Abstract: Forecasting electricity load is important for various purposes like planning, operation and control. Forecasts can save operating and maintenance costs, increase the reliability of power supply and delivery systems, and correct decisions for future development. This paper compares various time series methods to forecast 24 hours ahead of electricity load. The methods considered are the Holt-Winters smoothing, SARIMA Modeling, LSTM Network, Fbprophet and Tensorflow probability. The performance of each method is evaluated by using the forecasting accuracy criteria namely, the Mean Absolute Error and Root Mean Square Error. The National Renewable Energy Laboratory (NREL) residential energy consumption data are used to train the models. The results of this study show that SARIMA model is superior to the others for 24 hours ahead forecasts. Furthermore, a Bagging technique is used to make the predictions more robust. The obtained results show that by Bagging multiple time-series forecasts we can improve the robustness of the models for 24 hour ahead electricity load forecasting.
Abstract: Generative Adversarial Net (GAN) has proved to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions include both categorical and continuous variables with different auxiliary information. Our simulation studies show that CGAN has the capability to learn different types of normal and heavy-tailed distributions, as well as dependent structures of different time series. It also has the capability to generate conditional predictive distributions consistent with training data distributions. We also provide an in-depth discussion on the rationale behind GAN and the neural networks as hierarchical splines to establish a clear connection with existing statistical methods of distribution generation. In practice, CGAN has a wide range of applications in market risk and counterparty risk analysis: it can be applied to learn historical data and generate scenarios for the calculation of Value-at-Risk (VaR) and Expected Shortfall (ES), and it can also predict the movement of the market risk factors. We present a real data analysis including a backtesting to demonstrate that CGAN can outperform Historical Simulation (HS), a popular method in market risk analysis to calculate VaR. CGAN can also be applied in economic time series modeling and forecasting. In this regard, we have included an example of hypothetical shock analysis for economic models and the generation of potential CCAR scenarios by CGAN at the end of the paper.
Abstract: The Flash Flood Guidance (FFG) provides the rainfall amount of a given duration necessary to cause flooding. The approach is based on the development of rainfall-runoff curves, which helps us to find out the rainfall amount that would cause flooding. An alternative approach, mostly experimented with Italian Alpine catchments, is based on determining threshold discharges from past events and on finding whether or not an oncoming flood has its magnitude more than some critical discharge thresholds found beforehand. Both approaches suffer from large uncertainties in forecasting flash floods as, due to the simplistic approach followed, the same rainfall amount may or may not cause flooding. This uncertainty leads to the question whether a probabilistic model is preferable over a deterministic one in forecasting flash floods. We propose the use of a Bayesian probabilistic approach in flash flood forecasting. A prior probability of flooding is derived based on historical data. Additional information, such as antecedent moisture condition (AMC) and rainfall amount over any rainfall thresholds are used in computing the likelihood of observing these conditions given a flash flood has occurred. Finally, the posterior probability of flooding is computed using the prior probability and the likelihood. The variation of the computed posterior probability with rainfall amount and AMC presents the suitability of the approach in decision making in an uncertain environment. The methodology has been applied to the Posina basin in Italy. From the promising results obtained, we can conclude that the Bayesian approach in flash flood forecasting provides more realistic forecasting over the FFG.
Abstract: Ambient air pollution with fine particulate matter (PM10) is a systematic permanent problem in many countries around the world. The accumulation of a large number of measurements of both the PM10 concentrations and the accompanying atmospheric factors allow for their statistical modeling to detect dependencies and forecast future pollution. This study applies the classification and regression trees (CART) method for building and analyzing PM10 models. In the empirical study, average daily air data for the city of Pleven, Bulgaria for a period of 5 years are used. Predictors in the models are seven meteorological variables, time variables, as well as lagged PM10 variables and some lagged meteorological variables, delayed by 1 or 2 days with respect to the initial time series, respectively. The degree of influence of the predictors in the models is determined. The selected best CART models are used to forecast future PM10 concentrations for two days ahead after the last date in the modeling procedure and show very accurate results.
