• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.713-719
• /
• 2009

In this paper, we develope a water demand forecasting algorithm using AR(Auto-regressive) and MLP(Multi-layer perceptron). To show effectiveness of the proposed method, we analyzed characteristics of time-series data collected in "A" purification plant at Jeon-Buk province during 2007-2008, and then performed the proposed method with various input factors selected through various analyses. As noted in experimental results, the performance of three types model such as multi-regressive, AR(Auto-regressive), and AR+MLP(Auto-regressive + Multi-layer perceptron) show 5.1%, 3.8%, and 3.6% with respect to MAPE(Mean Absolute Percentage Error), respectively. Thus, it is noted that the proposed method can be used to predict short-term water demand for the efficient operation of a water purification plant.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.528-550
• /
• 2024

Warehousing demand prediction is an essential part of the supply chain, providing a fundamental basis for product manufacturing, replenishment, warehouse planning, etc. Existing forecasting methods cannot produce accurate forecasts since warehouse demand is affected by external factors such as holidays and seasons. Some aspects, such as consumer psychology and producer reputation, are challenging to quantify. The data can fluctuate widely or do not show obvious trend cycles. We introduce a new model for warehouse demand prediction called MAGRU, which stands for Multi-layer Attention with GRU. In the model, firstly, we perform the embedding operation on the input sequence to quantify the external influences; after that, we implement an encoder using GRU and the attention mechanism. The hidden state of GRU captures essential time series. In the decoder, we use attention again to select the key hidden states among all-time slices as the data to be fed into the GRU network. Experimental results show that this model has higher accuracy than RNN, LSTM, GRU, Prophet, XGboost, and DARNN. Using mean absolute error (MAE) and symmetric mean absolute percentage error(SMAPE) to evaluate the experimental results, MAGRU's MAE, RMSE, and SMAPE decreased by 7.65%, 10.03%, and 8.87% over GRU-LSTM, the current best model for solving this type of problem.

• The Korean Journal of Applied Statistics
• /
• v.27 no.5
• /
• pp.843-853
• /
• 2014

Accurate electricity demand forecasting for daily peak load is essential for management and planning at electrical facilities. In this paper, we rst, introduce the several time series models that forecast daily peak load and compare the forecasting performance of the models based on Mean Absolute Percentage Error(MAPE). The results show that the Reg-AR-GARCH model outperforms other competing models that consider Cooling Degree Day(CDD) and Heating Degree Day(HDD) as well as seasonal components.

• Communications for Statistical Applications and Methods
• /
• v.17 no.3
• /
• pp.473-481
• /
• 2010

Forecasting for air demand such as international passengers and freight has been one of the main interests for air industries. This research has mainly focus on the comparison of the performances of the multivariate time series models. In this paper, we used real data such as exchange rates, oil prices and export amounts to predict the future demand on international passenger and freight.

• Journal of Digital Convergence
• /
• v.11 no.2
• /
• pp.175-182
• /
• 2013

In this paper, the simulation model of house price is presented on the basis of pricing mechanism between the demand and the supply of apartments in seoul. The algorithm of house price simulation model for calculating the rate of price over time includes feedback control theory. The feedback control theory consists of stock variable, flow variable, auxiliary variable and constant variable. We suggest that the future price of apartment is simulated using mutual interaction variables which are demand, supply, price and parameters among them. In this paper we considers three items which include the behavior of apartment price index, the size of demand and supply, and the forecasting of the apartment price in the future economic scenarios. The proposed price simulation model could be used in public needs for developing a house price regulation policy using financial and non-financial aids. And the quantitative simulation model is to be applied in practice with more specific real data and Powersim Software modeling tool.

• Health Policy and Management
• /
• v.18 no.4
• /
• pp.85-110
• /
• 2008

In this study, we explore the long-term demand forecasting of high-price medical equipments based on logistic and Bass diffusion model. We analyze the specific pattern of each equipment's diffusion curve by interpreting the parameter estimates of Bass diffusion model. Our findings are as follows. First, ultrasonic imaging system, CT are in the stage of maturity and so, the future demands of them are not too large. Second, medical image processing unit is between growth stage and maturity stage and so, the demand is expected to increase considerably for two or three years. Third, MRI is in the stage of take-off and Mammmography X-ray system is in the stage of maturity but, estimates of the potential number of adopters based on logistic model is considerably different to that based on Bass diffusion model. It means that additional data for these two equipments should be collected and analyzed to obtain the reliable estimates of their demands. Fourth, medical image processing unit have the largest q value. It means that the word-of-mouth effect is important in the diffusion of this equipment. Fifth, for MRI and Ultrasonic system, q/p values have the relatively large value. It means that collective power has an important role in adopting these two equipments.

• Journal of Korean Society of Rural Planning
• /
• v.25 no.4
• /
• pp.109-117
• /
• 2019

The purpose of this study is to present a time series model of onion and garlic prices. After considering the various time series models, we calculated the appropriate time series models for each item and then selected the model with the minimized error rate by reflecting the monthly dummy variables and import data. Also, we examined whether the predictive power improves when we combine the predictions of the Korea Rural Economic Institute with the predictions of time series models. As a result, onion prices were identified as ARMGARCH and garlic prices as ARXM. Monthly dummy variables were statistically significant for onion in May and garlic in June. Garlic imports were statistically significant as a result of adding imports as exogenous variables. This study is expected to help improve the forecasting model by suggesting a method to minimize the price forecasting error rate in the case of the unstable supply and demand of onion and garlic.

• 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.

• Environmental and Resource Economics Review
• /
• v.16 no.4
• /
• pp.901-922
• /
• 2007

To see how the electricity demand for air-conditioning responds to weather condition and what kind of weather condition works better in forecasting maximum daily electricity demand, four different regression models, which are linear, exponential, power and S-curve, are adopted. The regression outcome turns out that the electricity demand for air-conditioning is inclined to rely on the exponential model. Another major discovery of this study is that the electricity demand for air-conditioning responds more sensitively to the weather condition year after year along with the higher non-air-conditioning electricity demand. In addition, it has also been found that the discomfort index explains the electricity demand for air-conditioning better than the highest temperature.

• KIPS Transactions on Computer and Communication Systems
• /
• v.1 no.3
• /
• pp.133-142
• /
• 2012

Cournot model is one of representative models among many game theoretic approaches available for analyzing competitive market models. Recent years have witnessed various kinds of attempts to model competitive electricity markets using the Cournot model. Cournot model is appropriate for oligopoly market which is one characteristic of electric power industry requiring huge amount of capital investment. When we use Cournot model for the application to electricity market, it is prerequisite to assume the downward sloping demand curve in the right direction. Generators in oligopoly market could try to maximize their profit by exercising the market power like physical or economic withholding. However advanced electricity markets also have demand side bidding which makes it possible for the demand to respond to the high market price by reducing their consumption. Considering this kind of demand reaction, Generators couldn't abuse their market power. Instead, they try to find out an equilibrium point which is optimal for both sides, generators and demand. This paper suggest a quantitative analysis between market variables based on econometrics for estimating demand responses in smart grid environment.