We examine the relationship between German wind and solar electricity and French spot price volatility. Using hourly data, we find that French imports from Germany driven by German wind and solar electricity sometimes decrease, sometimes increase the volatility of French spot prices. These two opposing effects depend on the shape of the French supply function and on the French demand. We, therefore, estimate different coefficients for imports depending on different demand levels. We acknowledge the endogeneity problem in identifying these effects and employ instrumental variable techniques to circumvent this problem. Our results show the urgent need for further coordination of national energy policies in order to reduce the potential for negative spill over effects of nationally driven energy policies in neighbouring countries as European electricity markets are becoming more integrated. / Series: Department of Economics Working Paper Series

Within forecasting electricity pricing, we analyse whether adding various vari- ables improves the predictions, and if shorter time intervals between observa- tions enhance accuracy of the forecasting. Next, we focus on proper selection of lagged observations, which has not been thoroughly covered in the past litera- ture. In addition, many papers studied electricity prices in larger markets (e.g. United States, Australia, Nord Pool, etc.) on datasets limited in scope, with 2-3 years timespan. To address these gaps in literature, we obtain one daily and one hourly dataset, both spanning 6 years (January 1, 2015 - December 31, 2020), from four Central and Eastern European countries - the Czech Repub- lic, the Slovak Republic, Hungary, and Romania. These contain information on the electricity prices, and information on our observed added variables - temperature and cross-border electricity flows. For the forecasting, we use two different methods - Autoregression (AR) and Seemingly Unrelated Regression (SUR). The thorough selection of lagged observations, which we accustom to the closing time of the auction-based electricity market system, serves further studies as a guidance on how to avoid possible errors and inconsistencies in their predictions. In our analyses, both AR and SUR models show that...

Many methods have been used to forecast real-time electricity prices in various regions around the world. The problem is difficult because of market volatility affected by a wide range of exogenous variables from weather to natural gas prices, and accurate price forecasting could help both suppliers and consumers plan effective business strategies. Statistical analysis with autoregressive moving average methods and computational intelligence approaches using artificial neural networks dominate the landscape. With the rise in popularity of convolutional neural networks to handle problems with large numbers of inputs, and convolutional neural networks conspicuously lacking from current literature in this field, convolutional neural networks are used for this time series forecasting problem and show some promising results. This document fulfills both MSEE Master's Thesis and BSCPE Senior Project requirements.

Power systems all over the world advance towards the direction of deregulation in the past few years. Introducing competition mechanism and the principle of market rules in deregulation. Utility companies will face unprecedented changes and challenges. Taiwan power company is also working on the deregulation direction with a competitive environment opened up, it will improve the scientific and technological levels and the service quality of electricity. Load management functions as the marginal price of electricity is predicted. Consumers can get Real-Time Pricing information determine their own buying strategy. One most representative deregulation example in U.S.A. is the PJM(Pennsylvania¡BNew Jersey¡BMaryland)system combining generating, transmitting, distribution and sales of electricity. It offers the information of real-time power supply and is one of the cases in the world. Historical data in the thesis comes from PJM. Artificial Neural Network was designed to the Locational Marginal Price(LMP), considering the factors such as temperature and other relevant data from deregulation with the introduction of various parameters in forecasting, and the use of week as a counting base. LMP will be forecasted. The forecasted results will be to check the accuracy and performance with initial data.

The Swing options are the natural outcomes of the increasing uncertainty in the power markets, which came along with the deregulation process triggered by the UK government&rsquo / s action in 1990 to privatize the national electricity supply industry. Since then, the ways of handling the risks in the price generation process have been explored extensively. Producer-consumers of the power market felt confident as they were naturally hedged against the price fluctuations surrounding the large consumers. Companies with high power consumption liabilities on their books demanded tailored financial products that would shelter them from the upside risks while not preventing them from benefiting the low prices. Furthermore, more effective risk management practices are strongly dependent upon the successful parameterization of the underlying stochastic processes, which is also key to the effective pricing of derivatives traded in the market. In this thesis, we refer to the electricity spot price model developed jointly by Hambly, Howison and Kluge ([13]), which incorporates jumps and still maintains the analytical tractability. We also derive the forward curve dynamics implied by the spot price model and explore the effects on the forward curve dynamics of the spikes in spot price. As the main discussion of this thesis, the Grid Approach, which is a generalization of the Trinomial Forest Method, is applied to the electricity Swing options. We investigate the effects of spikes on the per right values of the Swing options with various number of exercise rights, as well as the sensitivities of the model-implied prices to several parameters.

