Search

Geographically distributed wind turbines, photovoltaic panels and sensors (e.g., pyranometers) produce large volumes of data that can be used to improve renewable energy forecasting skill. However, data owners may be unwilling to share their data, even if privacy is ensured, due to a form of prisoner's dilemma: all could benefit from data sharing, but in practice no one is willing to do do. Our proposal hence consists of a data marketplace, to incentivize collaboration between different data owners through the monetization of data.We adapt here an existing auction mechanism to the case of renewable energy forecasting data. It accommodates the temporal nature of the data, i.e., lagged time-series act as covariates and models are updated continuously using a sliding window. A test case with wind energy data is presented to illustrate and assess the effectiveness of such data markets. All agents (or data owners) are shown to benefit in terms of higher revenue resulting from the combination of electricity and data markets. The results support the idea that data markets can be a viable solution to promote data exchange between renewable energy agents and contribute to reducing system imbalance costs.

This paper proposes a Local Energy Market using a P2P blockchain-powered marketplace where agents bilaterally trade energy after the consumption and production period, and not before, as usual in electricity market design. The EU and MIBEL regulatory framework for Renewable Energy Communities potentially creates space for such a market, but some improvements in the settlement procedures and agent’s participation must be met.

Variable-speed pump power storage is an innovative large-scale technology that is being deployed across the world. In addition to price arbitrage and provision of downward replacement reserve, its operational flexibility enables the provision of frequency restoration reserve (FRR) both in turbine and pump modes. This work proposes a bidding optimization strategy for the participation in the FRR market. The proposed framework encompasses a medium-term module to optimally allocate the yearly natural water inflows, representation of electrical and hydraulic losses in the water inflow/power curves, as well as forecasting techniques to predict market prices and natural water inflows. Moreover, it does not assume prior knowledge of the amount of activated FRR capacity band. An evaluation module is also proposed to replicate the “real” operation of the power plant and enables an accurate calculation of the revenue. A comparison between fixed and variable-speed Pump storage power (PSP) units participating in the Iberian electricity market presented an increase in revenue of almost 12%. Due to the low liquidity of the FRR market in Portugal, and the considerable capacity of the PSP unit, under some specific situations, it might be necessary to cap the size of the FRR bid to decrease the difference between the expected and realized revenue.

This paper analyzes the electricity prices of the MIBEL electricity spot market with respect to a set of possible explanatory variables. Understanding the main drivers of the electricity price is a key aspect in understanding price formation and in developing forecasting models, which are essential for the selling and buying strategies of market agents. For this analysis, different techniques have been applied in this work, including standard and lasso regression models, causal analysis based on bayesian networks and classification trees. Results from the different approaches are coherent and show strong dependency of the electricity prices with the Portuguese imported coal for lower non-dispatchable net demands, which has been progressively replaced by gas for larger non-dispatchable net demands. Hydro reservoirs and hydro production are also main explanatory variables of the electricity price for all non-dispatchable net demand levels.

Forecasts of residual demand curves (RDCs) are valuable information for price-maker market agents since it enables an assessment of their bidding strategy in the market-clearing price. This paper describes the application of deep learning techniques, namely long short-term memory (LSTM) network that combines past RDCs and exogenous variables (e.g., renewable energy forecasts). The main contribution is to build up on the idea of transforming the temporal sequence of RDCs into a sequence of images, avoiding any feature reduction and exploiting the capability of LSTM in handling image data. The proposed method was tested with data from the Iberian day-ahead electricity market and outperformed machine learning models with an improvement of above 35% in both root mean square error and Frechet distance.

Chapter Overview The technological revolution in the electric power system sector is producing large volumes of data with pertinent impact in the business and functional processes of system operators, generation companies, and grid users. Big data techniques can be applied to state estimation, forecasting, and control problems, as well as to support the participation of market agents in the electricity market. This chapter presents a revision of the application of data mining techniques to these problems. Trends like feature extraction/reduction and distributed learning are identified and discussed. The knowledge extracted from power system and market data has a significant impact in key performance indicators, like operational efficiency (e.g., operating expenses), investment deferral, and quality of supply. Furthermore, business models related to big data processing and mining are emerging and boosting new energy services.