Abstract: Load forecasting has become crucial in recent years
and become popular in forecasting area. Many different power
forecasting models have been tried out for this purpose. Electricity
load forecasting is necessary for energy policies, healthy and reliable
grid systems. Effective power forecasting of renewable energy load
leads the decision makers to minimize the costs of electric utilities
and power plants. Forecasting tools are required that can be used
to predict how much renewable energy can be utilized. The purpose
of this study is to explore the effectiveness of LSTM-based neural
networks for estimating renewable energy loads. In this study, we
present models for predicting renewable energy loads based on
deep neural networks, especially the Long Term Memory (LSTM)
algorithms. Deep learning allows multiple layers of models to learn
representation of data. LSTM algorithms are able to store information
for long periods of time. Deep learning models have recently been
used to forecast the renewable energy sources such as predicting
wind and solar energy power. Historical load and weather information
represent the most important variables for the inputs within the
power forecasting models. The dataset contained power consumption
measurements are gathered between January 2016 and December
2017 with one-hour resolution. Models use publicly available data
from the Turkish Renewable Energy Resources Support Mechanism.
Forecasting studies have been carried out with these data via deep
neural networks approach including LSTM technique for Turkish
electricity markets. 432 different models are created by changing
layers cell count and dropout. The adaptive moment estimation
(ADAM) algorithm is used for training as a gradient-based optimizer
instead of SGD (stochastic gradient). ADAM performed better than
SGD in terms of faster convergence and lower error rates. Models
performance is compared according to MAE (Mean Absolute Error)
and MSE (Mean Squared Error). Best five MAE results out of
432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting
performance of the proposed LSTM models gives successful results
compared to literature searches.
Abstract: This aims of this paper is to forecast the electricity spot prices. First, we focus on modeling the conditional mean of the series so we adopt a generalized fractional -factor Gegenbauer process (k-factor GARMA). Secondly, the residual from the -factor GARMA model has used as a proxy for the conditional variance; these residuals were predicted using two different approaches. In the first approach, a local linear wavelet neural network model (LLWNN) has developed to predict the conditional variance using the Back Propagation learning algorithms. In the second approach, the Gegenbauer generalized autoregressive conditional heteroscedasticity process (G-GARCH) has adopted, and the parameters of the k-factor GARMA-G-GARCH model has estimated using the wavelet methodology based on the discrete wavelet packet transform (DWPT) approach. The empirical results have shown that the k-factor GARMA-G-GARCH model outperform the hybrid k-factor GARMA-LLWNN model, and find it is more appropriate for forecasts.
Abstract: In this paper, we discuss a Bayesian approach to
quantile autoregressive (QAR) time series model estimation and
forecasting. Together with a combining forecasts technique, we then
predict USD to GBP currency exchange rates. Combined forecasts
contain all the information captured by the fitted QAR models
at different quantile levels and are therefore better than those
obtained from individual models. Our results show that an unequally
weighted combining method performs better than other forecasting
methodology. We found that a median AR model can perform well in
point forecasting when the predictive density functions are symmetric.
However, in practice, using the median AR model alone may involve
the loss of information about the data captured by other QAR models.
We recommend that combined forecasts should be used whenever
possible.
Abstract: At present, vibrations of rotors of gas transmittal unit evade sustainable forecasting. This paper describes elastic oscillation modes in resilient supports and rotor impellers modeled during computational experiments with regard to interference in the system of gas-dynamic flow and compressor rotor. Verification of aeroelastic approach was done on model problem of interaction between supersonic jet in shock tube with deformed plate. ANSYS 15.0 engineering analysis system was used as a modeling tool of numerical simulation in this paper. Finite volume method for gas dynamics and finite elements method for assessment of the strain stress state (SSS) components were used as research methods. Rotation speed and material’s elasticity modulus varied during calculations, and SSS components and gas-dynamic parameters in the dynamic system of gas-dynamic flow and compressor rotor were evaluated. The analysis of time dependence demonstrated that gas-dynamic parameters near the rotor blades oscillate at 200 Hz, and SSS parameters at the upper blade edge oscillate four times higher, i.e. with blade frequency. It has been detected that vibration amplitudes correction in the test points at magnetic bearings by aeroelasticity may correspond up to 50%, and about -π/4 for phases.