The purpose of this study is to describe and analyze how manufacturing companies are affected by the electricity crisis and what measures they have taken to maintain liquidity in their operations. To achieve this, the empirical evidence will be based on interviews with manufacturing companies located in electricity area 4. To answer the questions “In what way have manufacturing companies in electricity area 4 been affected during the current electricity crisis?” and “How have these companies changed their operations and managed their liquidity and costs during the electricity crisis?” the study is based on an abductive research and on a qualitative research method. The results of the study shows that companies with variable electricity contracts in combination with an electricity cost that makes up a larger part of their manufacturing cost have suffered the most from a liquidity point of view. The most common measures taken by the companies were to increase the selling price, reduce their electricity use and become more self-sufficient in electricity.

To overcome the curse of dimensionality, dimension reduction is important and necessary for understanding the underlying phenomena in a variety of fields. Dimension reduction is the transformation of high-dimensional data into a meaningful representation in the low-dimensional space. It can be further classified into feature selection and feature extraction. In this thesis, which is composed of four projects, the first two focus on feature selection, and the last two concentrate on feature extraction. The content of the thesis is as follows. The first project presents several efficient methods for the sparse representation of a multiple measurement vector (MMV); some theoretical properties of the algorithms are also discussed. The second project introduces the NP-hardness problem for penalized likelihood estimators, including penalized least squares estimators, penalized least absolute deviation regression and penalized support vector machines. The third project focuses on the application of manifold learning in the analysis and prediction of 24-hour electricity price curves. The last project proposes a new hessian regularized nonlinear time-series model for prediction in time series.

Production of electric energy is continuously affected by many factors. Therefore, tools for predicting the future production are needed. In turn, the production affects the electric energy price, which is set on electric energy exchanges. This thesis is intended to find out if the software SDDP can be used for hydrothermal power production simulations in the Nord pool area. By building a simplified model of the electric energy production in Sweden with a focus on hydro, thermal and wind power, the intention is to see how the model is affected by different conditions. The investigated conditions are several; higher and lower water inflows to the hydro power reservoirs; different amounts of installed wind power production; different price levels of emission allowances for CO2. By using the simulation software SDDP, more wind power was seen to lower the electric energy prices, as well as reduce the need of transmission of power from the northern to the southern parts of Sweden. In the simulation, Sweden was divided into four areas, connected where the main bottlenecks in the power grid are located. Water inflows to the reservoirs are crucial in the model. Actual inflow data can be bought from SMHI. However, due to the limited thesis budget, estimations were constructed instead. The estimations were difficult to make and turned out to be too high. Consequently, no reliable evaluation of the SDDP software could be done using this data.

There is a demand for decision support tools that can model the electricity markets and allows to forecast the hourly electricity price. Many different ap- proach such as artificial neural network or support vector regression are used in the literature. This thesis provides comparison of several different estima- tors under one settings using available data from Czech electricity market. The resulting comparison of over 5000 different estimators led to a selection of several best performing models. The role of historical weather data (temper- ature, dew point and humidity) is also assesed within the comparison and it was found that while the inclusion of weather data might lead to overfitting, it is beneficial under the right circumstances. The best performing approach was the Lasso regression estimated using modified Lars. 1

The main topic of this thesis is the trading with one of the most important commodity in the market – electricity. This thesis will analyse the topic from the point of view of a natural person who potentially would like to start trading in the market. The description focuses on causes and consequences of the market liberalization. The electricity trading will be also analyzed from the point of view of a consumer and also of a producer. Possibilities will be listed on how to purchase and sell electricity, principles how particular markets work and also comparison of the price of electricity with the prices of other commodities. The aim is to give a detailed description about domestic market electricity price creation. The main purpose of this thesis is to describe the situation in the domestic market with electricity and future development in this branch, expressing also considerations about switching the electricity supplier.