1. The case
- Midcontinent Independent System Operator (MISO) is an independent, not-for-profit organisation that delivers safe, cost-effective electric power across 15 U.S. states and the Canadian province of Manitoba.
- The Midcontinent ISO, MISO, organises prices by Locational Marginal Prices (LMP) incorporating the cost of producing and delivering energy from individual nodes, or locations on the grid, where the transmission lines and generation interconnect. MISO also publishes the System Marginal Price – MCE – which is LMPs minus system loss and system congestion at a given node.
- MISO allows trading at trading hubs: ARKANSAS.HUB, ILLINOIS.HUB, INDIANA.HUB, LOUISIANA.HUB, MICHIGAN.HUB, MINN.HUB and TEXAS.HUB in an intraday 5-minute and Hourly market , as well as an hourly DA market.
- This case study reviews a day-ahead (DA) price forecast model for MISO System price (MCE), at an hourly resolution. The price forecast model is implemented using QR AI Forecaster.
- The DA market opens for bids and schedules seven days before and closes the day prior to the trade date at 10:30 a.m. We therefore execute and publish our DA forecast at 8:00 a.m. market time for the next day, to allow ample time for traders to plan their DA trading strategies. QR AI Forecaster serves as the key input of QR Trading Optimizer to optimize the bidding of your assets.
2. The Data
The hourly time series of MISO system price (MCE) is the main data we use to train the AI model. Feature engineering is key to increasing the accuracy and stability of price forecasts. For these we use various demand and supply side data published by MISO.
Input Data. The AI forecast model in this case study uses 6 months of hourly data for training, from February 1st to August 1st:
- Actual data: MISO system price (MCE) data published by MISO. This is the price we are going to forecast.
- Demand side data: this is our own DA System demand forecast for MISO system demand.
- Supply side data: Different DA solar and wind generation forecasts, and total outages (hydro, renewable and thermal) data all published by MISO.
Output data. The output of this AI forecast model is hourly DA price forecast for MISO system price (MCE) executed and published at 8:00 a.m. New York time for the next day.
3. Data Exploration
The first step in designing the AI model is to take a deeper look into the data and identify quantifiable behavioural patterns that may not be visible at first glance.
In order to do that, the QR data science team uses different data analysis and visualisation tools to extract information from raw data. You can see below the 6 months hourly MISO DA system price used for training.
The above price data shows clear seasonality change in the trend and level of the peaks. These were due to weather factors leading to increased prices. We need more granular analysis to define the right features for this model.
The plot above displays the hourly MISO DA system price averages across the 6 months training data ranging from February 1st to August 1st. This data can help us see the daily pattern and daily Peak and off Peak.
- The MISO DA system price peaks at 5:00 p.m., and bottoms at 3:00 a.m.The forecast model is required to capture these.
- This plot suggests to split the day in 3 periods and train the model on each data set, midnight to 3 a.m., 3 a.m. to 5 p.m., and 5 p.m. to midnight. This can be automatically accomplished by checking the Model Splitter feature of QR AI Forecaster.
- The price is clearly hour dependent. We therefore must use the built-in feature Hour-of-the-day.
We can further refine the above analysis by drilling down to days of the week. The next plot displays the average hourly price for each day of the week, computed for the 6-month training data.
- a) Saturday and Sunday MISO DA system price are clearly lower than the rest of the weekdays
- b) Price for Friday is higher but the pattern is the same as Wednesday and Thursday
- c) Pattern of Monday and Tuesday is different from the other weekdays.
- Weekday as a predictor to the AI Model to indicate the days of the week.
- The Model Splitter feature of the QR Forecaster should be activated to split data at run time and create and train 5 different Models to forecast different days of the week: Monday – Tuesday, Wednesday – Thursday, Friday, Saturday, Sunday.
4. Feature & Correlation Analysis
To select the best external time series as features or predictors, we need to analyze their correlation with the main time series MISO DA system price we are forecasting. A good or useful feature must be closely correlated to and shed light on a particular behavior of the main time series.
The MISO DA price data, including MISO DA system price, present several challenges in the 6 months period considered in this Case Study. Our data science team resolves these by configuring the right AI model so as to produce accurate price forecasts for our clients.