Forecasting the hourly spot price of day-ahead and intraday markets is particularly challenging in electric power systems characterized by high installed capacity of renewable energy technologies. In particular, periods with low and high price levels are difficult to predict due to a limited number of representative cases in the historical dataset, which leads to forecast bias problems and wide forecast intervals. Moreover, these markets also require the inclusion of multiple explanatory variables, which increases the complexity of the model without guaranteeing a forecasting skill improvement. This paper explores information from daily futures contract trading and forecast of the daily average spot price to correct point and probabilistic forecasting bias. It also shows that an adequate choice of explanatory variables and use of simple models like linear quantile regression can lead to highly accurate spot price point and probabilistic forecasts. In terms of point forecast, the mean absolute error was 3.03 €/MWh for day-ahead market and a maximum value of 2.53 €/MWh was obtained for intraday session 6. The probabilistic forecast results show sharp forecast intervals and deviations from perfect calibration below 7% for all market sessions.

Power system regulators and operators are creating conditions for encouraging the participation of the demand-side into reserve markets. The electric vehicle (EV), when aggregated by a market agent, holds sufficient flexibility for offering reserve bids. Nevertheless, due to the stochastic nature of the drivers’ behavior and market variables, forecasting and optimization algorithms are necessary for supporting an EV aggregator participating in the electricity market. This paper describes a new day-ahead optimization model between energy and secondary reserve bids and an operational management algorithm that coordinates EV charging in order to minimize differences between contracted and realized values. The use of forecasts for EV and market prices is included, as well as a market settlement scheme that includes a penalty term for reserve shortage. The optimization framework is evaluated in a test case constructed with synthetic time series for EV and market data from the Iberian electricity market.

The charging flexibility of electric vehicles (EV) when aggregated by a market agent creates an opportunity for selling manual reserve in the electricity market. This paper describes a new optimization algorithm for optimizing manual reserve bids. Furthermore, two operational management algorithms covering alternative gate closures (i.e., day-ahead and hour-ahead) are also described. These operational algorithms coordinate EV charging for mitigating forecast errors. A case-study with data from the Iberian electricity market and synthetic EV time series is used for evaluating the algorithms.

This paper addresses the bidding problem faced by an electric vehicles (EV) aggregation agent when participating in the day-ahead electrical energy market. Two alternative optimization approaches, global and divided , with the same goal (i.e. solve the same problem) are described. The difference is on how information about EV is modeled. The global approach uses aggregated values of the EV variables and the optimization model determines the bids exclusively based on total values. The divided approach uses individual information from each EV. In both approaches, statistical forecasting methods are formulated for the EV variables. After the day-ahead bidding, a second phase (named operational management) is required for mitigating the deviation between accepted bids and consumed electrical energy for EV charging. A sequential linear optimization problem is formulated for minimizing the deviation costs. This chain of algorithms provides to the EV aggregation agent a pathway to move to the smart-grid paradigm where load dispatch is a possibility.

This paper presents numerical analysis of two alternative optimization approaches intended to support an EV aggregation agent in optimizing buying bids for the day-ahead electricity market. A study with market data from the Iberian electricity market is used for comparison and validation of the forecasting and optimization performance of the global and divided optimization approaches. The results show that evaluating the forecast quality separately from its impact in the optimization results is misleading, because a forecast with a low error might result in a higher cost than a forecast with higher error. Both bidding approaches were also compared with an inflexible EV load approach where the EV are not controlled by an aggregator and start charging when they plug-in. Results show that optimized bids allow a considerable cost reduction when compared to an inflexible load approach, and the computational performance of the algorithms satisfies the requirements for operational use by a future real EV aggregation agent.

Wind power probabilistic forecast is a key input in decision-making problems under risk, such as stochastic unit commitment, operating reserve setting and electricity market bidding. While the majority of the probabilistic forecasting methods are based on quantile regression, the associated limitations call for new approaches. This paper described a new quantile regression model based on the Reproducing Kernel Hilbert Space (RKHS) framework. In particular, two versions of the model, off-line and on-line, were implemented and tested for a real wind farm. Results showed the superiority of the on-line approach in terms of performance, robustness and computational cost. Additionally, it was observed that, in the presence of correlated data, the optimal on-line learning may cause unreliable modelling. Potential solutions to this effect are also described and implemented in the paper.

With the liberalization of the electricity markets, price forecasting has become crucial for the decision-making process of market agents. The unique features of electricity price, such as non-stationary, non-linearity and high volatility make this a very difficult task. For this reason, rather than a simple point forecast, market participants are more interested in a probabilistic forecast that is essential to estimate the uncertainty involved in the price. By focusing on this issue, the aim of this paper is to analyze the impact of external factors in the electricity price and present a methodology for probabilistic forecasting of day-ahead electricity prices from the Iberian electricity market. The models are built using regression techniques and aim to obtain, for each hour, the quantiles of 5% to 95% by steps of 5%.

