الفهرس | Only 14 pages are availabe for public view |
Abstract Smart grids, or intelligent electricity grids that utilize modern IT/communication/control technologies, become a global trend nowadays. Forecasting of future grid load (electricity usage) is an important task to provide intelligence to the smart gird. Accurate forecasting will enable a utility provider to plan the resources and also to take control actions to balance the supply and the demand of electricity. In this thesis, our contribution is the proposal of a new data mining and Artificial Intelligence scheme to forecast the peak load of a particular consumer entity in the smart grid for a future time unit. We utilize least-squares version of support vector regression and Decision Tree model with learning strategy in our approach. The electricity performance in buildings is influenced by many factors, such as ambient weather conditions, building structure and characteristics, occupancy and their behaviors, operation of sub-level components like Heating, Ventilation and Air-Conditioning (AC) system. This complex property makes the prediction, analysis, or fault detection/diagnosis of building energy consumption very difficult to accurately and quickly perform. This thesis mainly focuses on up-to-date artificial intelligence models to solve these problems. In this thesis, recently developed models for solving these problems, including detailed and simplified Artificial engineering, statistical and Artificial Intelligence (AI) methods are reviewed. Then electricity consumption profiles are simulated for single (home) building, and based on these datasets, decision tree models are trained and tested to do the prediction. The results from extensive experiments demonstrate high prediction accuracy and robustness of these models. Also, In this thesis, we carry out an experimental quantitative assessment of different expectation techniques for kWh energy utilization of three dissimilar consumer types: small, usual and highly variable individual consumers. We demonstrate that forecast precision heavily depends on consumer type. In This thesis, we proposed a framework that applies hybrid analytical techniques such as regression, and frame-network semantic methods to predict an accurate result for each meter’s IDs. Our experiment, reports the power request analytical representation based on the decision tree method and K-means clustering method. The proposed system has an error rate of 0.079% compared to state-of-art. |