Ahead Market Research Articles

Algorithm Design of Day Ahead Market Marginal Price Forecasting Considering New Energy Absorptive Capacity

Algorithm Design of Day Ahead Market Marginal Price Forecasting Considering New Energy Absorptive Capacity

An energy management system to schedule the optimal participation to electricity markets and a statistical analysis of the bidding strategies over long time horizons

This paper presents a tool that allows to perform an ex-ante estimation of the profitability to participate to the electric energy and service markets for a microgrid or a polygeneration power plant. The tool is the evolution of an Energy Management System (EMS) previously developed by the University of Genoa and Renantis Solutions Srl. Constraints are added to the original EMS to model the Ancillary Service Market (ASM) and Day Ahead Market (DAM) mechanisms in the framework of a planning tool that allows to get estimates of the microgrid/plant costs and revenues over a long-time horizon. As the market outcome strongly depends on the Transmission System Operator (TSO) acceptance/rejection of bids and offers, a statistical approach is proposed. The optimization process is split in two steps: the first one optimally dispatches the energy units and proposes DAM offers and ASM bid and offers over a specified time horizon. Then, a Monte Carlo method is launched; at each extraction the TSO acceptance/rejection of each ASM bid and offer is simulated and there is a second step of optimization in which the energy sources are optimally re-dispatched to meet the bidding program and so to avoid imbalance power exchange that would increase the energy cost. The cost/revenue is thus computed at each extraction. The result is the probability density function of the costs/revenues that allows to estimate the profitability of the participation to the electricity markets. One test performed on a real microgrid shows that the computational time needed to complete one iteration related to a time horizon of one month is approximately 20 s. Moreover, the comparison of the outcomes with two independent launches to define the set of bids and offers to be accepted in ASM demonstrates that the statistical analysis allows to avoid misleading conclusions on the costs/revenues. Consequently, the fact that the developed EMS allows to perform a statistical analysis in a reasonable time enables the possibility of comparing multiple scenarios and gives an indication related to the range of cost/revenues in which the microgrid/plant may incur. Finally, the computational efficiency of the proposed approach allows to conclude that the developed EMS is appropriate to perform a long-time horizon (of the order of magnitude of years) analysis and, at the same time, allows to model all the involved components with a high level of details.

Selection of an algorithm for classifying data quoted on the Day Ahead Market of TGE S.A. in MATLAB and Simulink using Deep Learning Toolbox

The article contains an analysis leading to the selection of an algorithm for classifying data listed on the Day-Ahead Market of TGE S.A. in MATLAB and Simulink using Deep Learning Toolbox. In this regard, an introduction to deep learning methods, classification methods, and classification algorithms is provided first. Particular attention was paid to the essence of three important deep learningmethods in the classification, i.e. the methods called: Stochastic Gradient Descent Momentum, Root Mean Square Prop and Adaptive Moment Estimation. Then, three architectures of artificial neural networks used in deep learning were characterized, i.e.: Deep Belief Network, Convolutional Neural Network and Recurrent Neural Network. Attention was paid to the selection parameters of algorithms for learning deep artificial neural networks that can be used in classification, such as: accuracy, information losses and learning time. Practical aspects of research experiments were also shown, including selected results of research conducted on volume and fixing 1 data quoted on the TGE S.A. Day-Ahead Market. After analyzing the obtained test results for the hourly system, it was noted that the least suitable algorithm for classification purposes was the Stochastic Gradient Descent Momentum algorithm, which in each case had worse results than the other two algorithms, i.e. the Adaptive Moment Estimation algorithm and the Root Mean algorithm Square Prop. However, the best algorithm turned out to be the Adaptive Moment Estimation algorithm, which obtained the highest accuracy, which was at a level comparable to the Root Mean Square Prop algorithm, with the latter algorithm having larger losses.

