English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Decarbonisation is driving dramatic growth in renewable power generation.This increases uncertainty in the load to be served by power plants and makestheir efficient scheduling, known as the unit commitment (UC) problem, moredifficult. UC is solved in practice by mixed-integer programming (MIP) methods;however, there is growing interest in emerging data-driven methods includingreinforcement learning (RL). In this paper, we extensively test two MIP(deterministic and stochastic) and two RL (model-free and with lookahead)scheduling methods over a large set of test days and problem sizes, for thefirst time comparing the state-of-the-art of these two approaches on a levelplaying field. We find that deterministic and stochastic MIP consistentlyproduce lower-cost UC schedules than RL, exhibiting better reliability andscalability with problem size. Average operating costs of RL are more than 2times larger than stochastic MIP for a 50-generator test case, while the costis 13 times larger in the worst instance. However, the key strength of RL isthe ability to produce solutions practically instantly, irrespective of problemsize. We leverage this advantage to produce various initial solutions for warmstarting concurrent stochastic MIP solves. By producing several near-optimalsolutions simultaneously and then evaluating them using Monte Carlo methods,the differences between the true cost function and the discrete approximationrequired to formulate the MIP are exploited. The resulting hybrid techniqueoutperforms both the RL and MIP methods individually, reducing total operatingcosts by 0.3% on average.

Reinforcement Learning and Mixed-Integer Programming for Power Plant Scheduling in Low Carbon Systems: Comparison and Hybridisation