Ontario Electricity Research Articles

Price forecasting in the Ontario electricity market via TriConvGRU hybrid model: Univariate vs. multivariate frameworks

Forecasting short-term electricity prices in a deregulated electricity market is challenging due to the inherent uncertainty and volatility of the prices, often exacerbated by unexpected events in generation and unpredictable price spikes coupled with unclear price patterns. As a response, this research introduces a novel hybrid Deep Learning model that employs both a Convolutional Neural Network (CNN) and a Gated Recurrent Unit (GRU) to forecast one-step, two-step, and three-step ahead electricity prices. The proposed architecture consists of three consecutive CNN-GRU models, each modelling the input at a different time granularity. By down-sampling input data using pooling layers at the beginning of two model streams, the model simultaneously captures differing frequencies of price patterns. Additionally, the forecasting models consider external variables, including previous prices, electricity load, generation, import and export, and weather data, to assess their potential to enhance model efficiency. This approach is designed to tackle the intrinsic challenges of electricity price forecasting by leveraging the strengths of CNNs for spatial pattern recognition and GRUs for capturing temporal dependencies, thus providing a more complete view of the price trends. Three studies for different weeks of 2022 were carried out in the Ontario electricity market to assess the model. The results indicate that the proposed model reduces the forecasting error by 63.3% in the first experiment, 41.8% in the second, and 28.2% in the third, on average. The proposed model outperforms several baseline models, including statistical time-series (Auto-regressive (AR), Auto-regressive Integrated Moving Average (ARIMA), and vector autoregression (VAR)), Machine Learning (Linear Regression (LR), Support Vector Regression (SVR), k-Nearest Neighbors (KNN), and Decision Tree (DT)), and Deep Learning (Multi-Layer Perceptron (MLP), Long Short-Term Memory (LSTM), GRU, and hybrid LSTM-GRU) models.

A new framework for electricity price forecasting via multi-head self-attention and CNN-based techniques in the competitive electricity market

Due to recent technical improvements, the smart grid has become a feasible platform for electricity market participants to successfully regulate their bidding process based on demand-side management (DSM) perspectives. At this level, practical design, implementation, and assessment of numerous demand response mechanisms and robust short-term price forecasting development in day-ahead transactions are all critical. The accuracy and effectiveness of the day-ahead price forecasting process are crucial concerns in a deregulated market. In this market, the reason for low accuracy is the limitation of electricity generation compared to the electricity demand variations. Hence, this study proposes a suitable technique for forecasting electricity prices using a multi-head self-attention and Convolutional Neural networks (CNN) based approach. Further, this study develops a feature selection technique using mutual information (MI) and neural networks (NN) to choose suitable input variable subsets significantly affecting electricity price predictions simultaneously. The combination of MI and NN reduces the number of input features used in the model, thereby decreasing the computational complexity of the NN. The actual data sets from the Ontario electricity market in 2020 are acquired to verify the simulation results. Finally, the simulation results proved the efficiency of the proposed method by demonstrating increased accuracy by attaining the lowest average value for MAPE and RMSE with a value of 1.75% and 0.0085, respectively, and compared to results obtained by recent computational intelligence approaches. By attaining accurate electricity price results, the significance of this study can be summed up as aiding the electricity industry's operators in administering effective energy management, efficient resource allocation, and informed decision-making.

Price Forecasting in the Ontario Electricity Market via TriConvGRU Hybrid Model: Univariate vs. Multivariate Frameworks

Price Forecasting in the Ontario Electricity Market via TriConvGRU Hybrid Model: Univariate vs. Multivariate Frameworks

