Alberta Electricity Market Research Articles

A Hybrid Model for Multi-Day-Ahead Electricity Price Forecasting considering Price Spikes

This paper proposes a new hybrid model to forecast electricity market prices up to four days ahead. The components of the proposed model are combined in two dimensions. First, on the “vertical” dimension, long short-term memory (LSTM) neural networks and extreme gradient boosting (XGBoost) models are stacked up to produce supplementary price forecasts. The final forecasts are then picked depending on how the predictions compare to a price spike threshold. On the “horizontal” dimension, five models are designed to extend the forecasting horizon to four days. This is an important requirement to make forecasts useful for market participants who trade energy and ancillary services multiple days ahead. The horizontally cascaded models take advantage of the availability of specific public data for each forecasting horizon. To enhance the forecasting capability of the model in dealing with price spikes, we deploy a previously unexplored input in the proposed methodology. That is, to use the recent variations in the output power of thermal units as an indicator of unplanned outages or shift in the supply stack. The proposed method is tested using data from Alberta’s electricity market, which is known for its volatility and price spikes. An economic application of the developed forecasting model is also carried out to demonstrate how several market players in the Alberta electricity market can benefit from the proposed multi-day ahead price forecasting model. The numerical results demonstrate that the proposed methodology is effective in enhancing forecasting accuracy and price spike detection.

Prediction of electricity prices for non‐regulated markets based on a power transformed mean reverting process

AbstractThe electricity price time series for non‐regulated markets presents two basic properties: (a) a mean reversion trend around a constant or deterministic function and (b) a price process with high volatility and marginal, conditional, and asymptotic distributions skewed to the right. We propose a microeconomic‐based model for the dynamics of electricity prices that provides a satisfactory explanation of the stylized features observed in non‐regulated electricity markets. The suggested model is based on a power transformation of the Ornstein–Uhlenbeck process, which accounts for the unobserved demand process. This means that the model requires only the spot price of the electricity price to be available. Parameter estimates were obtained using the maximum likelihood method. This approach was implemented for data from the Alberta electricity market in Canada, with satisfactory results in terms of residual analysis and forecasting. The success rate of predicting the price jump sign (upward and downward) was approximately . Moreover, the statistical properties for the maximum likelihood parameter estimators are shown via a Monte Carlo simulation of the electricity price time series.

Offer Price Information and the Exercise of Market Power: The Effect of the Publication of the Historical Trading Report on Competition in the Alberta Electricity Market

This paper considers the effect of the publication of offer price information on unilateral market power in Alberta’s electricity market. This market is an hourly auction characterized by repeated interaction among a small number of producers, common knowledge of costs and production capabilities, and price inelastic demand. For the period July 13, 2000 to May 18, 2017, offer prices for each hour were published by the market operator, the Alberta Electric System Operator (AESO), in the Historical Trading Report (HTR) after the end of the hour. Using counter-factual analysis from 2010 to 2015 (52,584 hours), the paper finds that the effect of offer price changes after the HTR publication was to raise the average hourly price for electricity in Alberta by $2.48/MWh or about 4.2%, which raised the cost of electricity for Alberta consumers during the six-year period by approximately $1.14 billion. Based on an earlier version of this paper, the AESO was instructed by Alberta’s utilities regulator to cease publication of the HTR.

Benefits of Strategically Sizing Wind-Integrated Energy Storage and Transmission

We examine the behavior of a strategic firm that invests-in and operates wind, energy storage, and transmission. The capacity of the energy storage and transmission are co-optimized with the firm's wind-supply and energy-storage offers into a centrally dispatched electricity market. We employ a bi-level stochastic optimization model. The upper level determines the capacities and offering strategies to maximize the firm's expected profits. Multiple lower-level problems represent market clearing under different operating conditions, which capture uncertainties. The resulting large-scale optimization model is solved using multi-cut Benders's decomposition. The model is applied to a case study that is based on Alberta's electricity market.

