Probability-based, Risk-adjusted Energy Consumption Optimisation in Industrial Applications

Abstract

Production planning is not normally concerned with energy costs, but with the increasing share of volatile renewable energy, energy prices are becoming volatile, too. Production planning will ultimately have to take this into account. The problem here is in the uncertainly of price predictions and the associated risk. The present work investigates how to integrate dynamic energy price prediction uncertainty into the optimization of energy consumption in an industrial production setting. To that end, we incorporate the cost of prediction errors into the predicted energy prices up to the planning horizon. Such risk-adjusted prices are then used as the basis for energy-aware production planning. First results show that this concept can handle different error distributions and can be assumed feasible.