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: Forecasting electricity load plays a crucial role regards
decision making and planning for economical purposes. Besides, in
the light of the recent privatization and deregulation of the power
industry, the forecasting of future electricity load turned out to be a
very challenging problem. Empirical data about electricity load
highlights a clear seasonal behavior (higher load during the winter
season), which is partly due to climatic effects. We also emphasize
the presence of load periodicity at a weekly basis (electricity load is
usually lower on weekends or holidays) and at daily basis (electricity
load is clearly influenced by the hour). Finally, a long-term trend may
depend on the general economic situation (for example, industrial
production affects electricity load). All these features must be
captured by the model.
The purpose of this paper is then to build an hourly electricity load
model. The deterministic component of the model requires non-linear
regression and Fourier series while we will investigate the stochastic
component through econometrical tools.
The calibration of the parameters’ model will be performed by
using data coming from the Italian market in a 6 year period (2007-
2012). Then, we will perform a Monte Carlo simulation in order to
compare the simulated data respect to the real data (both in-sample
and out-of-sample inspection). The reliability of the model will be
deduced thanks to standard tests which highlight a good fitting of the
simulated values.
Abstract: The use of hydroelectric pump-storage system at large
scale, MW-size systems, is already widespread around the world.
Designed for large scale applications, pump-storage station can be
scaled-down for small, remote residential applications. Given the cost
and complexity associated with installing a substation further than
100 miles from the main transmission lines, a remote, independent
and self-sufficient system is by far the most feasible solution. This
article is aiming at the design of wind and solar power generating
system, by means of pumped-storage to replace the wind and /or solar
power systems with a battery bank energy storage. Wind and solar
pumped-storage power generating system can reduce the cost of
power generation system, according to the user's electricity load and
resource condition and also can ensure system reliability of power
supply. Wind and solar pumped-storage power generation system is
well suited for remote residential applications with intermittent wind
and/or solar energy. This type of power systems, installed in these
locations, could be a very good alternative, with economic benefits
and positive social effects. The advantage of pumped storage power
system, where wind power regulation is calculated, shows that a
significant smoothing of the produced power is obtained, resulting in
a power-on-demand system’s capability, concomitant to extra
economic benefits.
Abstract: This paper presents the performance of electricity
generation and consumption from solar generator installed at
Rajabhat Suan Sunandha’s learning center in Samutsongkram.
The result from the experiment showed that solar cell began to
work and distribute the current into the system when the solar energy
intensity was 340 w/m2, starting from 8:00 am to 4:00 pm (duration
of 8 hours). The highest intensity read during the experiment was
1,051.64w/m2. The solar power was 38.74kWh/day. The
electromotive force from solar cell averagely was 93.6V. However,
when connecting solar cell with the battery charge controller system,
the voltage was dropped to 69.07V. After evaluating the power
distribution ability and electricity load of tested solar cell, the result
showed that it could generate power to 11 units of 36-watt
fluorescent lamp bulbs, which was altogether 396W. In the
meantime, the AC to DC power converter generated 3.55A to the
load, and gave 781VA.
Abstract: this paper presents an auto-regressive network called the Auto-Regressive Multi-Context Recurrent Neural Network (ARMCRN), which forecasts the daily peak load for two large power plant systems. The auto-regressive network is a combination of both recurrent and non-recurrent networks. Weather component variables are the key elements in forecasting because any change in these variables affects the demand of energy load. So the AR-MCRN is used to learn the relationship between past, previous, and future exogenous and endogenous variables. Experimental results show that using the change in weather components and the change that occurred in past load as inputs to the AR-MCRN, rather than the basic weather parameters and past load itself as inputs to the same network, produce higher accuracy of predicted load. Experimental results also show that using exogenous and endogenous variables as inputs is better than using only the exogenous variables as inputs to the network.
Abstract: Due to the liberalization of countless electricity markets, load forecasting has become crucial to all public utilities for which electricity is a strategic variable. With the goal of contributing to the forecasting process inside public utilities, this paper addresses the issue of applying the Holt-Winters exponential smoothing technique and the time series analysis for forecasting the hourly electricity load curve of the Italian railways. The results of the analysis confirm the accuracy of the two models and therefore the relevance of forecasting inside public utilities.
Abstract: This paper is a continuation of our daily energy peak load forecasting approach using our modified network which is part of the recurrent networks family and is called feed forward and feed back multi context artificial neural network (FFFB-MCANN). The inputs to the network were exogenous variables such as the previous and current change in the weather components, the previous and current status of the day and endogenous variables such as the past change in the loads. Endogenous variable such as the current change in the loads were used on the network output. Experiment shows that using endogenous and exogenous variables as inputs to the FFFBMCANN rather than either exogenous or endogenous variables as inputs to the same network produces better results. Experiments show that using the change in variables such as weather components and the change in the past load as inputs to the FFFB-MCANN rather than the absolute values for the weather components and past load as inputs to the same network has a dramatic impact and produce better accuracy.
Abstract: This paper proposed a novel model for short term load
forecast (STLF) in the electricity market. The prior electricity
demand data are treated as time series. The model is composed of
several neural networks whose data are processed using a wavelet
technique. The model is created in the form of a simulation program
written with MATLAB. The load data are treated as time series data.
They are decomposed into several wavelet coefficient series using
the wavelet transform technique known as Non-decimated Wavelet
Transform (NWT). The reason for using this technique is the belief
in the possibility of extracting hidden patterns from the time series
data. The wavelet coefficient series are used to train the neural
networks (NNs) and used as the inputs to the NNs for electricity load
prediction. The Scale Conjugate Gradient (SCG) algorithm is used as
the learning algorithm for the NNs. To get the final forecast data, the
outputs from the NNs are recombined using the same wavelet
technique. The model was evaluated with the electricity load data of
Electronic Engineering Department in Mandalay Technological
University in Myanmar. The simulation results showed that the
model was capable of producing a reasonable forecasting accuracy in
STLF.
Abstract: Short term electricity demand forecasts are required
by power utilities for efficient operation of the power grid. In a
competitive market environment, suppliers and large consumers also
require short term forecasts in order to estimate their energy
requirements in advance. Electricity demand is influenced (among
other things) by the day of the week, the time of year and special
periods and/or days such as Ramadhan, all of which must be
identified prior to modelling. This identification, known as day-type
identification, must be included in the modelling stage either by
segmenting the data and modelling each day-type separately or by
including the day-type as an input. Day-type identification is the
main focus of this paper. A Kohonen map is employed to identify the
separate day-types in Algerian data.