poses significant difficulty due to fluctuations in energy demand and wholesale electricity prices. The objective is to predict the overall cost of energy consumed during an entertainment event. Predictions are carried out separately for each event category and feature selection is used to select the most effective combination of event attributes for each category. Three machine learning approaches are considered: k-nearest neighbor (KNN) regression, support vector regression (SVR) and neural networks (NN). These approaches are evaluated on a case study involving a large event venue in Southern Ontario. In terms of prediction accuracy, KNN regression achieved the lowest average error. Error rates varied greatly among different event categories.
In recent years, advances in sensor technologies and expansion of smart meters have resulted in m... more In recent years, advances in sensor technologies and expansion of smart meters have resulted in massive growth of energy data sets. These Big Data have created new opportunities for energy prediction, but at the same time, they impose new challenges for traditional technologies. On the other hand, new approaches for handling and processing these Big Data have emerged, such as MapReduce, Spark, Storm, and Oxdata H2O. This paper explores how findings from machine learning with Big Data can benefit energy consumption prediction. An approach based on local learning with support vector regression (SVR) is presented. Although local learning itself is not a novel concept, it has great potential in the Big Data domain because it reduces computational complexity. The local SVR approach presented here is compared to traditional SVR and to deep neural networks with an H2O machine learning platform for Big Data. Local SVR outperformed both SVR and H2O deep learning in terms of prediction accuracy and computation time. Especially significant was the reduction in training time; local SVR training was an order of magnitude faster than SVR or H2O deep learning.
Advances in sensor technologies and the proliferation of smart meters have resulted in an explosi... more Advances in sensor technologies and the proliferation of smart meters have resulted in an explosion of energy-related data sets. These Big Data have created opportunities for development of new energy services and a promise of better energy management and conservation. Sensor-based energy forecasting has been researched in the context of office buildings, schools, and residential buildings. This paper investigates sensor-based forecasting in the context of event-organizing venues, which present an especially difficult scenario due to large variations in consumption caused by the hosted events. Moreover, the significance of the data set size, specifically the impact of temporal granularity, on energy prediction accuracy is explored. Two machine-learning approaches, neural networks (NN) and support vector regression (SVR), were considered together with three data granularities: daily, hourly, and 15 minutes. The approach has been applied to a large entertainment venue located in Ontario, Canada. Daily data intervals resulted in higher consumption prediction accuracy than hourly or 15-min readings, which can be explained by the inability of the hourly and 15-min models to capture random variations. With daily data, the NN model achieved better accuracy than the SVR; however, with hourly and 15-min data, there was no definitive dominance of one approach over another. Accuracy of daily peak demand prediction was significantly higher than accuracy of consumption prediction.
Electricity price, consumption, and demand forecasting has been a topic of research interest for ... more Electricity price, consumption, and demand forecasting has been a topic of research interest for a long time. The proliferation of smart meters has created new opportunities in energy prediction. This paper investigates energy cost forecasting in the context of entertainment event-organizing venues, which poses significant difficulty due to fluctuations in energy demand and wholesale electricity prices. The objective is to predict the overall cost of energy consumed during an entertainment event. Predictions are carried out separately for each event category and feature selection is used to select the most effective combination of event attributes for each category. Three machine learning approaches are considered: k-nearest neighbor (KNN) regression, support vector regression (SVR) and neural networks (NN). These approaches are evaluated on a case study involving a large event venue in Southern Ontario. In terms of prediction accuracy, KNN regression achieved the lowest average error. Error rates varied greatly among different event categories.
Uploads