Kittipong Methaprayoon

An Integration of ANN Wind Power Estimation Into Unit Commitment Considering the Forecasting Uncertainty

The development of wind power generation has rapidly progressed over the last decade. With the advancement in wind turbine technology, wind energy has become competitive with other fuel-based resources. The fluctuation of wind, however, makes it difficult to optimize the usage of wind power. The current practice ignores wind generation capacity in the unit commitment (UC), which discounts its usable capacity and may cause operational issues when the installation of wind generation equipment increases. To ensure system reliability, the forecasting uncertainty must be considered in the incorporation of wind power capacity into generation planning. This paper discusses the development of an artificial-neural-network-based wind power forecaster and the integration of wind forecast results into UC scheduling considering forecasting uncertainty by the probabilistic concept of confidence interval. The data from a wind farm located in Lawton City, OK, is used in this paper.

Reactive compensation techniques to improve the ride-through capability of wind turbine during disturbance

World wind energy capacity expanded at an annual rate of 25% during the 1990s. The total world wind turbine installation capacity was approximately 40 000 MW at the end of 2003. Germany has the highest installed capacity of over 10 000 MW, while Denmark, where the wind energy accounts for more than 13% of electricity consumed, has the highest wind energy level per capita. The United States is catching up in the development of wind farms, with several large-scale wind generation projects currently being materialized. Even though there is significant progress in the wind generation technology, most of the currently installed wind turbines utilize induction generators to produce the electricity. Since the induction generators do not perform voltage regulation and absorb reactive power from the utility grid, they are often the source of voltage fluctuations. It is necessary to examine their responses during the faults and possible impacts on the system stability when the percentage of the wind generation increases. This paper compares the steady-state voltage profile and the voltage ride-through capabilities of the induction-generator-based wind farms with different reactive compensation techniques.

Multi-Stage Artificial Neural Network Short-term Load Forecasting Engine with Front-End Weather Forecast

A significant portion of the operating cost of utilities comes from energy production. To minimize the cost, unit commitment (UC) scheduling can be used to determine the optimal commitment schedule of generation units to accommodate the forecasted demand. The load forecast is a prerequisite for UC planning. The projected load of up to seven days is important for the allocation of generation resources. Hour-ahead forecast is used for optimally dispatching online resources to supply the next hour load. This paper addresses the systematic design of a multistage artificial-neural-network-based short-term load forecaster (ANNSTLF). The developed ANNSTLF engine has been utilized in a real utility system. The performance analysis over the past year shows that a majority of the forecast error was detected in a consistent period with a large temperature forecast error. The enhancement of ANNSTLF is proposed to improve the forecasting performance. The comparison of forecasting accuracy due to this enhancement is analyzed.A significant portion of electric utility operating expense comes from the energy production. In order to minimize the cost, unit commitment (UC) scheduling is an important tool to properly assign generation units to accommodate the forecasted system demand. The short-term load forecast is a prerequisite for UC planning. The projected load up to 7 days ahead is important for the reconfiguration of generation units. Hour-ahead forecast is used for optimally dispatching online resources to supply the next hour load. This paper addresses the systematic design of artificial neural network based short-term load forecaster (ANNSTLF). The developed ANNSTLF engine has been utilized in a real utility system. The performance analysis over the past year shows that a majority of forecast error was detected in a consistent period with a large temperature forecast error. The enhancement of multi-stage ANNSTLF is proposed to improve the forecasting performance. The comparison of forecasting accuracy due to this enhancement is analyzed

Improve the unit commitment scheduling by using the neural network based short term load forecasting

Unit commitment scheduling of the utility company relies upon the forecast of the demand, demand pattern, availability and capacity of the generators, minimum/maximum up and down time of the generators, and heat rate. According to the experiences of a local utility company, the difference of the fuel cost can reach million dollars per day with different unit commitment scheduling. Accurate hour-ahead and day-ahead demand forecasting play important roles for proper unit commitment scheduling. This paper describes the procedure to improve the unit commitment scheduling by using the hour-ahead and day-ahead results from the newly developed neural network based short-term load forecasting program in the SCADA/EMS system. Comparison of field records is also provided.

Multiregion Load Forecasting for System With Large Geographical Area

In a power system covering a large geographical area, a single model for load forecasting of the entire area sometimes cannot guarantee satisfactory forecasting accuracy. One of the major reasons is because of the load diversity, usually caused by weather diversity, throughout the area. Multiregion load forecasting will be a feasible and effective solution to generate more accurate forecasting results, as well as provide regional forecasts for the utilities. However, a major challenge is how to optimally partition/merge the areas according to the regional load and weather conditions. This paper investigates the electricity demand and weather data from an electric utility in Midwest, U.S. Based on the data analysis, we demonstrate the existence of weather and load diversity within its control area and then develop a short-term multiregion load forecasting system based on support vector regression for day-ahead operation and market. The proposed multiregion forecasting system can find the optimal region partition under diverse weather and load conditions and finally achieve more accurate forecasts for aggregated system load. The proposed forecasting system has been tested by using the real data from the system. The numerical results obtained for different region partition schemes validate the effectiveness of the proposed multiregion forecasting system. The detailed discussions on the forecasting results have also been given in this paper.