NEXT-HOUR ELECTRICITY PRICE FORECASTING USING LEAST SQUARES SUPPORT VECTOR MACHINE AND GENETIC ALGORITHM

Predicting the price of electricity is crucial for the operation of power systems. Short-term electricity price forecasting deals with forecasts from an hour to a day ahead. Hourly-ahead forecasts offer expected prices to market participants before operation hours. This is especially useful for effective bidding strategies where the bidding amount can be reviewed or changed before the operation hours. Nevertheless, many existing models have relatively low prediction accuracy. Furthermore, single prediction models are typically less accurate for different scenarios. Thus, a hybrid model comprising least squares support vector machine (LSSVM) and genetic algorithm (GA) was developed in this work to predict electricity prices with higher accuracy. This model was tested on the Ontario electricity market. The inputs, which were the hourly Ontario electricity price (HOEP) and demand for the previous seven days, as well as 1-h pre-dispatch price (PDP), were optimized by GA to prevent losing potentially important inputs. At the same time, the LSSVM parameters were optimized by GA to obtain accurate forecasts. The hybrid LSSVM-GA model was shown to produce an average mean absolute percentage error (MAPE) of 8.13% and the structure of this model is less complex compared with other models developed in previous studies. This is due to the fact that only two algorithms were used (LSSVM and GA), with the load and HOEP for the week preceding the forecasting hour as the inputs. Based on the results, it is concluded that the proposed hybrid algorithm is a promising alternative to produce good electricity price forecasts.

INFERENCE ON THE DIMENSION OF THE NONSTATIONARY SUBSPACE IN FUNCTIONAL TIME SERIES

We propose a statistical procedure to determine the dimension of the nonstationary subspace of cointegrated functional time series taking values in the Hilbert space of square-integrable functions defined on a compact interval. The procedure is based on sequential application of a proposed test for the dimension of the nonstationary subspace. To avoid estimation of the long-run covariance operator, our test is based on a variance ratio-type statistic. We derive the asymptotic null distribution and prove consistency of the test. Monte Carlo simulations show good performance of our test and provide evidence that it outperforms the existing testing procedure. We apply our methodology to three empirical examples: age-specific U.S. employment rates, Australian temperature curves, and Ontario electricity demand.

Development of an integrated hydropower system with hydrogen and methanol production

In the present study, a methanol synthesis plant integrated with a hydropower station with river hydro storage option is developed and analyzed thermodynamically to study the ability of increased benefit and sustainability via the generation of multiple useful commodities. The present system is, in this regard, designed to produce methanol steadily throughout the day at baseload and generate power at an increased rate during the on-peak period. This system also cogenerates heat and fresh water through reverse osmosis and oxygen via water electrolysis. The methanol synthesis unit is simulated in the AspenPlus in a recirculation loop based on a plug flow pressurized reactor. The reaction extent for synthesis reaches a maximum at an optimum temperature for any specified pressure. The water electrolysis is conducted at 80 °C and 2 kA/m2 since the parametric study confirms that at higher current density, the duty of the water preheating heat exchanger becomes high, which increases unnecessarily the capital investment. One key focus of the paper is to devise the operating strategy of hydro-storage, which is done for an illustrative case study in which the hourly Ontario electricity price (HOEP) for the year 2020. The system is controlled in such a way that the power generation during the on-peak periods is maximized for increased revenue. A river with a 425 m3/s annual average flow rate is assumed for the case study. The gross head for hydro-storage must reach a maximum at about 30 m at 7 a.m., and 6 p.m. and the storage pool is discharged to 23 m after morning peak and to 20 m after evening peak. The overall energy efficiency of the system is found to be 61.6%. The overall exergy efficiency of the system is obtained to be 58.2% with a generation mix of grid-delivered power, methanol, heating, oxygen and fresh water.