This paper discusses the potential use of probabilistic wind power forecasting in electricity markets, with focus on the scheduling and dispatch decisions of the system operator. We apply probabilistic kernel density forecasting with a quantile-copula estimator to forecast the probability density function, from which forecasting quantiles and scenarios with temporal dependency of errors are derived. We show how the probabilistic forecasts can be used to schedule energy and operating reserves to accommodate the wind power forecast uncertainty. We simulate the operation of a two-settlement electricity market with clearing of day-ahead and real-time markets for energy and operating reserves. At the day-ahead stage, a deterministic point forecast is input to the commitment and dispatch procedure. Then a probabilistic forecast is used to adjust the commitment status of fast-starting units closer to real time, on the basis of either dynamic operating reserves or stochastic unit commitment. Finally, the real-time dispatch is based on the realized availability of wind power. To evaluate the model in a large-scale real-world setting, we take the power system in Illinois as a test case and compare different scheduling strategies. The results show better performance for dynamic compared with fixed operating reserve requirements. Furthermore, although there are differences in the detailed dispatch results, dynamic operating reserves and stochastic unit commitment give similar results in terms of cost. Overall, we find that probabilistic forecasts can contribute to improve the performance of the power system, both in terms of cost and reliability. Copyright © 2012 John Wiley & Sons, Ltd.

An electric vehicle (EV) aggregation agent, as a commercial middleman between electricity market and EV owners, participates with bids for purchasing electrical energy and selling secondary reserve. This paper presents an optimization approach to support the aggregation agent participating in the day-ahead and secondary reserve sessions, and identifies the input variables that need to be forecasted or estimated. Results are presented for two years (2009 and 2010) of the Iberian market, and considering perfect and naive forecast for all variables of the problem.

SUMMARY The foreseeable increase in the use of electric vehicles (EV) led to the discussion on intermediate entities that could help manage a great number of EV. An aggregation agent for electric vehicles is a commercial middleman between a system operator (SO) and plug-in EV. From the SO perspective, the aggregator is seen as a large source of generation or load, which could provide ancillary services such as spinning and regulating reserve. Generally, these services will be provided in the day-ahead and intraday electricity markets. In addition, the aggregator also participates in the electricity market with supply and demand energy bids. This paper provides a comprehensive bibliographic survey on the aggregator role in the power system operation and electricity market. The scope of the survey covers 59 references divided in journal, conference proceedings, thesis, research papers, and technical reports published after 1994. These papers are put into several technical categories: electricity market and EV technical and economic issues; aggregation agent concept, role and business model; algorithms for EV management as a load/resource. Copyright © 2011 John Wiley & Sons, Ltd.

This paper reports a study on the importance of the training criteria for wind power forecasting and calls into question the generally assumed neutrality of the ‘goodness’ of particular forecasts. The study, focused on the Spanish Electricity Market as a representative example, combines different training criteria and different users of the forecasts to compare them in terms of the benefits obtained. In addition to more classical criteria, an information theoretic learning training criterion, called parametric correntropy, is introduced as a means to correct problems detected in other criteria and achieve more satisfactory compromises among conflicting criteria, namely forecasting value and quality. We show that the interests of wind farm owners may lead to a preference for biased forecasts, which may be in conflict with the larger needs of secure operating policies. The ideas and conclusions are supported by results from three real wind farms. Copyright © 2010 John Wiley & Sons, Ltd.

Photovoltaic (PV) solar power capacity is growing in several countries, either concentrated in medium/large size solar parks or distributed by the medium and low voltage grid. Solar power forecasting is a key input for supporting grid management, participation in the electricity market and maintenance planning. This paper proposes a new forecasting system that is a hybrid of different models, such as electrical and statistical models, as well as different Numerical Weather Prediction (NWP) sources. The time horizon is 48 hours ahead. The proposed model was operationalized and tested in a real PV installation located in North Portugal with 16 kW.

Demand aggregators are new market players that represent a group of consumers in the electricity market. This paper proposes an aggregator model responsible for gathering residential and commercial consumers, which has the role of managing their flexible consumption in the day-ahead electricity market. A methodology to optimize the aggregator's bids is also presented. It optimizes the scheduling of the flexible loads taking simultaneously into account the consumers' preferences and temporal trajectories of forecasted outdoor temperatures and electricity prices. The proposed methodology was tested using a case study with 200 residential and commercial consumers from the Iberian market.

The Electric Vehicle (EV) is one source of flexibility to the electric power system. When aggregated by a market agent, it can offer its flexibility in the balancing reserve market. In order to meet this goal, a framework of optimization and forecasting algorithms must designed to cover the different time horizons of the decision process. This paper describes a full framework for EV aggregators participating in different electricity market sessions. This framework is illustrated for the balancing reserve market and the impact of forecasts of different quality for the balancing reserve direction is evaluated. The test case consists in synthetic time series generated from real data for 3000 EV participating in the Iberian electricity market.

