Abstract: The demand for renewable energy is significantly increasing, major investments are being supplied to the wind power generation industry as a leading source of clean energy. The wind energy sector is entirely dependable and driven by the prediction of wind speed, which by the nature of wind is very stochastic and widely random. This s0tudy employs deep multi-fidelity Gaussian process regression, used to predict wind speeds for medium term time horizons. Data of the RUNE experiment in the west coast of Denmark were provided by the Technical University of Denmark, which represent the wind speed across the study area from the period between December 2015 and March 2016. The study aims to investigate the effect of pre-processing the data by denoising the signal using empirical wavelet transform (EWT) and engaging the vector components of wind speed to increase the number of input data layers for data fusion using deep multi-fidelity Gaussian process regression (GPR). The outcomes were compared using root mean square error (RMSE) and the results demonstrated a significant increase in the accuracy of predictions which demonstrated that using vector components of the wind speed as additional predictors exhibits more accurate predictions than strategies that ignore them, reflecting the importance of the inclusion of all sub data and pre-processing signals for wind speed forecasting models.
Abstract: In an era where machines run and shape our world, the need for a stable, non-ending source of energy emerges. In this study, the focus was on the solar energy in Egypt as a renewable source, the most important factors that could affect the solar energy’s market share throughout its life cycle production were analyzed and filtered, the relationships between them were derived before structuring a Bayesian network. Also, forecasted models were built for multiple factors to predict the states in Egypt by 2035, based on historical data and patterns, to be used as the nodes’ states in the network. 37 factors were found to might have an impact on the use of solar energy and then were deducted to 12 factors that were chosen to be the most effective to the solar energy’s life cycle in Egypt, based on surveying experts and data analysis, some of the factors were found to be recurring in multiple stages. The presented Bayesian network could be used later for scenario and decision analysis of using solar energy in Egypt, as a stable renewable source for generating any type of energy needed.
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: Energy production optimization has been traditionally very important for utilities in order to improve resource consumption. However, load forecasting is a challenging task, as there are a large number of relevant variables that must be considered, and several strategies have been used to deal with this complex problem. This is especially true also in microgrids where many elements have to adjust their performance depending on the future generation and consumption conditions. The goal of this paper is to present a solution for short-term load forecasting in microgrids, based on three machine learning experiments developed in R and web services built and deployed with different components of Cortana Intelligence Suite: Azure Machine Learning, a fully managed cloud service that enables to easily build, deploy, and share predictive analytics solutions; SQL database, a Microsoft database service for app developers; and PowerBI, a suite of business analytics tools to analyze data and share insights. Our results show that Boosted Decision Tree and Fast Forest Quantile regression methods can be very useful to predict hourly short-term consumption in microgrids; moreover, we found that for these types of forecasting models, weather data (temperature, wind, humidity and dew point) can play a crucial role in improving the accuracy of the forecasting solution. Data cleaning and feature engineering methods performed in R and different types of machine learning algorithms (Boosted Decision Tree, Fast Forest Quantile and ARIMA) will be presented, and results and performance metrics discussed.
Abstract: A forecasting model for steel demand uncertainty in Thailand is proposed. It consists of trend, autocorrelation, and outliers in a hierarchical Bayesian frame work. The proposed model uses a cumulative Weibull distribution function, latent first-order autocorrelation, and binary selection, to account for trend, time-varying autocorrelation, and outliers, respectively. The Gibbs sampling Markov Chain Monte Carlo (MCMC) is used for parameter estimation. The proposed model is applied to steel demand index data in Thailand. The root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE) criteria are used for model comparison. The study reveals that the proposed model is more appropriate than the exponential smoothing method.
Abstract: The paper evaluates several hundred one-day-ahead
VaR forecasting models in the time period between the years 2004
and 2009 on data from six world stock indices - DJI, GSPC, IXIC,
FTSE, GDAXI and N225. The models model mean using the ARMA
processes with up to two lags and variance with one of GARCH,
EGARCH or TARCH processes with up to two lags. The models are
estimated on the data from the in-sample period and their forecasting
accuracy is evaluated on the out-of-sample data, which are more
volatile. The main aim of the paper is to test whether a model
estimated on data with lower volatility can be used in periods with
higher volatility. The evaluation is based on the conditional coverage
test and is performed on each stock index separately. The primary
result of the paper is that the volatility is best modelled using a
GARCH process and that an ARMA process pattern cannot be found
in analyzed time series.
Abstract: Spare parts inventory management is one of the major
areas of inventory research. Analysis of recent literature showed that
an approach integrating spare parts classification, demand
forecasting, and stock control policies is essential; however, adapting
this integrated approach is limited. This work presents an integrated
framework for spare part inventory management and an Excel based
application developed for the implementation of the proposed
framework. A multi-criteria analysis has been used for spare
classification. Forecasting of spare parts- intermittent demand has
been incorporated into the application using three different
forecasting models; namely, normal distribution, exponential
smoothing, and Croston method. The application is also capable of
running with different inventory control policies. To illustrate the
performance of the proposed framework and the developed
application; the framework is applied to different items at a service
organization. The results achieved are presented and possible areas
for future work are highlighted.