Forecasting Electricity Load With Hybrid Scalable Model Based on Stacked Non Linear Residual Approach

Power has totally different attributes than other material commodities as electrical energy stockpiling is a costly phenomenon. Since it should be generated when demanded, it is necessary to forecast its demand accurately and efficiently. As electrical load data is represented through time series pattern having linear and non-linear characteristics, it needs a model that may handle this behavior well in advance. This paper presents a scalable and hybrid approach for forecasting the power load based on Vector Auto Regression (VAR) and hybrid deep learning techniques like Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN). CNN and LSTM models are well known for handling time series data. The VAR model separates the linear pattern in time series data, and CNN-LSTM is utilized to model non-linear patterns in data. CNN-LSTM works as CNN can extract complex features from electricity data, and LSTM can model temporal information in data. This approach can derive temporal and spatial features of electricity data. The experiment established that the proposed VAR-CNN-LSTM(VACL) hybrid approach forecasts better than more recent deep learning methods like Multilayer Perceptron (MLP), CNN, LSTM, MV-KWNN, MV-ANN, Hybrid CNN-LSTM and statistical techniques like VAR, and Auto Regressive Integrated Moving Average (ARIMAX). Performance metrics such as Mean Square Error, Root Mean Square Error, and Mean Absolute Error have been used to evaluate the performance of the discussed approaches. Finally, the efficacy of the proposed model is established through comparative studies with state-of-the-art models on Household Power Consumption Dataset (UCI machine learning repository) and Ontario Electricity Demand dataset (Canada).

Multi-step-ahead electricity load forecasting using a novel hybrid architecture with decomposition-based error correction strategy

In this study, a novel architecture combining a hybrid learning paradigm and an error correction strategy is presented for multi-step-ahead electricity load forecasting. The detail of the proposed architecture is provided as follows: (1) a novel hybrid learning paradigm based on complementary ensemble empirical mode decomposition (CEEMD) and backpropagation (BP) neural network improved by particle swarm optimization (PSO-BP) is developed for preliminary prediction of the electricity load; (2) an error prediction approach based on variational mode decomposition (VMD) and PSO-BP is established for prediction of the subsequent error; (3) calibrate the preliminary prediction values using the forecast results of the error prediction model. Specifically, in the error correction process, the original data series is separated into three subsets to generate a reasonable historical error series used for establishing the error prediction model. Two case studies based on the data of PJM and Ontario electricity markets are presented and investigated to assess the effectiveness of the proposed architecture. The evaluation results demonstrate that the proposed architecture can yield results in higher accuracy than other benchmark models considered in this study.

A stakeholder analysis of investments in wind power electricity generation in Ontario

This study uses an ex-post evaluation of the grid-connected wind projects in Ontario, Canada, to quantify the stakeholder impacts of such renewable energy projects. Our study includes a financial, economic and stakeholder analysis of a sample of three wind farms. The analysis sheds light on the distributional impacts that arise when there is a significant gap between the incentives created by the financial price paid for electricity generation and the economic value of the electricity generated. The analysis shows that the negotiated power purchase agreements (PPAs) have resulted in a negative outcome for the economy in all circumstances. It is found that the present value of the economic costs is at least three times the present value of the economic benefits, including the global benefits from the reduced CO2 emissions. This loss is borne by all the stakeholders of the electricity system, except the private owners of the wind farms. The losers are primarily the electricity consumers followed by the governments. The Ontario Electricity Rebate (OER) programme, which is financed by increased government borrowing, has the effect of transferring a large share of the costs incurred to promote investments in wind power to future generations of taxpayers in Ontario.

Market Power and Renewables: The Effects of Ownership Transfers

Adding renewable energy sources (RES) to an electricity market has an ambiguous effect on wholesale prices. The merit order effect (MoE) has a downward pressure on prices while, with market power, higher inframarginal rents will tend to increase prices. We quantify the interaction of the two effects in the Ontario electricity market. We identify the market power effect by simulating transfers of RES capacity from the fringe to larger firms: these transfers increase prices by up to 24%. We then add RES capacity and allocate it to players with varying levels of market power. Following a net expansion of RES capacity of 5% relative to total capacity, prices decrease by 30% when new capacity is assigned to the fringe, but only by 7% when assigned to the largest firm. Our findings show that the MoE is largely mitigated by market power, hence the importance of the market structure in the design of uniform incentives for RES adoption.

