Intan Azmira Wan Abdul Razak

Short term load forecasting using data mining technique

Accurate load and price forecasting are become very essential in power system planning. This will increase the efficiency of electricity generation and distribution while maintaining sufficient security of operation. This paper proposes method for Short Term Load Forecasting using data mining technique. The data provided by utility of Malaysia were analyzed to see its behavior or load pattern in a day during weekday and weekend in Peninsular Malaysia. By considering day-type in a week, five model of SARIMA (Time Series approach) have been created using Minitab. The forecasting is held based on the similar repeating trend of patterns from historical load data. The half hourly load data for six weeks had been plotted according to day-type to forecast the load demand for a day ahead. The MAPEs (Mean Absolute Percentage Error) obtained were ranging from 1.07% to 3.26%. Hence this modeling had improved the accuracy of forecasting rather than using only one model for all day in a week.

A novel hybrid method of LSSVM-GA with multiple stage optimization for electricity price forecasting

Predicting price has now become an important task in the operation of electrical power system. Day-ahead prediction provides forecast prices for a day ahead that is useful for daily operation and decision-making. The main challenge for day ahead price forecasting is the accuracy and efficiency. Lower accuracy is produced due to the nature of electricity price that is highly volatile compared to load series. Hence, some researchers have developed complex procedures to produce accurate forecast while considering significant features and optimum parameters. Therefore, a multistage optimization for hybrid Least Square Support Vector Machine (LSSVM) and Genetic Algorithm (GA) model is developed in this study to provide an accurate price forecast with optimized parameters and input features. So far, no literature has been found on multistage feature and parameter selections using the methods of LSSVM-GA for day-ahead price prediction. All the models are examined on the Ontario power market; which is reported as among the most volatile market worldwide. A huge number of features are selected by two stages of optimization to avoid from missing any important features. The developed LSSVM-GA shows higher forecast accuracy with lower complexity than the existing models.

Support vector machine for day ahead electricity price forecasting

Electricity price forecasting has become an important part of power system operation and planning. In a pool- based electric energy market, producers submit selling bids consisting in energy blocks and their corresponding minimum selling prices to the market operator. Meanwhile, consumers submit buying bids consisting in energy blocks and their corresponding maximum buying prices to the market operator. Hence, both producers and consumers use day ahead price forecasts to derive their respective bidding strategies to the electricity market yet reduce the cost of electricity. However, forecasting electricity prices is a complex task because price series is a non-stationary and highly volatile series. Many factors cause for price spikes such as volatility in load and fuel price as well as power import to and export from outside the market through long term contract. This paper introduces an approach of machine learning algorithm for day ahead electricity price forecasting with Least Square Support Vector Mac...

Experimental Study on the Ground Resistance Reduction Based on Different Types of Grounding Rod

Grounding of electrical installation is primarily concerned with ensuring safety. The main purpose of grounding is to channel the fault current straightly to the earth. To produce a good grounding system, the value of earth resistance must be reduced as low as possible. Otherwise, current may flows through to those who touch the damage electrical equipment instead of flowing through grounding system. In this project, a 3 meter length of copper, galvanized iron and pure steel rod were installed in formatting of grounding system. The installation of the grounding rods was based on the fall of potential method. Both single rod testing and parallel rod testing were performed in this project. A comparison on grounding resistance value for copper rod, steel rod and galvanized iron rod was examined and the selection of the best grounding rod was determined from the experimental data. Result shows that different types of rod will produce different value of resistivity in which depend on installation technique and soil condition.

A case study on ground resistance based on copper electrode vs. galvanized iron electrode

Grounding of electrical installation is primarily concern with ensuring safety. The main purpose of grounding is to channel the fault current straightly to earth. To produce a good grounding system, the value of earth resistance must be reduce as low as possible. Otherwise, current may flow through to those who touch the damage electrical equipment instead of flowing through grounding system. In this project, a variety diameter of copper rod and galvanized iron rod were installed to build grounding system. The aim of this project is to find if there exists significance difference in the value of resistance when different diameter and different type of rod were used. Single rod testing and parallel rod testing were performed with fall of potential method to measure the value of earth resistance. Result shows that different types of rod with different diameter size produce different resistivity value which also depends on installation technique and soil condition.

Electricity Load Forecasting Using Data Mining Technique

Accurate load forecasting is become crucial in power system operation and planning; both for deregulated and regulated electricity market.A variety of methods including neural networks, time series, hybrid method and fuzzy logic have been developed for load forecasting. The time series techniques have been widely used because load behavior can be analyzed in a time series signal with hourly, daily, weekly, and seasonal periodicities. However, for a huge power system covering large geographical area such as Peninsular Malaysia, a single forecasting model for the entire Malaysia would not satisfy the forecasting accuracy; due to the load and weather diversity. Thus, this research will cater these conditions whereby five models of SARIMA (Seasonal ARIMA) Time Series were developed for five day types.