An integration of ANN wind power estimation into UC considering the forecasting uncertainty

The development of wind generation has rapidly progressed over the last decade. With the advance in wind turbine technologies, wind energy has become competitive with other fuel-based generation resources. The fluctuation of wind, however, makes it difficult to optimize the use of wind power generation. Current practice ignores the possible available capacity of the wind generation during the unit commitment scheduling. This may cause operation issues and waste usable capacity when the installation of the wind generation increases. An accurate wind capacity forecasting is essential for efficient wind energy and capacity dispatching. To ensure the system reliability, one also has to consider the forecast uncertainty when integrating the wind capacity into generation planning. This paper discusses the development of an artificial neural network based wind forecast model with the consideration of wind generation uncertainty by using probabilistic concept of confidence interval. The data from a wind farm located in the Southern Oklahoma is used for this study

Multi-area load forecasting for system with large geographical area

In a power system covering large geographical area, a single model for overall load forecasting of the entire area sometimes can not guarantee satisfactory forecasting accuracy. One of the major reasons is due to the load diversity, usually caused by weather diversity, throughout the area. Multi-area load forecasting will be a feasible and effective solution to generate more accurate forecasting results, as well as provide regional forecasts for the utilities. However, the major challenge is how to optimally partition/merge the areas according to the load and weather conditions. This paper investigates the electricity demand and weather data from an electric utility in Midwest US. Based on the data analysis, we demonstrate the existence of weather and load diversity within its control area, and then develop a short-term adaptive multi-area load forecasting system based on support vector regression (SVR) for day-ahead operation and market. The proposed multi-area forecasting system can find the optimal area partition under diverse weather and load conditions, and finally achieve more accurate aggregate load forecasts. The proposed forecasting system has been tested by using the real data from the system. The numerical results obtained for different area partition schemes validate the effectiveness of the proposed multi-area forecasting system. The detailed discussions on the forecasting results have also been given in this paper.

Neural network-based short term load forecasting for unit commitment scheduling

Todays electric power industry is undergoing many fundamental changes due to the process of deregulation. In the new market environment, the power system operation will become more competitive. The utilities are required to perform optimal planning in order to operate their system efficiently. The accuracy of future load forecast becomes crucial. This paper presents the development of an artificial neural network-based short-term load forecasting (STLF) for unit commitment scheduling and resource planning. The network structures are carefully tuned to obtain satisfying forecast results according to the load characteristics of the target utility system. The result indicates that ANN forecaster provides more accurate result and can be modified to satisfy the target utilitys requirement.

Short-term Multi-Region Load Forecasting Based on Weather and Load Diversity Analysis

In a power system covering large geographical area, a single forecasting model for overall load of the whole region sometimes can not guarantee satisfactory forecasting accuracy. One of the major reasons is because the existence of load diversity, usually caused by weather diversity. In such a system, multi-region load forecasting will be a feasible and effective solution to provide more accurate forecasting results. This paper aims to demonstrate the existence of weather and demand diversity within the control area of an electric utility in Midwest US. Based on the analysis, an artificial neural network (ANN) based multi-region load forecasting system has been developed and tested by using the actual data. Simulation results validate the superiority of the proposed multi-region load forecasting system to the single aggregate forecasting model.

A Novel Approach for Arcing Fault Detection for Medium/Low-Voltage Switchgear

Switchgear arcing faults have been a primary cause for concern for the manufacturing industry and safety personnel alike. The deregulation of the power industry being in full swing and the ever-growing competitiveness in the distribution sector call for the transition from preventive to predictive maintenance. Switchgears form an integral part of the distribution system in any power system setup. Keeping in mind the switchgear arcing faults, the aforementioned transition applies, most of all, to the switchgear industry. Apart from the fact that it is the primary cause of serious injuries to electrical workers worldwide, switchgear arcing faults directly affect the quality and continuity of electric power to the consumers. A great amount of technological advancement has taken place in the development of arc-resistant/proof switchgears. However, most of these applications focus on minimizing the damage after the occurrence of the arcing fault. The problem associated with the compromise on the quality and continuity of electric power in such a scenario still awaits a technical as well as economically feasible solution. This paper describes the development of a novel approach for the detection of arcing faults in medium-/low-voltage switchgears. The basic concept involves the application of differential protection for the detection of any arcing within the switchgear. The new approach differs from the traditional differential concept in the fact that it employs higher frequency harmonic components of the line current as the input for the differential scheme. Actual arc-generating test benches have been set up in the Power System Simulation Laboratory at the Energy Systems Research Center to represent both medium- and low-voltage levels. Hall effect sensors in conjunction with data acquisition in LabVIEW are employed to record the line current data before, during, and after the arcing phenomenon. The methodology is first put to test via simulation approach for medium-voltage levels and then corroborated by actual hardware laboratory testing for low-voltage levels. The plots derived from the data gathering and simulation process clearly underline the efficiency of this approach to detect switchgear arcing faults. Both magnitude and phase differential concepts seem to provide satisfactory results. Apart from the technical efficiency, the approach is financially feasible, considering the fact that the differential protection is already being comprehensively employed worldwide.