Particle Swarm Optimization for Least Square Support Vector Machine in MediumTerm Electricity Price Prediction

Predicting electricity price has now become an important task for planning and maintenance of power system. In medium-term forecast, electricity price can be predicted for several weeks ahead, up to a few months or a year ahead. It is useful for resources reallocation where the market players have to manage the price risk on the expected market scenario. However, the research on medium-term price forecast have also exhibited low forecast accuracy due to the limited historical data for training and testing purposes. Therefore, an optimization technique using Particle Swarm Optimization (PSO) for Least Square Support Vector Machine (LSSVM) was developed in this study to provide an accurate electricity price forecast with optimized LSSVM parameters. After thorough database mining in English language, no literature has been found on parameter optimization using LSSVM-PSO for medium-term price prediction. The model was examined on the Ontario power market which was reported as among the most volatile market worldwide. Monthly average of Hourly Ontario Electricity Price (HOEP) for the past 12 months and month index were selected as the input. The developed LSSVM-PSO showed higher forecast accuracy with lower complexity than the existing models.

Tweets and transitions: Exploring Twitter-based political discourse regarding energy and electricity in Ontario, Canada

The article explores how Twitter data can inform the study of the socio-political dimensions of sustainability transitions. Twitter is a widely used microblogging platform that allows users to share short comments, media, and links, and that offers researchers significant data collection opportunities. Twitter-based research has been growing in application in many disciplines but has not been prominently used in relation to sustainability transitions or sustainable energy research. This study aims to characterize the Twitter-based conversations regarding energy issues and politics in Ontario, Canada. The analysis in this article is based on 6946 tweets, from 2841 unique users, which were collected between September 2, 2017 and January 12, 2018. The Twitter-based discourse regarding energy issues in Ontario is described by a minority of very engaged users contributing disproportionately to the conversation, the most engaged users contributing different types of tweets to the conversation, and overall engagement that varies based on news events. Coding based on manual interpretation of the tweets by the most engaged users and those tweets that were highly retweeted identified a discourse that was highly partisan and often highlighted economic issues associated with electricity costs. Topics commonly associated with sustainable energy transitions were not prominent in the Twitter discourse. Additionally, the analysis suggests that users lacking traditional political empowerment can influence the political discourse on Twitter through high levels of retweets; however, savvy and strategic use of Twitter communication, rather than simply engagement with an issue, is important in generating consistent amplification from other users.

Behind-the-meter compressed air energy storage feasibility and applications

In this paper, the operations model of a behind-the-meter Small Scale Compressed Air Energy Storage (SS-CAES) facility is developed for an industrial customer with existing wells/caverns that can be re-purposed for air storage. The operations model seeks to minimize the electricity costs of the industrial customer, while determining the energy output and the corresponding charging and discharging decisions of the SS-CAES system. In order to examine the financial viability of a practical behind-the-meter SS-CAES facility, an economic analysis is carried out using real data of an industrial customer based in Ontario, Canada. Key parameters such as life cycle, CAES capacity and capital cost, and electricity price are considered for carrying out a sensitivity analysis, with the results showing that SS-CAES is economically viable for the current Ontario electricity tariff rate structure. The low capital cost of a SS-CAES project with a re-purposed storage cavern, and the high Global Adjustment charges levied in Ontario are shown to be a key determining factors for the economic feasibility of deployment of SS-CAES in Ontario.

Electric vehicle charging optimization to minimize marginal greenhouse gas emissions from power generation

