الفهرس 
AbstractOnly 14 pages are availabe for public view
 |  | from | 177 |  |  |
| | | from | 177 | | |
Abstract
Internet of Things (IoT) enables the Smart Electrical Grids (SEGs) to support a lot of tasks throughout the generation, transmission, distribution, and consumption of energy. This thesis provides a new Electrical Load Forecasting (ELF) strategy based on the 3-tier architecture. ELF consists of two phases, which are; (i) Data Pre-processing Phase (DP2) and (ii) Load Prediction Phase (LP2). Both phases take place at a Cloud Servers (CSs) on the collected data, which is received from all fogs connected to the entire cloud. DP2 aims to perform feature selection and outlier rejection processes on the collected data using data mining techniques. Then, the filtered data is used to give fast and accurate load predictions in the next LP2. ELF strategy satisfies two contributions which are; Hybrid Outlier Rejection Methodology (HORM), and Multi-Ensemble Load Prediction (MELP) method. HORM try to eliminate all outliers from the training dataset before start learning the prediction model during LP2. HORM involves two stages which are; (i) a new statistical based outlier rejection stage, which is called Fast Outlier Rejection (FOR) and (ii) an Accurate Outlier Rejection (AOR) stage using Genetic Algorithm (GA). MELP can deal with big electrical data based on Map-Reduce method to provide fast and accurate predictions. It mainly consists of two levels which are; (i) Local Ensemble Level (LEL) in map phase and (ii) Global Ensemble Level (GEL) in reduce phase. In LEL, the ensemble classification principle is applied at every device in map phase. In GEL, the perfect and final decision for load prediction is taken in reduce phase based on Global Judger (GJ) method. According to ELF strategy, initially all informative features are selected using Fuzzy Based Feature selection (FBFS), all outliers are rejected, and then load prediction method is used to predict the future required power. The conducted experimental results had proven the effectiveness of HORM, and MELP methods. It is concluded that ELF can deal with big electrical data. It has a good impact in maximizing system reliability, resilience, and stability as it introduces fast and accurate load predictions.