A forecasting model for predicting electricity day-ahead market prices for scheduling industrial applications

Over the last 20 years, electricity price forecasting (EPF) modeling has become a fundamental process of the decision support mechanisms of energy companies for successfully participating in the power markets. Given the growing uncertainty and the stochasticity of the evolving energy mix, this process has also proven to be of importance for industrial companies whose production scheduling decisions are greatly affected by the energy costs. While different approaches have been tested (with varying degrees of success), in this study the accurate Day Ahead Market (DAM) prices prediction, in different European markets, are directly associated with the production scheduling processes of various industrial loads. We propose a configuration based on a Random Forest (RF) model implementation for the prediction of DAM prices for a number of European countries with interconnected electric (market) systems. The proposed model for a particular country is enriched by including power market information from neighboring countries, which in turn consistently improves the accuracy of the forecast. The distributed developed DAM price forecaster allows industries to schedule optimally their production processes with respect to energy cost reduction and energy efficiency improvement. The optimality of operations, sometimes, requires rescheduling of production activities in neighboring countries in the case of industries with multi-site production facilities.

A methodology of identification and metaidentification research on the example of Day Ahead Market System

A methodology of identification and metaidentification research on the example of Day Ahead Market System

PV Penetration under Market Environment and with System Constraints

The installed capacity of PVs in the distribution grid is affected not only by network constraints, but also by the economic viability of the related investments. Depending on the market participation models, this is determined critically by the Day Ahead Market (DAM) prices. Increasing RES installations in a country usually results in a long term drop in the market prices and, as a consequence, a reduction in the income of the PVs investors and possible market cannibalization. This paper models the effect of large-scale penetration of PVs on the market prices and identifies the optimal penetration level for the viability of PV projects. The optimal penetration is highly related to the installation of new PVs and this is a parameter for the analysis. Therefore, the paper identifies different penetration costs for the different installation cost. Furthermore, the PV network hosing capacity can be increased by distribution network reinforcements. Therefore, in the paper, the investments for enhancement of the distribution grid are assessed with respect to market prices and are analyzed at the macroscopic level. Again, the analysis considers different costs for network reinforcements.

Optimal Scheduling Research for Day Ahead Market Transaction of Virtual Power Plant Considering Uncertainty and CVaR

Considering the uncertainty of renewable energy generation and the market transaction risk in the day ahead market of virtual power plants, an optimal scheduling model of virtual power plant in the day ahead market was presented. Firstly, this study modeled and analyzed the uncertainty of wind and photovoltaic power generation fluctuations in the virtual power plant. In addition, based on the conditional value at risk theory and the day ahead market clearing rules, the optimal scheduling model of virtual power plants in the day ahead market was established aiming at minimizing the implementation deviation and maximizing the operating income. Finally, the transaction data of a typical region was selected for case study to verify the effectiveness and the feasibility of the optimal scheduling strategy of virtual power plant in day ahead market transaction.

Optimal Bidding Strategy of a Pumped Hydro Energy Storage Integrated Nuclear Power Plant considering Possible Outage

Recently, harmful gases emitted into the atmosphere disrupt the balance of nature and cause climate changes. The tendency towards renewable energy is increasing in order to prevent climate change. The importance of the conventional power plants in the power system is maintained due to the intermittent nature of renewable energy sources. In this regard, nuclear power which is one of the conventional power plants takes attention. In this study, a new approach for optimal scheduling of a Pumped Hydro Energy Storage (PHES) integrated Nuclear Power Plant (NPP) system is proposed. It is expected that PHES provides significant economic contribution to the grid operator especially by ensuring energy supply security of the NPP. Two different market types named Day Ahead Market (DAM) and Balancing Market (BM) in Turkey are implemented in the trades by using real electricity prices obtained from Energy Exchange Istanbul (EXIST), which is Energy Market Operator in Turkey. In order to evaluate the effectiveness of the proposed model, seasonal impacts of four different months are also examined in several case studies. Furthermore, sustainability analyzes are conducted considering probability of interruption of the NPP during 8 hours. According to the results, it is observed that promising solutions can be obtained thanks to the integration of the PHES in the presence of the different market types even if outages are planned.

Optimizing Hydrogen Production Capacity and Day Ahead Market Bidding for a Wind Farm in Texas

Optimizing Hydrogen Production Capacity and Day Ahead Market Bidding for a Wind Farm in Texas

Forecast for Market Clearing Price with Artificial Neural Networks in Day Ahead Market

In this study, the Market Clearing Price (MCP) is forecasted with Artificial Neural Networks and the modeling success is examined for different preprocessing strategies. The purpose of the study is to obtain the optimum model with a significant estimation success and to provide the best price prediction. The hour-based electricity generation data of diverse production items are assigned as inputs and the resulting MCP is modeled. The raw data are first cleaned from outliers, then subjected to different normalization processes and 70 different ANNs are trained. Additionally, networks are trained with data classified in seasons and the effect of seasonal patterns on model success is observed. Finally, networks showing the optimum performance are selected. It is noted that the type of the normalization strategy and the hidden layer size are the key factors to make a decent estimation. Then, in order to test the networks with extreme cases, data for the special days (official holidays) are applied to these networks as input. The success of the networks is evaluated by comparing the MCP predictions with the actual values. It is revealed to make a prediction for official holidays, a model which is special to this period of year is required.