Electrification of urban transportation systems is an important path towards achieving low carbon transportation and meeting climate commitments. Despite zero on-road greenhouse gas emissions, the upstream emissions from electricity generation cannot be ignored. In this study, a heuristic algorithm was designed to optimize regional electric vehicle charging schedules with the objective of minimizing greenhouse gas emissions from electricity generation. Our study is set in the Greater Toronto and Hamilton Area. Emissions from the charging demand are estimated by a marginal emission model calibrated with historical data for Ontario electricity generation. The results illustrate that the optimized plan can reduce greenhouse gas emissions by around 97% compared to a base case, where vehicles are powered by gasoline. Four other charging scenarios (home, out of home, after trip, and after 3am) that do not entail optimization were also investigated and compared with the optimized plan. The scenario where charging is only allowed after 3am generates the lowest emissions among all four scenarios but its emissions are 50% higher than the optimized scenario. Charging at the end of each trip was observed to generate the highest emissions. Locations serving the most charging events, and the number of non-residential charging plugs were also evaluated. The home location serves most charging events, followed by workplace. The optimized plan requires the second highest number of public charging plugs . This implies a trade-off between greenhouse gas emissions associated with vehicle charging and investments in electric vehicle charging infrastructure.

The impact of political directors on corporate strategy for government-owned utilities: Evidence from Ontario's electricity distribution sector

We contribute to research on governance of state-owned electric utilities by examining the implications of oversight by independent versus ‘political’ directors for corporate strategy. While policy think-tanks often recommend that governments appoint independent professional directors to boards of state-owned corporations, governments sometimes select politicians who bring a politically-oriented perspective to their oversight duties. To examine the potential strategic consequences, we draw on a novel survey of 384 directors of municipally-owned local electricity distribution companies in Canada, of which about a third were elected municipal councillors and the remaining were independent business professionals. The survey solicited individual director views about strategic priorities, including mergers and acquisitions, business diversification, and corporate financing options. Our statistical analysis of the survey response data finds that political directors, after controlling for prior executive experience and organizational context, were more risk-tolerant on average than independent directors, as evidenced by a greater willingness to diversify into unregulated business activities and to acquire equity stakes in other utilities; but at the same time, they prioritized enhanced dividend payments to the municipal government over re-investment in the corporation, a potential constraint on future business growth.

Wind Power Forecasting Using Wavelet Transform and General Regression Neural Network for Ontario Electricity Market

Objective: The estimation accuracy of wind power is an important subject of concern for reliable grid operations and taking part in open access. So, with an objective to improve the wind power forecasting accuracy. Methods: This article presents Wavelet Transform (WT) based General Regression Neural Network (GRNN) with statistical time series input selection technique. Results: The results of the proposed model are compared with four different models namely naïve benchmark model, feed forward neural networks, recurrent neural networks and GRNN on the basis of Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) performance metric. Conclusion: The historical data used by the presented models has been collected from the Ontario Electricity Market for the year 2011 to 2015 and tested for a long time period of more than two years (28 months) from November 2012 to February 2015 with one month estimation moving window.

Assessing the potential of fuel cell-powered and battery-powered forklifts for reducing GHG emissions using clean surplus power; a game theory approach

This work aims at developing a game theory model for assessing the potential of fuel cell-powered and battery-powered forklifts for reducing GHG emissions in the province of Ontario, Canada. Two stakeholders are considered in the developed model: government and energy consumer. The energy consumer, which is assumed to be an industrial facility, operates 150 diesel forklifts but has the option of replacing them with fuel cell-powered and battery-powered forklifts. The government can encourage this replacement by allocating a percentage of Ontario's surplus power to the energy consumer at a discounted price. The discount is assumed to be exempting the energy consumer from paying the global adjustment. As a result, the energy consumer only pays the hourly Ontario electricity price when discounted power is available. Discounted electricity will decrease the cost of operating battery-powered and fuel cell-powered forklifts for the energy consumer and will encourage it to use those technologies instead of diesel forklifts. The government has an incentive to pursue such policy as the replacement of diesel forklifts with fuel cell-powered and battery-powered forklifts will reduce GHG emissions and subsequently, the social cost of carbon in the province. The reults of our modeling show that when the government does not allocate discounted power to the energy consumer, energy consumer does not reduce emissions and keeps using its 150 diesel forklifts. However, when the government provides 0.1% of Ontario's surplus power at each hour to the energy consumer at a discounted price, the energy consumer replaces 31 of its diesel forklifts with battery-powered forklifts. When the percentage of discounted power is 0.6% of Ontario's surplus power at each hour, energy consumer replaces 91 of its diesel forklifts with battery-powered forklifts and 54 of its diesel forklifts with fuel cellpowered forklifts.A policy of discounting surplus power to encourage replacing diesel forklifts with battery-powered and fuel cell-powered forklifts is shown to benefit both stakeholders in the system. Our analysis also shows that the deployment of both fuel-cell powered and battery-powered forklifts is effective in reducing GHG emissions in Ontario when surplus clean power is available. Battery-powered forklifts are more cost-effective when lower levels of discounted power are available; however, with an increase in the level of available discounted power, fuel cell-powered forklifts become more cost-effective technologies compared to battery-powered forklifts.