This book chapter reports a study on the importance of modeling wind power uncertainty in the reliability assessment commitment procedure. The study compares, in terms of economic and reliability benefits, the deterministic and stochastic approaches to modeling wind power. The report describes the mathematical formulation of both approaches and gives numerical results on a 10-unit test system. It is found that scenario representation of wind power uncertainty in conjunction with a proper reserve margin to accommodate for wind power uncertainty may provide higher benefits to market participants.

Summary form only given. In this paper we analyze how demand dispatch combined with the use of probabilistic wind power forecasting can help accommodate large shares of wind power in electricity market operations. We model the operation of day-ahead and real-time electricity markets, which the system operator clears by centralized unit commitment and economic dispatch. We use probabilistic wind power forecasting to estimate dynamic operating reserve requirements, based on the level of uncertainty in the forecast. At the same time, we represent price responsive demand as a dispatchable resource, which adds flexibility in the system operation. In a case study of the power system in Illinois, we find that both demand dispatch and probabilistic wind power forecasting can contribute to efficient operation of electricity markets with large shares of wind power.

In order to participate in the electricity market, electric vehicles (EV) need to be aggregated by a market agent, since the current rules do not allow the participation of small loads. The EV aggregator purchases electrical energy for charging its clients, and can offer reserve services. This activity requires forecasting methods for several variables. This paper presents a global view of the relevant variables for an EV aggregation agent participating in the electricity market and discusses the associated forecasting issues. The load forecast problem for direct and indirect control of the EV charging process is discussed. Variables from the market-side, such as reserve price and direction, are also addressed. Existing approaches are reviewed, discussed and tested according to different metrics.

The participation of an EV aggregator in the electricity market for purchasing electrical energy requires an algorithm for managing the EV charging during the operational day. In this paper the coordination of EV for minimizing the deviation between bid and consumed electrical energy is studied and compared with an uncoordinated strategy. Two algorithms are proposed: a heuristic algorithm that dispatches the EV for each time interval separately, and another one, formulated as an optimization problem for dispatching the EV considering all the time intervals. Furthermore, the aggregator architecture is compared with an autonomous architecture where each EV operates and participates in the market individually. The results, for a realistic case-study, show that the aggregator with an optimized coordination strategy achieves the lowest deviation cost and magnitude. (6 pages)

Wind power forecasting (WPF) provides important inputs to power system operators and electricity market participants. It is therefore not surprising that WPF has attracted increasing interest within the electric power industry. In this report, we document our research on improving statistical WPF algorithms for point, uncertainty, and ramp forecasting. Below, we provide a brief introduction to the research presented in the following chapters. For a detailed overview of the state-of-the-art in wind power forecasting, we refer to [1]. Our related work on the application of WPF in operational decisions is documented in [2]. Point forecasts of wind power are highly dependent on the training criteria used in the statistical algorithms that are used to convert weather forecasts and observational data to a power forecast. In Chapter 2, we explore the application of information theoretic learning (ITL) as opposed to the classical minimum square error (MSE) criterion for point forecasting. In contrast to the MSE criterion, ITL criteria do not assume a Gaussian distribution of the forecasting errors. We investigate to what extent ITL criteria yield better results. In addition, we analyze time-adaptive training algorithms and how they enable WPF algorithms to cope with non-stationary data and, thus, to adapt to new situations without requiring additional offline training of the model. We test the new point forecasting algorithms on two wind farms located in the U.S. Midwest. Although there have been advancements in deterministic WPF, a single-valued forecast cannot provide information on the dispersion of observations around the predicted value. We argue that it is essential to generate, together with (or as an alternative to) point forecasts, a representation of the wind power uncertainty. Wind power uncertainty representation can take the form of probabilistic forecasts (e.g., probability density function, quantiles), risk indices (e.g., prediction risk index) or scenarios (with spatial and/or temporal dependence). Statistical approaches to uncertainty forecasting basically consist of estimating the uncertainty based on observed forecasting errors. Quantile regression (QR) is currently a commonly used approach in uncertainty forecasting. In Chapter 3, we propose new statistical approaches to the uncertainty estimation problem by employing kernel density forecast (KDF) methods. We use two estimators in both offline and time-adaptive modes, namely, the Nadaraya-Watson (NW) and Quantilecopula (QC) estimators. We conduct detailed tests of the new approaches using QR as a benchmark. One of the major issues in wind power generation are sudden and large changes of wind power output over a short period of time, namely ramping events. In Chapter 4, we perform a comparative study of existing definitions and methodologies for ramp forecasting. We also introduce a new probabilistic method for ramp event detection. The method starts with a stochastic algorithm that generates wind power scenarios, which are passed through a high-pass filter for ramp detection and estimation of the likelihood of ramp events to happen. The report is organized as follows: Chapter 2 presents the results of the application of ITL training criteria to deterministic WPF; Chapter 3 reports the study on probabilistic WPF, including new contributions to wind power uncertainty forecasting; Chapter 4 presents a new method to predict and visualize ramp events, comparing it with state-of-the-art methodologies; Chapter 5 briefly summarizes the main findings and contributions of this report.