Offer Price Information and the Exercise of Market Power: The Effect of the Publication of the Historical Trading Report on Competition in the Alberta Electricity Market

This paper considers the effect of the publication of offer price information on unilateral market power in Alberta’s electricity market. This market is an hourly auction characterized by repeated interaction among a small number of producers, common knowledge of costs and production capabilities, and price inelastic demand. For the period July 13, 2000 to May 18, 2017, offer prices for each hour were published by the market operator, the Alberta Electric System Operator (AESO), in the Historical Trading Report (HTR) after the end of the hour. Using counter-factual analysis from 2010 to 2015 (52,584 hours), the paper finds that the effect of offer price changes after the HTR publication was to raise the average hourly price for electricity in Alberta by $2.48/MWh or about 4.2%, which raised the cost of electricity for Alberta consumers during the six-year period by approximately $1.14 billion. Based on an earlier version of this paper, the AESO was instructed by Alberta’s utilities regulator to cease publication of the HTR.

Impacts of transmission tariff on price arbitrage operation of energy storage system in Alberta electricity market

This paper investigates the application of existing tariff structures to understand how they impact the economic operation of energy storage system (ESS) for arbitrage. The scope of this research covers impacts on profitability, operating cost, energy-traded volume, and price volatility. Two facilities of different scales are considered: an ESS unit small enough to have no impact on price, and an ESS unit, large enough to have a quantifiable impact on pool price. The hourly impact of ESS operations on the pool price is estimated by modeling the price sensitivity quota curve from actual hourly market data.

Carbon pricing with an output subsidy under imperfect competition: The case of Alberta's restructured electricity market

In this paper, we examine the use of carbon pricing and an output-based subsidy in a market with imperfect competition. We consider a carbon pricing policy in Alberta's electricity market as a case study. This policy consists of two phases. In the first phase, the carbon price is increased with the output subsidy being based on a fraction of facility-level emission intensity. In the second phase, the output subsidy is altered to be uniform across assets and based on the emissions intensity of an efficient natural gas asset. Using a model of oligopoly competition, we simulate the short-run impacts of the two phases on electricity prices, emissions, and unit and firm-level profitability. We find that the mechanisms by which electricity prices and emissions change in response to carbon pricing differ depending on whether the market is perfectly competitive or oligopolistic. We demonstrate that by differentiating the effective carbon price across technologies, changing the basis of the output subsidy has substantially larger price and emissions effects than increasing the carbon price for all generators. The estimated effects of carbon pricing vary as the firms’ generation portfolios change.

Economic assessment of a price-maker energy storage facility in the Alberta electricity market

Dynamic price fluctuations in the Alberta electricity market bring potential economic opportunities for electricity energy storage technologies. However, storage operation in the market could have significant impact on electricity prices. This paper evaluates the potential operating profit available through arbitrage operation for a price-maker storage facility in Alberta. Considering a five-year period from 2010 to 2014, hourly generation and demand price quota curves (GPQCs and DPQCs) are constructed to incorporate price impact as an input to the self-scheduling problem of a price-maker storage facility. The self-scheduling model is applied to the historical hourly GPQCs and DPQCs of the Alberta electricity market to investigate the potential economic performance of a price-maker energy storage facility.

Strategic Sizing of Energy Storage Facilities in Electricity Markets

This paper proposes a model to determine the optimal size of an energy storage facility from a strategic investor's perspective. This investor seeks to maximize its profit through making strategic planning, i.e., storage sizing, and strategic operational, i.e., offering and bidding, decisions. We consider the uncertainties associated with rival generators’ offering strategies and future load levels in the proposed model. The strategic investment decisions include the sizes of charging device, discharging device, and energy reservoir. The proposed model is a stochastic bi-level optimization problem; the planning and operation decisions are made in the upper-level, and market clearing is modeled in the lower-level under different operating scenarios. To make the proposed model computationally tractable, an iterative solution technique based on Benders’ decomposition is implemented. This provides a master problem and a set of subproblems for each scenario. Each subproblem is recast as an mathematical programs with equilibrium constraints. Numerical results based on real-life market data from Alberta's electricity market are provided.

