IIC Journal of Innovation 12th Edition | Page 71

Artificial and Human Intelligence with Digital Twins case is to create a set of lagged variables for the predictors and the response variable. The response variable is the energy produced. You can use RNNs for one-step-ahead forecasting where the forecast interval matches, or is less than, the desired forecast interval. This will yield the most accurate forecast. In some cases, you might need a multistep forecast to project future time periods based on the near term forecast estimates. These forecasts are typically less accurate but can be tested to determine if they have sufficient accuracy. To train this RNN, take the historical input database and create lagged variables for the predictors and response variable. The number of lags is determined by the time interval of the measurement data and the expected correlation of previous measurements on the forecast time horizon. For the solar farm example, we are producing one-hour-ahead forecasts, and the data over the last few hours is sufficient to capture the primary effects for the forecast. Note that there are a large variety of conditions possible throughout the year and previously observed weather, even though the forecast horizon is fairly short. Since we have a large amount of historical data of the various conditions, the use of an RNN is appropriate for this problem. Reinforcement learning Reinforcement learning (RL) is a subfield of machine learning and deals with sequential decision-making in a stochastic environment. In any RL problem, there is at least one agent and an environment. The agent observes the state of the environment and takes and executes a decision. The environment returns a reward and a new state in response to the action. With the new state, the agent takes and executes another action, the environment returns a reward and new state and this procedure continues iteratively. RL algorithms are designed to train an agent through this interaction with the environment, and the goal is maximizing the summation of rewards. Since training and evaluating the RNN model is dependent on the sequence, partitioning the data requires more care than typical random partitioning. In this case, we need to preserve the sequence of the data for use in the model creation steps (training, validation, test). The easiest way to do this is to partition the data based on the time variable. Use the earliest historical data for the training data set. Then use the next time partition for the validation data set. Finally, use the most recent data for the testing data set. This is sufficient if the performance of the asset has been consistent over the historical data sample. If there have been periods of degraded performance, it is best to eliminate that data from the data sets used to create the model. RL has recently received much attention due to its successes in computer games and - 66 - November 2019