Factoring in demand effects
In the first plot below you can see that MISO DA system prices are higher starting from June 2023. Weather impact can explain this as seen in the second plot below. Also higher levels of demand data time series show a clear positive correlation during the same interval. This was uncovered by our data science team, using our data analysis toolbox, they executed correlation analysis across many time series data published by MISO against the main MISO DA system price.
- MISO Demand time series should be included as an external feature or predictor in the AI model, to guide the forecast in predicting such irregularities.
Factoring in renewable generation effects
As can be seen in the plot below, there are significant negative correlation between wind generation and MISO DA higher system prices starting from June 2023. As above, this was uncovered by our data science team using our data analysis toolbox.
- MISO Wind Generation time series should be included as an external feature or predictor in the AI model, to guide the forecast in predicting such irregularities.
5. The AI Forecast Model
By now the preliminary data analysis work has been done and we are ready to implement the best AI model for this case study, considering the specific features and data discussed previously. We use QR AI Forecaster cloud service. This platform is a no-coding automated AI platform, where modeling is done by dragging and dropping various model and feature engineering components in an intuitive AI dashboard, to automatically assemble and execute the final forecast model.
1) Data Preprocessing
- a) Gap Filling can be accomplished by several methods (Linear Interpolation, Weekly Pattern, Daily Pattern, etc. ), for price data we use Linear Interpolation.
- b) Outlier Detection can be accomplished by several methods. For the current price forecast case study, we use a standard deviation method, removing data at 4 SD, and replacing it with local average.
- c) Calendar is used by a processor to swap mid–week holiday data with Sundays in the future, and with a regular day in the past during forecast and training respectively, as well as labeling working days and weekends for the AI modeling.
2) Feature Engineering
We configure the following features in QR AI Forecaster dashboard:
Previous Point (which here is previous hour)
Hour, Enhanced Weekday, Week Number, Month, Is Working Day.
External Time Series Predictors
Demand, and QR designed formulas with a combination of predictors (Wind forecast , Solar forecast, …)
As was discussed above, the day ahead price forecast model for MISO, is supposed to provide forecasts one day ahead at 8:00 a.m. EST with hourly grain for the whole next day. The so-called ‘job’ for producing the forecast in the QR AI Forecaster Machine is scheduled accordingly with a complete automated procedure which executes the AI job every day at the specified 8:00 a.m. New York time.
3) AI Model
- a) Model Splitter:
- Recall that this feature allows the AI machine to split the data and define and train multiple models at run-time to forecast specific profiles. In this case considering the structure of the data, discussed in the previous chapter, we want to model specific days of the week, with a total of five models forecasting for Monday – Tuesday, Wednesday – Thursday, Friday, Saturday, Sunday.
- We are using augmentation in this job, the data has been scaled by 10%.
- b) Model Optimization:
- We configured a range of deep learning AI models for this case study. They have their own advantages. We present here 3 machine learning models, NGBoots, LightGBM and XGBoost. These can be configured to perform with nearly equal accuracy levels.
For example with XGBoost we configure the following 12 hyper-parameters:
|number of estimators
min child weight
max delta step
l1 regularization coefficient
l2 regularization coefficient
- c) Model Execution:
- Once the model is finalized, training one of the machine learning models over 6 months of hourly MISO DA system price data, and executing a DA forecast takes about 1 minute.
6. Forecast and Accuracy Analysis
1) The Forecast Display Dashboard
- a) Our forecast MISO DA system price data, computed and published at 8:00 a.m NY time.
- b) The actual MISO DA system price data is published after the DA market has closed at 10:30 a.m. for the next day.
- c) Forecast error is computed by MAPE (mean absolute percentage error), and MAE (mean absolute error). These are listed in table format and gauges.
2) Accuracy Analysis
- The MISO DA system price forecast has a MAPE of 7.4%.
- Other MISO trading hubs DA price forecasts, using the same machine learning model, have a similar accuracy.
- As you can compare with other Case Studies we have published for DA price forecasting, in MISO and PJM, using the same machine learning model, with different parameters and features, results in a MAPE of 6 to 7%. This is mainly due to the fact that:
- The dynamic of price level change from one day to the next can be very different across markets. E.g. CAISO DA prices are a lot more correlated to fuel.
- Each market publishes different sets of supply and renewable data. Some are better correlated to DA prices.
QR AI Forecaster offers a wide range of ready-for-use, advanced AI forecasting solutions, learn more about our forecasting solutions.