Electricity Price Forecasting in European Day Ahead Markets: A Greedy Consideration of Market Integration

In this manuscript we explore European feature importance in Day Ahead Market (DAM) price forecasting models, and show that model performance can deteriorate when too many features are included due to over-fitting. We propose a greedy algorithm to search over candidate countries for European features to be used in a DAM price forecasting model, that can be applied to several regression and machine learning modelling methodologies. We apply the algorithm to build price forecasting models for the Dutch market, using candidate countries selected through an integrated analysis based on open-source European electricity market data. Feature importance is visualised using an Auto Regressive and Random Forest model. We explain these results using cross-border flow and DAM price data. Two types of models (LEAR and the Deep Neural Network) are considered for the DAM price forecasting with and without European features. We show that in the Dutch case, taking European market integration into account improves the Mean Absolute Error (MAE) of the best performing DAM price forecasting model by 3.1%, the relative MAE (rMAE) by 3.85%, and the Symmetrical Mean Absolute Percentage Error (sMAPE) by 0.31 p.p., compared to the best forecasting model without European features. Through statistical testing we show that European features improve the accuracy of the forecasts with statistical significance.

A Mixed-Integer Linear Programming for Nodal Clearing Price in Day Ahead Market Considering Security Constraints

A nodal clearing price model in day ahead market considering security constraints is established. First, the intra-region and inter-region transaction modes are explained, and the order types are shown. The clearing model takes the total social welfare as the goal, considers the security constraints of the network, and specifies the market clearing price expressed by the Lagrangian multiplier. Then the mixed linear programming algorithm is used to solve the model in this paper, and a verification method based on the N-1 criterion is performed. Finally, a numerical case is performed to calculate the clearing price of the network, which illustrates the effectiveness of the proposed method and model.

On the development of organized nodal local energy markets and a framework for the TSO-DSO coordination

In this paper we propose a market design for implementing organized nodal electricity markets for the distribution grid. Distribution System Operators (DSOs) are expected to manage a massive penetration of Distributed Energy Resources (DERs), such as Renewable Energy Resources (RES), Electric Vehicles (EVs), Storage and Demand response. A Day Ahead Market (DAM) and a Real-Time Market (RTM) is proposed to optimize and clear offers and bids submitted by the DERs. A Mixed Integer Programming (MIP) Security Constrained Unit Commitment (SCUC) and a Security Constrained Economic Dispatch (SCED) iterates with a detailed asymmetric and unbalanced three-phased Distribution Power Flow (DPF) to enforce all constraints in the distribution grid. The solution produces Distribution Locational Marginal Prices (DLMPs) for all phases at every node of the distribution grid. A general framework for the coordination of the DSO with the ISO/TSO markets is also presented as an integral part of the proposed multi-level energy market design. The proposed new methodology has been applied to an actual large-scale distribution system. Numerous simulation scenarios have been executed to prove the validity of the proposed approach. In this paper a simple small subset of the actual distribution system is selected to illustrate the proposed methodology.

Artificial Neural Networks with Turkey Interconnected System for Day Ahead Market Transmission Lines Estimated Losses

