• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.3
• /
• pp.163-172
• /
• 2016

Electric load forecasting is essential for effective power system planning and operation. Complex and nonlinear relationships exist between the electric loads and their exogenous factors. In addition, time-series load data has non-stationary characteristics, such as trend, seasonality and anomalous day effects, making it difficult to predict the future loads. This paper proposes a locally-weighted polynomial neural network (LWPNN), which is a combination of a polynomial neural network (PNN) and locally-weighted regression (LWR) for daily shortterm peak load forecasting. Model over-fitting problems can be prevented effectively because PNN has an automatic structure identification mechanism for nonlinear system modeling. LWR applied to optimize the regression coefficients of LWPNN only uses the locally-weighted learning data points located in the neighborhood of the current query point instead of using all data points. LWPNN is very effective and suitable for predicting an electric load series with nonlinear and non-stationary characteristics. To confirm the effectiveness, the proposed LWPNN, standard PNN, support vector regression and artificial neural network are applied to a real world daily peak load dataset in Korea. The proposed LWPNN shows significantly good prediction accuracy compared to the other methods.

• Proceedings of the KIEE Conference
• /
• 1985.07a
• /
• pp.144-147
• /
• 1985

In electricity industry, the improvement of load factor by flattening of load has been considered to be more important than any other tasks and has received wide concern and interest. Especially while annual peak load had occured early evening in winter during past decades, but we found the trend has changed so that annual peak load occured during the daytime in summer since1981 The useful practicing methods of this load management ale as follows; 1. Inducing of midnight load by thermal storage water heating 2. Seasonal differential rates. 3. Revising the peak load priceing (Time-of -use) It seems hard to expect that load research can be carried out in a short time, and we all have to exert outselves continuously to provide efficient load management method without wasting resources.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.7
• /
• pp.67-74
• /
• 2009

This paper describes the speed control functions of the typical steam turbine speed controllers and the test results of generator load rejection simulations. The goal of the test is to verify the speed controller's ability to limit the steam turbine's peak speed within a predetermined level in the event of generator load loss. During normal operations, the balance between the driving force of the steam turbine and the braking force of the generator load is maintained and the speed of the turbine-generator is constant. Upon the generator's load loss, in other word, the load rejection, the turbine speed would rapidly increase up to the peak speed at a fast acceleration rate. It is required that the speed controller has the ability to limit the peak speed below the overspeed trip point, which is typically 110[%] of rated speed. If an actual load rejection occurs, a substantial amount of stresses will be applied to the turbine as well as other equipments, In order to avoid this unwanted situation, not an actual test but the other method is necessary. We are currently developing the turbine control system for another nuclear power plant and have plan to do the simulation suggested in this paper.

• Proceedings of the KIEE Conference
• /
• 2002.07a
• /
• pp.530-532
• /
• 2002

The contracted electric power and the demand factor of customers are used to predict the peak load in distribution transformers. The conventional demand factor was determined more than ten years ago. The contracted electric power and power demand have been increased. Therefore, we need to prepare the novel demand factor that appropriates at present. In this paper, we modify the demand factor to improve the peak load prediction of distribution transformers. To modify the demand factor, we utilize the 169 data acquisition devices for sample distribution transformers. The peak load currents were measured by the case studies using the actual load data, through which we verified that the proposed demand factors were correct than the conventional factors. A newly demand factor will be used to predict the peak load of distribution transformers.

• Proceedings of the KIEE Conference
• /
• 2002.11b
• /
• pp.41-43
• /
• 2002

The contracted electric power and the demand factor of customers are used to predict the peak load in distribution transformers. The conventional demand factor was determined more than ten years ago. The contracted electric power and power demand have been increased. Therefore, we need to prepare the novel demand factor that appropriates at present. In this paper, we modify the demand factor to improve the peak load prediction of distribution transformers. To modify the demand factor, we utilize the 169 data acquisition devices for sample distribution transformers in winter, spring summer. And, the peak load currents were measured by the case studies using the actual load data, through which we verified that the proposed demand factors were correct than the conventional factors. A newly demand factor will be used to predict the peak load of distribution transformers.

• Solar Energy
• /
• v.19 no.3
• /
• pp.63-73
• /
• 1999

Ice storage systems are used to shift the peak load in day time into night time in summer. This paper describes a system simulation of partial ice storage system composed of an encapsulated ice storage tank, a screw compressor chiller, a heat exchanger, and a brine pump. For the system simulation, a one-dimensional model of ice storage tank is developed and validated by comparison with the performance data from measurements of an ice storage tank installed at a building. The control strategies considered in this study are chiller priority and storage priority being used commercially. The system is simulated with design cooling load of 600 RT peak load in design day and with off-design day cooling load, and the electric energy costs of the two control strategies for the same system size are compared. As a result of calculation, the energy consumption in a week for storage priority is higher than that for chiller priority control. However due to lower cost of night electric charge rate, energy cost for storage priority control is lower than chiller priority.

• Proceedings of the KIEE Conference
• /
• 1999.11b
• /
• pp.276-278
• /
• 1999

In this paper, we analyze customers' working electric energy (kWh) which is served pole-transformer in order to reduce peak load current error which is generated in application load correlation equation. The characteristic of electric load which customers are using is classified by customer's working electric energy (kWh) and ratio of cooling equipment possession. For the input data of fuzzy model, we used to kWh on April which represents basic load and kWh which is increased from April to August. The April kWh is used to classify into large, medium, small customer. Also, the increased kWh is used to know information of cooling equipment possession. For the output value of fuzzy model, we can determined peak load current limit in application load correlation equation.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.572-573
• /
• 2008

Demand side management can be defined as series of planning and programs to change the electric usage pattern of customers from their normal ones with a least cost while meeting customers electric demand. In general, conventional demand side management programs can be classified into two groups, one of which is a load management and the other is energy efficiency. In this paper, the load management tariff programs in Korea are explored in terms of their effect on the peak demand reduction.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.53 no.2
• /
• pp.87-96
• /
• 2004

This paper summarizes the research results of the load management for pole transformers done in 1997-1998 and 2000-2002. The purpose of the research is to enhance the accuracy of peak load estimation in pole transformers. We concentrated our effort on the acquisition of massive actual load data for modifying the load regression coefficients, which related to the peak load estimation of lamp-use customers, and adjusting the demand-factor coefficients, which used for the peak load prediction of motor-use customers. To enhance the load regression equations, the 264 load data acquisition devices are equipped to the sample pole transformers. For the modification of demand factor coefficients, the peak load currents are measured in each customer and pole transformer for 13 KEPCO (Korea Electric Power Corporation) distribution branch offices. Case studies for 50 sample pole transformers show that the proposed coefficients could reduce estimating error of the peak load for pole transformers, compared with the conventional one.

• Proceedings of the KIEE Conference
• /
• 1999.07c
• /
• pp.1267-1269
• /
• 1999

This paper studies on arrangement of load correlation coefficient for advanced load management. To accurate load correlation coefficient, we used two real factors, electrical energy(kWh) and peak load current of pole transformers, acquired by measuring instrument. Out of several correlation equations, we find that the quadratic equation is the most accurate to express peak load current and working electrical energy. If the data is located in the outside of ${\pm}3{\sigma}$ it is discarded. For load management, we rearranged load correlation coefficient considering +2${\sigma}$ at load correlation equation. Comparing conventional load correlation coefficient with rearranged one, we can get the result of error reduced and it is adjacent to the actual data. It will be used peak load forecasting from working electrical energy and we are able to prevent from the damaging of pole transformer due to overload.