Demand forecasting is an important challenge for industries seeking to optimize service quality and expenditures. Generating accurate forecasts is difficult because it depends on the quality of the data available to train predictive models, as well as on the model chosen for the task. We evaluate the approach on two datasets of varying complexity and compare the results with three machine learning algorithms. Results show our approach can outperform these approaches.
We present an electricity demand forecasting algorithm based on Gaussian processes. By introducing a task-specific, custom covariance function k_power, which incorporates all available seasonal information as well as weather data, we are able to make accurate predictions of power consumption and renewable energy production. The hyper-parameters of the Gaussian process are optimized automatically using marginal likelihood maximization. There are no parameters to be specified by the user. We evaluate the prediction performance on simulated data and get superior results compared to a simple baseline method.
Having completed the implementation and roll-out, we are now working with teams in individual markets to build trust and increase forecast adoption. This is where the expertise of the HQ Demand Planners is coming into play. Each month, the team is reviewing, analyzing and sharing forecasts with the markets. At this point, we see the limitations of what the tool can do. The forecasting tool is perfect to find models that minimize forecast error but several proposed models have been found to be unusable and unrealistic.