Gunumuzde ulke ekonomilerine olumsuz etkileri nedeniyle enerji kayiplarinin maliyeti oldukca onem arz etmektedir. Iletim sistemi kayiplari istenilen bir durum olmamakla beraber sifirlanmasi da mumkun degildir. Bu kapsamda, ulkemiz enterkonnekte iletim sisteminde meydana gelen enerji kayiplari, 28 Mart 2015 tarihinde Dengeleme ve Uzlastirma Yonetmeligi(DUY)’ne eklenen gecici 27. madde hukumleri dogrultusunda, Turkiye Elektrik Iletim Anonim Sirketi(TEIAS) yukumlulugune birakilmistir. Soz konusu tarihten itibaren Enerji Piyasalari Isletme Anonim Sirketi(EPIAS) tarafindan isletilen gun oncesi piyasasinda TEIAS piyasa katilimcisi olarak on gorulerini yapip, gerceklesen veriler ortaya cikmadan once bu miktarlari piyasadan satin almakla yukumlu hale getirilmistir. TEAIS’in iletim sistemi kayiplari icin gelir tavanindan ayirdigi kaynak ortalama 1.500.000.000 TL, dir. Bu kaynagin, 150.000.000 TL’lik kismini ise gun oncesi piyasasi icin yapilan tahmin hatalarina ayirmaktadir. Bu calismada, iletim sistemi kayip tahminlerinin en dogru sekilde yapilarak odenen tutarin azaltilmasi ve TEIAS ozelinde ulke ekonomisine katki saglanmasi amaclanmistir. Bu kapsamda, oncelikli olarak enterkonnekte iletim sistemi kayiplari ve Turkiye elektrik piyasasi anlatilmis, yapay sinir aglari hakkinda bilgi verilmistir. Son olarak, gerekli olan verilerin saglamasi amaciyla, ozgun olarak yazilimi yapilan, Turkiye Enterkonnekte Iletim Kaybi Tahmin programi olarak adlandirilan yazilim programi anlatilmis ve yapay sinir aglari araciligiyla yapilan tahminler, gerceklesen iletim kayiplari ile saatlik olarak kiyaslanmistir. Calismanin, TEIAS tarafindan iletim sistemi kayip tahminlerinde kullanmasi durumunda, enerji dengesizlik miktarinin ve tutarinin azalmasi ongorulmektedir.

Assessing Financial and Flexibility Incentives for Integrating Wind Energy in the Grid Via Agent-Based Modeling

This article provides an agent-based model of a hypothetical standalone electricity network to identify how the feed-in tariffs and the installed capacity of wind power, calculated in percentage of total system demand, affect the electricity consumption from renewables. It includes the mechanism of electricity pricing on the Day Ahead Market (DAM) and the Imbalance Market (IM). The extra production volumes of Electricity from Renewable Energy Sources (RES-E) and the flexibility of electrical consumption of industries is provided as reserves on the IM. Five thousand simulations were run by using the agent-based model to gather data that were then fit in linear regression models. This helped to quantify the effect of feed-in tariffs and installed capacity of wind power on the consumption from renewable energy and market prices. The consumption from renewable sources, expressed as percentage of total system consumption, increased by 8.17% for every 10% increase in installed capacity of wind power. The sharpest increase in renewable energy consumption is observed when a feed-in tariff of 0.04 €/kWh is provided to the wind farm owners, resulting in an average increase of 9.1% and 5.1% in the consumption from renewable sources while the maximum installed capacity of wind power is 35% and 100%, respectively. The regression model for the annualized DAM prices showed an increase by 0.01 €cents/kWh in the DAM prices for every 10% increase in the installed wind power capacity. With every increase of 0.01 €/kWh in the value of feed-in tariffs, the mean DAM price is lowered as compared to the previous value of the feed-in tariff. DAM prices only decrease with increasing installed wind capacity when a feed-in tariff of 0.04 €/kWh is provided. This is observed because all wind power being traded on DAM at a very cheap price. Hence, no volume of electricity is being stored for availability on IM. The regression models for predicting IM prices show that, with every 10% increase in installed capacity of wind power, the annualized IM price decreases by 0.031 and 0.34 €cents/kWh, when installed capacity of wind power is between 0 and 25%, and between 25 and 100%, respectively. The models also showed that, until the maximum installed capacity of wind power is less than 25%, the IM prices increase when the value of feed-in tariff is 0.01 and 0.04 €/kWh, but decrease for a feed-in tariff of 0.02 and 0.03 €/kWh. When installed capacity of wind power is between 25 and 100%, increasing feed-in tariffs to the value of 0.03 €/kWh result in lowering the mean IM price. However, at 0.04 €/kWh, the mean IM price is higher, showing the effect of no storage reserves being available on IM and more expensive reserves being engaged on the IM. The study concludes that the effect of increasing installed capacity of wind power is more significant on increasing consumption of renewable energy and decreasing the DAM and IM prices than the effect of feed-in tariffs. However, the effect of increasing values of both factors on the profit of RES-E producers with storage facilities is not positive, pointing to the need for customized rules and incentives to encourage their market participation and investment in storage facilities.