Measuring the competitiveness benefits of a transmission investment policy: The case of the Alberta electricity market

Transmission expansions can increase the extent of competition faced by wholesale electricity suppliers with the ability to exercise unilateral market power. This can cause them to submit offer curves closer to their marginal cost curves, which sets market-clearing prices closer to competitive benchmark price levels. These lower wholesale market-clearing prices are the competitiveness benefit consumers realize from the transmission expansion. This paper quantifies empirically the competitiveness benefits of a transmission expansion policy that causes strategic suppliers to expect no transmission congestion. Using hourly generation-unit level offer, output, market-clearing price and congestion data from the Alberta wholesale electricity market from January 1, 2009 to July 31, 2013, an upper and lower bound on the hourly consumer competitiveness benefits of this transmission policy is computed. Both of these competitiveness benefits measures are economically significant, which argues for including them in transmission planning processes for wholesale electricity markets to ensure that all transmission expansions with positive net benefits to electricity consumers are undertaken.

Data Mining for Electricity Price Classification and the Application to Demand-Side Management

Forecasting electricity prices plays a significant role in making optimal scheduling decisions in competitive electricity markets. Predominantly, price forecasting is performed from a “point forecasting” perspective, i.e., forecasting the exact values of future prices. However, in some applications, such as demand-side management, operation decisions are made based on certain price thresholds. It is, hence, desirable to obtain the “classes” of future prices, which can be cast as an electricity price classification problem. In this paper, we investigate the application and effectiveness of several data mining approaches for electricity market price classification. In addition, we propose a new data model for forming the initial data set for price classification. Simulation results for New York, Ontario, and Alberta electricity market prices are provided. Finally, the application of the generated numerical results to a demand-side management case study is demonstrated.

Informational Efficiency and Interchange Transactions in Alberta’s Electricity Market

This paper aims to investigate the informational efficiency of the Alberta electricity market and also the issue of whether interchange transactions (power flows between markets) are becoming increasingly significant factors in electric power markets. In doing so, we use hourly data for all hours, peak hours, and off-peak hours over the period from January 1st, 1999 to July 31st, 2005. In testing the efficiency of the Alberta power market, we use a statistical physics approach - namely the ‘detrending moving average (DMA)’ technique, introduced by Alessio et al. (2002) and further developed by Carbone et al. (2004a, 2004b), and recently applied to energy futures markets by Serletis and Rosenberg (2007). In analyzing the relationship between power imports and exports and pool prices, we assess whether regulatory changes have modified the causal relationship between import/export volumes and the pool price. According to our results, the electricity market in Alberta is highly inefficient and cross-border trade of electricity between Alberta and neighbouring jurisdictions helps predict the price dynamics in Alberta’s electricity market.

Empirical Assessment of Market Power in the Alberta Wholesale Electricity Market

This paper develops an index to measure a firm's strategic behaviour in the Alberta electricity market. A firm-behaviour parameter is extracted from price-cost margin data by distinguishing a firm-behaviour effect and a demand-elasticity effect. Although strategic firms withheld capacity during the sample period of 2003-2004, when price was above marginal cost, evidence suggests that it is more likely that firms priced competitively than that they used unilateral market power pricing given an inelastic residual demand faced by strategic firms.

Randomly Modulated Periodic Signals in Alberta's Electricity Market

This paper uses hourly electricity prices and MW hour demand for Alberta, Canada over the deregulated period after 1996 to test for randomly modulated periodicity. In doing so, we apply the signal coherence spectral analysis to the time series of hourly spot prices and megawatt-hours (MWh) demand from 1/1/1996 to 12/7/2003 using the FORTRAN 95 program developed by Hinich (2000). We detect relatively steady weekly and daily cycles in demand but very unstable cycles in prices.