In this paper we discuss the use of wind power forecasting in electricity market operations. In particular, we demonstrate how probabilistic forecasts can contribute to address the uncertainty and variability in wind power. We focus on efficient use of forecasts in the unit commitment problem and discuss potential implications for electricity market operations.

It is foreseeable that electricity retailers for electrical mobility will be market agents. These retailers are electric vehicle (EV) aggregation agents, which operate as a commercial middleman between electricity market and EV owners. Furthermore, with the foreseen evolution of the smart-grid concept, these agents will be able to control the EV charging rates and offer several ancillary services. This paper formulates an optimization problem for the EV aggregation agent participation in the day-ahead and secondary reserve market sessions. Forecasting issues are also discussed. The methodology was tested for two years (2009 and 2010) of the Iberian market, considering perfect and naive forecast for all variables of the problem.

A probabilistic forecast, in contrast to a point forecast, provides to the end-user more and valuable information for decision-making problems such as wind power bidding into the electricity market or setting adequate operating reserve levels in the power system. One important requirement is to have flexible representations of wind power forecast (WPF) uncertainty, in order to facilitate their inclusion in several problems. This paper reports results of using the quantile-copula conditional Kernel density estimator in the WPF problem, and how to select the adequate kernels for modeling the different variables of the problem. The method was compared with splines quantile regression for a real wind farm located in the U.S. Midwest.

This paper discusses risk management, contracting, and bidding for a wind power producer. A majority of the wind power in the United States is sold on long-term power purchase agreements, which hedge the wind power producer against future price risks. However, a significant amount is sold as merchant power and therefore is exposed to fluctuations in future electricity prices (day-ahead and real-time) and potential imbalance penalties. Wind power forecasting can serve as a tool to increase the profit and reduce the risk from participating in the wholesale electricity market. We propose a methodology to derive optimal day-ahead bids for a wind power producer under uncertainty in realized wind power and market prices. We also present an initial illustrative case study from a hypothetical wind site in the United States, where we compare the results of different day-ahead bidding strategies. The results show that the optimal day-ahead bid is highly dependent on the expected day-ahead and real-time prices, and also on the risk preferences of the wind power producer. A deviation penalty between day-ahead bid and real-time delivery tends to drive the bids closer to the expected generation for the next day.

This paper reports new results in adopting information theoretic learning concepts in the training of neural networks to perform wind power forecasts. The forecast “goodness” is discussed under two paradigms: one is only concerned in measuring the deviation between the forecasted and realized values, the other is related with the value of the forecast in the electricity market for different agents. The results and conclusions are supported by a real case example.

An aggregator agent for electric vehicles is a commercial middleman between a system operator and plug-in electrical vehicles (EV). For the system operator perspective, the aggregator is seen as a large source of generation or load, which could provide ancillary services such as spinning and regulating reserve. Generally these services will be provided in the day-ahead and intraday electricity markets. In addition, the aggregator also participates in the electricity market with supply and demand energy bids. In this paper, the integration of these concepts in an electricity market environment is discussed through proposing a framework for the information characterization (and availability) between aggregator, system operators and clients. A specific market (the Iberian Market MIBEL) is discussed. In the sequence, the different degrees of availability of the relevant information are identified and characterized, including the variables that are necessary to forecast. (9 pages)

Wind power forecasting is becoming an important tool in electricity markets, but the use of these forecasts in market operations and among market participants is still at an early stage. The authors discuss the current use of wind power forecasting in U.S. ISO/RTO markets, and offer recommendations for how to make efficient use of the information in state-of-the-art forecasts.

International audience; Electricity systems around the world are decarbonizing, driven by reductions in the cost of renewable energy and encouraged by supportive regulatory policy. Electricity market designs are increasingly being tested to ensure that the bulk power system can deliver reliable, cost-effective energy to all consumers.