Improvement in social welfare division among buyer and supplier in LP based market clearing method in day-ahead electricity market

ABSTRACTMost Electric Power Exchange (PX) around the world employs Linear Programming (LP) based method for step-wise market clearing in Day-Ahead Electricity Market (DAM). Market clearing involves calculation of Market Clearing Volume (MCV) and Market Clearing Price (MCP) for various time blocks. LP based method gives accurate results when there exists unique intersection point between cumulative supply and cumulative demand curve. It requires additional information to handle multiple intersection points. But MCP obtained using LP based method leads to an unfair social welfare division among suppliers and buyers. Therefore, this paper investigates all possible cases where there exists an unfair social welfare division among suppliers and buyers. Modification to the existing LP based market clearing method to obtain that market equilibrium point which results in fair social welfare division is also discussed. The performance of the proposed method to obtain MCV & MCP which ensures fair social welfare division between suppliers and buyers under six different cases is tested using a simple test problem and DAM data obtained from Indian Energy Exchange (IEX) websites. Results clearly show that the proposed method is capable enough to generate market equilibrium which results in fair social welfare division among buyers and suppliers.Abbreviations: PX - Electric Power Exchange; LP - Linear Programming; DAM - Day Ahead Electricity Market; MCV - Market Clearing Volume; MCP - Market Clearing Price; IEX - Indian Energy Exchange; USD - United States Dollar; REC - Renewable Energy; TAM - Term Ahead Market; CERC - Central Electricity Regulatory Commission

A neural model supported by the Evolutionary Algorithm inspired by quantum calculations to determine prices at the Polish Power Exchange Day Ahead Market

The paper contains selected results of research related to the nature and the implementation of the neural model supported by the evolutionary algorithm inspired by quantum calculations for determination of prices at the Polish Power Exchange. Numeric data quoted at the Day Ahead Market in the period of 1st January 2015 to 30th June 2015 were used to train the artificial neural network in the model of the system. Attention was paid to quantization method, dequantization method and the method of quantum calculations. Significant improvement of the neural model supported by the quantum-inspired evolutionary algorithm was obtained compared with the model without quantum inspiration.

Stochastic Operation Framework for Distribution Networks Hosting High Wind Penetrations

In this paper, a stochastic framework including two hierarchical stages is presented for the operation of distribution networks with high penetrations of wind power. In the first stage termed Day Ahead Market Stage (DAMS), the power purchases from the day-ahead market and commitment of distributed generations (DGs) are determined. The DAMS model is formulated as a mixed integer linear programming optimization problem. The uncertainty in predictions of wind generation, real time prices, and load profile are included in the optimization problem according to a scenario-based stochastic programming approach. The risk encountered due to the uncertainties is also taken into account. The objective is to minimize the expected operation cost while satisfying the acceptable level of risk. In the second stage named Real Time Market Stage (RTMS), the power purchases from the real time market, dispatch of committed DGs, load curtailment invocations, and hourly reconfigurations are determined. In each hour, the RTMS problem is solved based on the information of that hour and next few hours. To prevent large numbers of switching operations during a day, the switching cost of reconfiguration is considered. The RTMS is modeled as a mixed integer conic programming problem. To analyze the proposed framework, the IEEE 33-bus DN is used as a case study.

Optimal Bidding Strategy for Profit Maximization of Generation Companies based on Whale Optimization Algorithm in Day Ahead Market

Optimal Bidding Strategy for Profit Maximization of Generation Companies based on Whale Optimization Algorithm in Day Ahead Market

STATE-SPACE MODEL AND IMPLEMENTATION POLISH POWER EXCHANGE IN MATLAB AND SIMULNK ENVIRONMENTS

This work contains selected results of research on modelling identification of Polish Power Exchange (TGEE) on the example of the figures quoted on the Day Ahead Market (DAM) on TGEE in Poland. In order to obtain a model of the TGEE system on the beginning it was conducted to identify the figures for the period 01.01.2013-31.12.2015 obtaining discrete parametric model arx in MATLAB and Simulink environments using System Identification Toolbox (SIT). The resultant model was converted to a continuous parametric model, and that one on a continuous model in the state space. On the basis of obtained equations of state and outputs, there was interpreted a state variables and parameters of the selected model, i.e. selected elements of the matrix A and matrix B. Research continues.