Analyzing the impact of electricity price forecasting on energy cost-aware scheduling

Abstract

Publication information AbstractEnergy cost-aware scheduling, i.e., scheduling that adapts to real-time energy price volatility, can save large energy consumers millions of dollars every year in electricity costs. Energy price forecasting coupled with energy priceaware scheduling, is a step towards this goal. In this work, we study cost-aware schedules and the effect of various price forecasting schemes on the end schedule-cost. We show that simply optimizing price forecasts based on classical regression error metrics (e.g., Mean Squared Error), does not work well for scheduling. Price forecasts that do result in significantly better schedules, optimize a combination of metrics, each having a different impact on the end-schedulecost. For example, both price estimation and price ranking are important for scheduling, but they carry different weight. We consider day-ahead energy price forecasting using the Irish Single Electricity Market as a case-study, and test our price forecasts for two real-world scheduling applications: animal feed manufacturing and home energy management systems. We show that price forecasts that co-optimize price estimation and price ranking, result in significant energy-cost savings. We believe our results are relevant for many real-life scheduling applications that are currently plagued with very large energy bills.

An Investigation into Prediction + Optimisation for the Knapsack Problem

“…Learning-to-rank Following the observation of [10] that for load-shifting problems the correlation between the rankings of the predictions and the true values is indicative for the optimisation quality, we may opt to learn to rank the items consistently. This is studied in machine learning as learning-to-rank.…”

“…The question that arises is whether such contextual data, together with historical data, can be used to improve decision making, i.e. solve the underlying optimisation problem more effectively.Such problems are encountered in load shifting [10], where the aim is to create an energy-aware day-head schedule based on predicted hourly energy prices.…”

“…Such problems are encountered in load shifting [10], where the aim is to create an energy-aware day-head schedule based on predicted hourly energy prices.…”

“…Traditional approaches to this problem consist of two phases: 1) use machine learning to estimate the problem parameters, and 2) optimise over the estimated parameters. However, Grimes et al [10] and Mathaba et al [16] have separately shown that in energy-aware scheduling, learning accurate values of the parameters by minimising the mean-square error of the predictions, a commonly used metric in machine learning, does not necessarily lead to solutions of better quality for the optimisation problem. The reason is that not all errors on estimated energy prices have an equal effect on the optimisation problem, but the machine learning algorithm does not take this into account.…”

“…This has been done with a two-phase approach in practice, e.g. in energy-aware load shifting [16,10].…”