Market Power and Renewables: The Effects of Ownership Transfers

The introduction of renewable energy sources (RES) in an electricity market changes the shape of the system’s supply curve. In a perfectly competitive market, this causes a downward pressure on equilibrium prices called the merit order effect (MoE). However, when introducing or transferring RES assets to firms with market power, effects on inframarginal rents are ambiguous and depend on the share of RES capacity in the firms’ portfolios. We quantify this effect empirically in the Ontario electricity market by finding equilibria under different counterfactual scenarios of RES ownership transfers and expansions. First, we identify the effect of market power in isolation by keeping the system’s capacity fixed, but we transfer RES capacity from the fringe (competitive) to firms with market power. These transfers yield increases in prices of up to 24% relative to average wholesale prices. Then, in order to measure the interaction of market power with the MoE, we introduce new RES capacity to the system by giving it to different players with varying levels of market power. We find that, following a net expansion of RES capacity of 5% relative to total capacity, wholesale prices decrease by up to 30% in the case of perfect competition. However, if capacity is assigned to the largest firm the decrease in prices is only 7%. These findings suggest that the MoE can be largely mitigated by market power, hence the key importance of the nature of the owner of new capacity when designing uniform incentives for RES adoption.

Do Incentive Rates Provide Consumer Value? An Empirical Assessment from Ontario’s Electricity Distribution Sector

:This article discusses empirical evidence regarding the theoretical claims that Incentive Rate regulation for electricity distribution creates greater consumer value than Cost of Service in terms of consumer rates. Institutional economists have identified a problem with IR in that it gives an incentive not to reduce consumer costs but to reduce adequate spending on asset maintenance. The Ontario electricity distribution sector combines both forms of regulation which creates an unusual opportunity to test the claims of increased consumer value by comparing the unit average revenues in years in which rates were set by CoS with those in which they were set by IR. The application of a t-test to data from 2011 to 2015 results in the acceptance of the null hypothesis at a 95% confidence level. The analysis concludes that there is no support for the claim that IR results in lower revenues collected from consumers.

A Hybrid Method of Least Square Support Vector Machine and Bacterial Foraging Optimization Algorithm for Medium Term Electricity Price Forecasting

Predicting electricity price has now become an important task for planning and maintenance of power system. In medium term forecast, electricity price can be predicted for several weeks ahead up to a year or few months ahead. It is useful for resources reallocation where the market players have to manage the price risk on the expected market scenario. However, researches on medium term price forecast have also exhibit low forecast accuracy. This is due to the limited historical data for training and testing purposes. Therefore, an optimization technique of Bacterial Foraging Optimization Algorithm (BFOA) for Least Square Support Vector Machine (LSSVM) was developed in this study to provide an accurate electricity price forecast with optimized LSSVM parameters and input features. So far, no literature has been found on feature and parameter selections using the LSSVM-BFOA method for medium term price prediction. The model was examined on the Ontario power market; which is reported as among the most volatile market worldwide. Monthly average of Hourly Ontario Electricity Price (HOEP) for the past 12 months and month index are selected as the input features. The developed LSSVM-BFOA shows higher forecast accuracy with lower complexity than the existing models.