• Industrial Engineering and Management Systems
• /
• v.14 no.3
• /
• pp.318-324
• /
• 2015

This paper proposes a dynamic short-term load forecasting method that utilizes a new sequential learning algorithm based on Relevance Vector Machine (RVM). The method performs general optimization of weights and hyperparameters using the current relevance vectors and newly arriving data. By doing so, the proposed algorithm is trained with the most recent data. Consequently, it extends the RVM algorithm to real-time and nonstationary learning processes. The results of application of the proposed algorithm to prediction of electrical loads indicate that its accuracy is comparable to that of existing nonparametric learning algorithms. Further, the proposed model reduces computational complexity.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.3
• /
• pp.73-78
• /
• 2001

BP neural network model and multiple-regression model were composed for forecasting the special-days load. Special-days load was forecasted using that neural network model made use of pattern conversion ratio and multiple-regression made use of weekday-change ratio. This methods identified the suitable as that special-days load of short and long term was forecasted with the weekly average percentage error of 1∼2[%] in the weekly peak load forecasting model using pattern conversion ratio. But this methods were hard with special-days load forecasting of summertime. therefore it was forecasted with the multiple-regression models. This models were used to the weekday-change ratio, and the temperature-humidity and discomfort-index as explanatory variable. This methods identified the suitable as that compared forecasting result of weekday load with forecasting result of special-days load because months average percentage error was alike. And, the fit of the presented forecast models using statistical tests had been proved. Big difficult problem of peak load forecasting had been solved that because identified the fit of the methods of special-days load forecasting in the paper presented.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.10
• /
• pp.453-459
• /
• 2002

This paper proposes an improved algorithm of the daily peak load forecasting for Korean Thanksgiving Day and the Lunar New Year's day. So far, many studies on the short-term load forecasting have been made to improve the accuracy of the load forecasting. However, the large errors of the load forecasting occur i case of Korean Thanksgiving Day and the Lunar New Year's Day. In order to reduce the errors of the load forecasting, the fuzzy linear regression method is introduced and a good selection method of the past load pattern is presented. Test results show that the proposed algorithm improves the accuracy of the load forecasting.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.51-65
• /
• 2024

Accurate electrical load forecasting is important to the effective operation of power systems in smart grids. With the recent development in machine learning, artificial intelligence-based models for predicting power demand are being actively researched. However, since existing models get input variables as numerical features, the accuracy of the forecasting model may decrease because they do not reflect the semantic relationship between these features. In this paper, we propose a scheme for short-term load forecasting by using features extracted through the large language models for input data. We firstly convert input variables into a sentence-like prompt format. Then, we use the large language model with frozen weights to derive the embedding vectors that represent the features of the prompt. These vectors are used to train the forecasting model. Experimental results show that the proposed scheme outperformed models based on numerical data, and by visualizing the attention weights in the large language models on the prompts, we identified the information that significantly influences predictions.

• Proceedings of the KIEE Conference
• /
• 2000.07a
• /
• pp.295-297
• /
• 2000

In case of power demand forecasting the most important problem is to deal with the load of special-days, Accordingly, this paper presents a method that forecasting special-days load with regression models and neural networks. Special-days load in summer season was forecasted by the multiple regression models using weekday change ratio Neural networks models uses pattern conversion ratio, and orthogonal polynomial models was directly forecasted using past special-days load data. forecasting result obtains % forecast error of about $1{\sim}2[%]$. Therefore, it is possible to forecast long and short special-days load.

• Proceedings of the KIEE Conference
• /
• 2005.07a
• /
• pp.810-812
• /
• 2005

In this paper, the short-term load forecasting of pole-transformer is performed by artificial neural networks. Input parameters of the Nosed algorithm are peak loads of pole-transformer of previous days and their temperatures. The proposed algorithm is tested for ore of the pole-transformers in seoul, korea. Test results show that the proposed algorithm improves the accuracy of the load forecasting of pole-transformer compared with the conventional algorithm.

• Proceedings of the KIEE Conference
• /
• 2000.11a
• /
• pp.184-186
• /
• 2000

This paper proposes the introduction of TAR(Threshold Autoregressive) model for short-term load forecasting including temperature variable. TAR model is a piecewise linear autoregressive model. In the scatter diagram of daily peak load versus daily maximum or minimum temperature, we can find out that the load-temperature relationship has a negative slope in lower regime and a positive slope in upper regime due to the heating and cooling load, respectively. In this paper, daily peak load was forecasted by applying TAR model using this load-temperature characteristic in these regimes. The results are compared with those of linear and quadratic regression models.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.1
• /
• pp.17-24
• /
• 2024

This paper introduces a novel approach to time-series estimation for energy load forecasting within Virtual Power Plant (VPP) systems, leveraging advanced artificial intelligence (AI) algorithms, namely Long Short-Term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA). Virtual power plants, which integrate diverse microgrids managed by Energy Management Systems (EMS), require precise forecasting techniques to balance energy supply and demand efficiently. The paper introduces a hybrid-method forecasting model combining a parametric-based statistical technique and an AI algorithm. The LSTM algorithm is particularly employed to discern pattern correlations over fixed intervals, crucial for predicting accurate future energy loads. SARIMA is applied to generate time-series forecasts, accounting for non-stationary and seasonal variations. The forecasting model incorporates a broad spectrum of distributed energy resources, including renewable energy sources and conventional power plants. Data spanning a decade, sourced from the Korea Power Exchange (KPX) Electrical Power Statistical Information System (EPSIS), were utilized to validate the model. The proposed hybrid LSTM-SARIMA model with parameter sets (1, 1, 1, 12) and (2, 1, 1, 12) demonstrated a high fidelity to the actual observed data. Thus, it is concluded that the optimized system notably surpasses traditional forecasting methods, indicating that this model offers a viable solution for EMS to enhance short-term load forecasting.

• 전기의세계
• /
• v.31 no.5
• /
• pp.368-374
• /
• 1982

This paper describes a combined algorithm for short-term-load forecating. One of the specific features of this algorithm is that the base, weather sensitive and residual components are predicted respectively. The base load is represented by the exponential smoothing approach and residual load is represented by the Box-Jenkins methodology. The weather sensitive load models are developed according to the information of temperature and discomfort index. This method was applied to Korea Electric Company and results for test periods up to three years are given.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.12
• /
• pp.1765-1773
• /
• 2012

The accuracy of load forecast is very important from the viewpoint of economical power system operation. In general, the weekdays' load demand pattern has the continuous time series characteristics. Therefore, the conventional methods expose stable performance for weekdays. In case of special days or weekends, the load demand pattern has the discontinuous time series characteristics, so forecasting error is relatively high. Especially, weekdays near the thanksgiving day and lunar new year's day have the mixed load profile characteristics of both weekdays and weekends. Therefore, it is difficult to forecast these days by using the existing algorithms. In this study, a new load forecasting method is proposed in order to enhance the accuracy of the forecast result considering the characteristics of weekdays and weekends. The proposed method was tested with these days during last decades, which shows that the suggested method considerably improves the accuracy of the load forecast results.