Abstract: We regard forecasting of energy consumption by
private production areas of a large industrial facility as well as by the
facility itself. As for production areas, the forecast is made based on
empirical dependencies of the specific energy consumption and the
production output. As for the facility itself, implementation of the
task to minimize the energy consumption forecasting error is based
on adjustment of the facility’s actual energy consumption values
evaluated with the metering device and the total design energy
consumption of separate production areas of the facility. The
suggested procedure of optimal energy consumption was tested based
on the actual data of core product output and energy consumption by
a group of workshops and power plants of the large iron and steel
facility. Test results show that implementation of this procedure gives
the mean accuracy of energy consumption forecasting for winter
2014 of 0.11% for the group of workshops and 0.137% for the power
plants.
Abstract: In this paper, temperature extremes are forecast by
employing the block maxima method of the Generalized extreme
value(GEV) distribution to analyse temperature data from the
Cameroon Development Corporation (C.D.C). By considering two sets
of data (Raw data and simulated data) and two (stationary and
non-stationary) models of the GEV distribution, return levels analysis
is carried out and it was found that in the stationary model, the
return values are constant over time with the raw data while in the
simulated data, the return values show an increasing trend but with
an upper bound. In the non-stationary model, the return levels of
both the raw data and simulated data show an increasing trend but
with an upper bound. This clearly shows that temperatures in the
tropics even-though show a sign of increasing in the future, there
is a maximum temperature at which there is no exceedence. The
results of this paper are very vital in Agricultural and Environmental
research.
Abstract: A model was constructed to predict the amount of
solar radiation that will make contact with the surface of the earth in
a given location an hour into the future. This project was supported
by the Southern Company to determine at what specific times during
a given day of the year solar panels could be relied upon to produce
energy in sufficient quantities. Due to their ability as universal
function approximators, an artificial neural network was used to
estimate the nonlinear pattern of solar radiation, which utilized
measurements of weather conditions collected at the Griffin, Georgia
weather station as inputs. A number of network configurations and
training strategies were utilized, though a multilayer perceptron with
a variety of hidden nodes trained with the resilient propagation
algorithm consistently yielded the most accurate predictions. In
addition, a modeled direct normal irradiance field and adjacent
weather station data were used to bolster prediction accuracy. In later
trials, the solar radiation field was preprocessed with a discrete
wavelet transform with the aim of removing noise from the
measurements. The current model provides predictions of solar
radiation with a mean square error of 0.0042, though ongoing efforts
are being made to further improve the model’s accuracy.
Abstract: Fuzzy systems have been successfully used for
exchange rate forecasting. However, fuzzy system is very confusing
and complex to be designed by an expert, as there is a large set of
parameters (fuzzy knowledge base) that must be selected, it is not a
simple task to select the appropriate fuzzy knowledge base for an
exchange rate forecasting. The researchers often look the effect of
fuzzy knowledge base on the performances of fuzzy system
forecasting. This paper proposes a genetic fuzzy predictor to forecast
the future value of daily US Dollar/Euro exchange rate time’s series.
A range of methodologies based on a set of fuzzy predictor’s which
allow the forecasting of the same time series, but with a different
fuzzy partition. Each fuzzy predictor is built from two stages, where
each stage is performed by a real genetic algorithm.
Abstract: This paper presents an Artificial Neural Network based approach for short-term load forecasting and exactly for two days ahead. Two seasons have been discussed for Iraqi power system, namely summer and winter; the hourly load demand is the most important input variables for ANN based load forecasting. The recorded daily load profile with a lead time of 1-48 hours for July and December of the year 2012 was obtained from the operation and control center that belongs to the Ministry of Iraqi electricity.
The results of the comparison show that the neural network gives a good prediction for the load forecasting and for two days ahead.
Abstract: Technical analysis comprised by various technical indicators is a holistic way of representing price movement of stocks in the market. Various forms of indicators have evolved from the primitive ones in the past decades. There have been many attempts to introduce volume as a major determinant to determine strong patterns in market forecasting. The law of demand defines the relationship between the volume and price. Most of the traders are familiar with the volume game. Including the time dimension to the law of demand provides a different visualization to the theory. While attempting the same, it was found that there are different thresholds in the market for different companies. These thresholds have a significant influence on the price. This article is an attempt in determining the thresholds for companies using the three dimensional graphs for optimizing the portfolios. It also emphasizes on the magnitude of importance of volumes as a key factor for determining of predicting strong price movements, bullish and bearish markets. It uses a comprehensive data set of major companies which form a major chunk of the Indian automotive sector and are thus used as an illustration.
