The error induced by using representative periods in capacity expansion models: system cost, total capacity mix and regional capacity mix

Abstract

AbstractCapacity Expansion Models (CEMs) are optimization models used for long-term energy planning on national to continental scale. They are typically computationally demanding, thus in need of simplification, where one such simplification is to reduce the temporal representation. This paper investigates how using representative periods to reduce the temporal representation in CEMs distorts results compared to a benchmark model of a full chronological year. The test model is a generic CEM applied to Europe. We test the performance of reduced models at penetration levels of wind and solar of 90%. Three measures for accuracy are used: (i) system cost, (ii) total capacity mix and (iii) regional capacity. We find that: (i) the system cost is well represented (~ 5% deviation from benchmark) with as few as ten representative days, (ii) the capacity mix is in general fairly well (~ 20% deviation) represented with 50 or more representative days, and (iii) the regional capacity mix displays large deviations (> 50%) from benchmark for as many as 250 representative days. We conclude that modelers should be aware of the error margins when presenting results on these three aspects.