Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userShort- and long-term forecasting of electricity prices using embedding of calendar information in neural networks
66
0
0.0
(
0
)
Added by
Andreas Wagner
Publication date
2020
fields
Mathematical Statistics
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Electricity prices strongly depend on seasonality on different time scales, therefore any forecasting of electricity prices has to account for it. Neural networks proved successful in forecasting, but complicated architectures like LSTM are used to integrate the seasonal behavior. This paper shows that simple neural networks architectures like DNNs with an embedding layer for seasonality information deliver not only a competitive but superior forecast. The embedding based processing of calendar information additionally opens up new applications for neural networks in electricity trading like the generation of price forward curves. Besides the theoretical foundation, this paper also provides an empirical multi-year study on the German electricity market for both applications and derives economical insights from the embedding layer. The study shows that in short-term price-forecasting the mean absolute error of the proposed neural networks with embedding layer is only about half of the mean absolute forecast error of state-of-the-art LSTM approaches. The predominance of the proposed approach is also supported by a statistical analysis using Friedman and Holms tests.
rate research
Read More
The world is facing major challenges related to global warming and emissions of greenhouse gases is a major causing factor. In 2017, energy industries accounted for 46% of all CO2 emissions globally, which shows a large potential for reduction. This paper proposes a novel short-term CO2 emissions forecast to enable intelligent scheduling of flexible electricity consumption to minimize the resulting CO2 emissions. Two proposed time series decomposition methods are developed for short-term forecasting of the CO2 emissions of electricity. These are in turn bench-marked against a set of state-of-the-art models. The result is a new forecasting method with a 48-hour horizon targeted the day-ahead electricity market. Forecasting benchmarks for France show that the new method has a mean absolute percentage error that is 25% lower than the best performing state-of-the-art model. Further, application of the forecast for scheduling flexible electricity consumption is studied for five European countries. Scheduling a flexible block of 4 hours of electricity consumption in a 24 hour interval can on average reduce the resulting CO2 emissions by 25% in France, 17% in Germany, 69% in Norway, 20% in Denmark, and just 3% in Poland when compared to consuming at random intervals during the day.
Accurate short-term wind speed forecasting is needed for the rapid development and efficient operation of wind energy resources. This is, however, a very challenging problem. Although on the large scale, the wind speed is related to atmospheric pressure, temperature, and other meteorological variables, no improvement in forecasting accuracy was found by incorporating air pressure and temperature directly into an advanced space-time statistical forecasting model, the trigonometric direction diurnal (TDD) model. This paper proposes to incorporate the geostrophic wind as a new predictor in the TDD model. The geostrophic wind captures the physical relationship between wind and pressure through the observed approximate balance between the pressure gradient force and the Coriolis acceleration due to the Earths rotation. Based on our numerical experiments with data from West Texas, our new method produces more accurate forecasts than does the TDD model using air pressure and temperature for 1- to 6-hour-ahead forecasts based on three different evaluation criteria. Furthermore, forecasting errors can be further reduced by using moving average hourly wind speeds to fit the diurnal pattern. For example, our new method obtains between 13.9% and 22.4% overall mean absolute error reduction relative to persistence in 2-hour-ahead forecasts, and between 5.3% and 8.2% reduction relative to the best previous space-time methods in this setting.
The recent advent of smart meters has led to large micro-level datasets. For the first time, the electricity consumption at individual sites is available on a near real-time basis. Efficient management of energy resources, electric utilities, and transmission grids, can be greatly facilitated by harnessing the potential of this data. The aim of this study is to generate probability density estimates for consumption recorded by individual smart meters. Such estimates can assist decision making by helping consumers identify and minimize their excess electricity usage, especially during peak times. For suppliers, these estimates can be used to devise innovative time-of-use pricing strategies aimed at their target consumers. We consider methods based on conditional kernel density (CKD) estimation with the incorporation of a decay parameter. The methods capture the seasonality in consumption, and enable a nonparametric estimation of its conditional density. Using eight months of half-hourly data for one thousand meters, we evaluate point and density forecasts, for lead times ranging from one half-hour up to a week ahead. We find that the kernel-based methods outperform a simple benchmark method that does not account for seasonality, and compare well with an exponential smoothing method that we use as a sophisticated benchmark. To gauge the financial impact, we use density estimates of consumption to derive prediction intervals of electricity cost for different time-of-use tariffs. We show that a simple strategy of switching between different tariffs, based on a comparison of cost densities, delivers significant cost savings for the great majority of consumers.
Recommender systems objectives can be broadly characterized as modeling user preferences over short-or long-term time horizon. A large body of previous research studied long-term recommendation through dimensionality reduction techniques applied to the historical user-item interactions. A recently introduced session-based recommendation setting highlighted the importance of modeling short-term user preferences. In this task, Recurrent Neural Networks (RNN) have shown to be successful at capturing the nuances of users interactions within a short time window. In this paper, we evaluate RNN-based models on both short-term and long-term recommendation tasks. Our experimental results suggest that RNNs are capable of predicting immediate as well as distant user interactions. We also find the best performing configuration to be a stacked RNN with layer normalization and tied item embeddings.
In the wind energy industry, it is of great importance to develop models that accurately forecast the power output of a wind turbine, as such predictions are used for wind farm location assessment or power pricing and bidding, monitoring, and preventive maintenance. As a first step, and following the guidelines of the existing literature, we use the supervisory control and data acquisition (SCADA) data to model the wind turbine power curve (WTPC). We explore various parametric and non-parametric approaches for the modeling of the WTPC, such as parametric logistic functions, and non-parametric piecewise linear, polynomial, or cubic spline interpolation functions. We demonstrate that all aforementioned classes of models are rich enough (with respect to their relative complexity) to accurately model the WTPC, as their mean squared error (MSE) is close to the MSE lower bound calculated from the historical data. We further enhance the accuracy of our proposed model, by incorporating additional environmental factors that affect the power output, such as the ambient temperature, and the wind direction. However, all aforementioned models, when it comes to forecasting, seem to have an intrinsic limitation, due to their inability to capture the inherent auto-correlation of the data. To avoid this conundrum, we show that adding a properly scaled ARMA modeling layer increases short-term prediction performance, while keeping the long-term prediction capability of the model.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