Abstract: The aim of this paper is to present a methodology in
three steps to forecast supply chain demand. In first step, various data
mining techniques are applied in order to prepare data for entering
into forecasting models. In second step, the modeling step, an
artificial neural network and support vector machine is presented
after defining Mean Absolute Percentage Error index for measuring
error. The structure of artificial neural network is selected based on
previous researchers' results and in this article the accuracy of
network is increased by using sensitivity analysis. The best forecast
for classical forecasting methods (Moving Average, Exponential
Smoothing, and Exponential Smoothing with Trend) is resulted based
on prepared data and this forecast is compared with result of support
vector machine and proposed artificial neural network. The results
show that artificial neural network can forecast more precisely in
comparison with other methods. Finally, forecasting methods'
stability is analyzed by using raw data and even the effectiveness of
clustering analysis is measured.
Abstract: In this paper bi-annual time series data on unemployment rates (from the Labour Force Survey) are expanded to quarterly rates and linked to quarterly unemployment rates (from the Quarterly Labour Force Survey). The resultant linked series and the consumer price index (CPI) series are examined using Johansen’s cointegration approach and vector error correction modeling. The study finds that both the series are integrated of order one and are cointegrated. A statistically significant co-integrating relationship is found to exist between the time series of unemployment rates and the CPI. Given this significant relationship, the study models this relationship using Vector Error Correction Models (VECM), one with a restriction on the deterministic term and the other with no restriction.
A formal statistical confirmation of the existence of a unique linear and lagged relationship between inflation and unemployment for the period between September 2000 and June 2011 is presented. For the given period, the CPI was found to be an unbiased predictor of the unemployment rate. This relationship can be explored further for the development of appropriate forecasting models incorporating other study variables.
Abstract: Load forecasting has become in recent years one of the major areas of research in electrical engineering. Most traditional forecasting models and artificial intelligence neural network techniques have been tried out in this task. Artificial neural networks (ANN) have lately received much attention, and a great number of papers have reported successful experiments and practical tests. This article presents the development of an ANN-based short-term load forecasting model with improved generalization technique for the Regional Power Control Center of Saudi Electricity Company, Western Operation Area (SEC-WOA). The proposed ANN is trained with weather-related data and historical electric load-related data using the data from the calendar years 2001, 2002, 2003, and 2004 for training. The model tested for one week at five different seasons, typically, winter, spring, summer, Ramadan and fall seasons, and the mean absolute average error for one hour-ahead load forecasting found 1.12%.
Abstract: This paper presents performance comparison of three estimation techniques used for peak load forecasting in power systems. The three optimum estimation techniques are, genetic algorithms (GA), least error squares (LS) and, least absolute value filtering (LAVF). The problem is formulated as an estimation problem. Different forecasting models are considered. Actual recorded data is used to perform the study. The performance of the above three optimal estimation techniques is examined. Advantages of each algorithms are reported and discussed.
Abstract: The aim of the article is extending and developing
econometrics and network structure based methods which are able to
distinguish price manipulation in Tehran stock exchange. The
principal goal of the present study is to offer model for
approximating price manipulation in Tehran stock exchange. In order
to do so by applying separation method a sample consisting of 397
companies accepted at Tehran stock exchange were selected and
information related to their price and volume of trades during years
2001 until 2009 were collected and then through performing runs
test, skewness test and duration correlative test the selected
companies were divided into 2 sets of manipulated and non
manipulated companies. In the next stage by investigating
cumulative return process and volume of trades in manipulated
companies, the date of starting price manipulation was specified and
in this way the logit model, artificial neural network, multiple
discriminant analysis and by using information related to size of
company, clarity of information, ratio of P/E and liquidity of stock
one year prior price manipulation; a model for forecasting price
manipulation of stocks of companies present in Tehran stock
exchange were designed. At the end the power of forecasting models
were studied by using data of test set. Whereas the power of
forecasting logit model for test set was 92.1%, for artificial neural
network was 94.1% and multi audit analysis model was 90.2%;
therefore all of the 3 aforesaid models has high power to forecast
price manipulation and there is no considerable difference among
forecasting power of these 3 models.
Abstract: Accurately predicting non-peak traffic is crucial to
daily traffic for all forecasting models. In the paper, least squares
support vector machines (LS-SVMs) are investigated to solve such a
practical problem. It is the first time to apply the approach and analyze
the forecast performance in the domain. For comparison purpose, two
parametric and two non-parametric techniques are selected because of
their effectiveness proved in past research. Having good
generalization ability and guaranteeing global minima, LS-SVMs
perform better than the others. Providing sufficient improvement in
stability and robustness reveals that the approach is practically
promising.