Search

The article is concerned with a theoretical generalization of the use of indices for electric power at the European spot exchanges and elaborating proposals on establishment of a similar spot index for the Ukrainian power exchange. 16 indices that are published daily by the power exchanges BSP Regional Energy Exchange, Power Exchange Central Europe, Polish Power Exchange and Opcom have been analyzed. It has been indicated that these indices are used for electricity price forecasting and monitoring the situation in the power market. The article examines the way spot indices are calculated by power exchanges, based on the value of the arithmetic average of market prices «day ahead». Imperfection of such way of calculation for price index values has been substantiated. The key characteristics of the future price index for Ukrainian spot market as benchmarks within the introduction of futures contracts for electricity have been identified.

A novel hybrid data-driven approach is developed for forecasting power system parameters with the goal of increasing the efficiency of short-term forecasting studies for non-stationary time-series. The proposed approach is based on mode decomposition and a feature analysis of initial retrospective data using the Hilbert-Huang transform and machine learning algorithms. The random forests and gradient boosting trees learning techniques were examined. The decision tree techniques were used to rank the importance of variables employed in the forecasting models. The Mean Decrease Gini index is employed as an impurity function. The resulting hybrid forecasting models employ the radial basis function neural network and support vector regression. A part from introduction and references the paper is organized as follows. The second section presents the background and the review of several approaches for short-term forecasting of power system parameters. In the third section a hybrid machine learningbased algorithm using Hilbert-Huang transform is developed for short-term forecasting of power system parameters. Fourth section describes the decision tree learning algorithms used for the issue of variables importance. Finally in section six the experimental results in the following electric power problems are presented: active power flow forecasting, electricity price forecasting and for the wind speed and direction forecasting.

Despite the availability of a large number of different methods for industrial sector forecasting, there is a shortage of methods that could provide a reliable fore-cast of the Ukrainian transport system development. Forecasting the transport system development is particularly important for Ukraine as a country that has been at the stage of its economy reconstruction. Identi-fication of trends in the development of the transport industry allows making deci-sions that could contribute to the achievement of sustainable development goals of the entire nation. Various methods of long-term forecasting have been analyzed and classified in the paper. The ForFITS Model developed by the United Nations Economic Commis-sion for Europe was chosen to forecast the transport activity to provide passenger transportation, energy use, and CO2 emission in Ukraine. On the basis of the existing trends, using the ForFITS Model we have made a preliminary forecast of the Ukrainian transport system development, which has re-vealed a high degree of dependence of the Model on the quality of the initial information and made it possible to develop a concept of rational forecasting horizon. [ABSTRACT FROM AUTHOR]

Energy saving on railway transport under a market economy is one of the priorities of scientific and technical policy of Ukrzaliznytsa. A very big impact on the profitability of the transport process has the dynamics of prices growth on power sources, and, in particular, on electricity. It should be noted that the work on energy efficiency and reducing the cost of electricity, which was held on ukrainian railways during the existence of an independent Ukraine, despite a significant increase of electricity prices in recent years to keep the energy costs in total expenditures on transportation at the same level. In this paper we show that the optimal coefficients of transformers calculated by unit costs are more than optimal transformers coefficients calculated on the base of coefficient of efficiency. It's found that the optimal load factor of power transformers inversely depends on the cost of electricity and the nominal power of the transformer. Using of the rational modes of the transformers allow us to reduce the technological expenses to the electric power. [ABSTRACT FROM AUTHOR]