Abstract: This paper presents a Gaussian process model-based
short-term electric load forecasting. The Gaussian process model is
a nonparametric model and the output of the model has Gaussian
distribution with mean and variance. The multiple Gaussian process
models as every hour ahead predictors are used to forecast future
electric load demands up to 24 hours ahead in accordance with the
direct forecasting approach. The separable least-squares approach that
combines the linear least-squares method and genetic algorithm is
applied to train these Gaussian process models. Simulation results
are shown to demonstrate the effectiveness of the proposed electric
load forecasting.
Abstract: In this paper, we forecast the volatility of Baht/USDs using Markov Regime Switching GARCH (MRS-GARCH) models. These models allow volatility to have different dynamics according to unobserved regime variables. The main purpose of this paper is to find out whether MRS-GARCH models are an improvement on the GARCH type models in terms of modeling and forecasting Baht/USD volatility. The MRS-GARCH is the best performance model for Baht/USD volatility in short term but the GARCH model is best perform for long term.
Abstract: ERP has been used in many enterprises for management, the accuracy of the production forecasting module is vital to the decision making of the enterprise, and the profit is affected directly. Therefore, enhancing the accuracy of the production forecasting module can also increase the efficiency and profitability. To deal with a lot of data, a suitable, reliable and accurate statistics model is necessary. LSSVM and Grey System are two main models to be studied in this paper, and a case study is used to demonstrate how the combination model is effective to the result of forecasting.
Abstract: While the European Union (EU) harmonized methodology is a benchmark of worldwide used business survey (BS) methodology, the choice of variables that are components of the confidence indicators, as the leading indicators, is not strictly determined and unique. Therefore, the aim of this paper is to investigate and to quantify the relationship between all business survey variables in manufacturing industry and industrial production as a reference macroeconomic series in Croatia. The assumption is that there are variables in the business survey, that are not components of Industrial Confidence Indicator (ICI) and which can accurately (and sometimes better then ICI) predict changes in Croatian industrial production. Empirical analyses are conducted using quarterly data of BS variables in manufacturing industry and Croatian industrial production over the period from the first quarter 2005 to the first quarter 2013. Research results confirmed the assumption: three BS variables which is not components of ICI (competitive position, demand and liquidity) are the best leading indicator then ICI, in forecasting changes in Croatian industrial production instantaneously, with one, two or three quarter ahead.
Abstract: In this paper, we have presented a new multivariate fuzzy time series forecasting method. This method assumes mfactors with one main factor of interest. History of past three years is used for making new forecasts. This new method is applied in forecasting total number of car accidents in Belgium using four secondary factors. We also make comparison of our proposed method with existing methods of fuzzy time series forecasting. Experimentally, it is shown that our proposed method perform better than existing fuzzy time series forecasting methods. Practically, actuaries are interested in analysis of the patterns of causalities in road accidents. Thus using fuzzy time series, actuaries can define fuzzy premium and fuzzy underwriting of car insurance and life insurance for car insurance. National Institute of Statistics, Belgium provides region of risk classification for each road. Thus using this risk classification, we can predict premium rate and underwriting of insurance policy holders.
Abstract: One of the essential sectors of Myanmar economy is
agriculture which is sensitive to climate variation. The most
important climatic element which impacts on agriculture sector is
rainfall. Thus rainfall prediction becomes an important issue in
agriculture country. Multi variables polynomial regression (MPR)
provides an effective way to describe complex nonlinear input output
relationships so that an outcome variable can be predicted from the
other or others. In this paper, the modeling of monthly rainfall
prediction over Myanmar is described in detail by applying the
polynomial regression equation. The proposed model results are
compared to the results produced by multiple linear regression model
(MLR). Experiments indicate that the prediction model based on
MPR has higher accuracy than using MLR.