Improving the on-line control of energy storage via forecast error metric customization

Abstract

The economical operation of many distributed energy assets relies on effective on-line control, which in turn often requires forecasts to be made. To produce and evaluate forecasts, the error metric by which one measures forecast accuracy must be selected. A new method is presented which customizes a forecast error metric to a given on-line control problem instance, in order to improve the controller's performance. This method is applied to the real-time operation of a battery with the objective of minimizing the peak power drawn by an aggregation of customers over a billing period. In the empirical example considered, customizing the forecast error metric to each problem instance, improved performance by 45% on average, compared to a controller provided with a forecast of the same type, but trained to minimize meansquared-error. Error metric customization is made possible by two newly proposed parametrized error metrics. The proposed method can be applied to any on-line optimization problem which requires a point forecast as an input, and which can be accurately simulated ahead of time. The method is likely to be most effective in applications where forecasting errors are quite high, as in these applications the choice of forecast error metric significantly affects the forecasts which are produced.

Use of Forecasting in Energy Storage Applications: A Review

“…However, the paper does not talk about the accuracy of the forecasts developed for the work. In [45], the authors present an interesting approach whereby, the forecast error metric is customized to improve the output of the control algorithm. The controller's objective is to minimize the monthly electricity bill.…”

A Novel Short-Term Residential Electric Load Forecasting Method Based on Adaptive Load Aggregation and Deep Learning Algorithms

“…Among the public datasets about residential electric load, three datasets are used widely in the papers. They include the data from Smart Grid Smart City (SGSC) project in Australia [39], the data from the Smart Metering project in Ireland [40], and the data from the Smart-star project in the USA [41]. The SGSC project comprises historical electric load data of 10,000 households recorded from 2012 to the 2014 under a sampling interval of 30 min, while the load data of about 4000 households from 2009 to 2010 was recorded under the same sampling interval in the Smart Metering project.…”

Assessing and Comparing Short Term Load Forecasting Performance

“…It is often infeasible to calculate the benefits of the forecast accurately. When it is possible to accurately model the decision-making process which exploits the forecasts and the resulting costs, the error metric can be selected so that the resulting costs are minimized [6].…”

“…Forecast value is also related to the error metrics. According to [6], error metrics should be easy to interpret, quick to compute and reflect the net increase in costs resulting from decisions made based on incorrect forecasts. MAPE also penalizes over-forecasts (where forecast load is greater than realized load) more than under-forecasts [7,8].…”