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

The decentralisation and unpredictability of new renewable energy sourcesrequire rethinking our energy system. Data-driven approaches, such asreinforcement learning (RL), have emerged as new control strategies foroperating these systems, but they have not yet been applied to system design.This paper aims to bridge this gap by studying the use of an RL-based methodfor joint design and control of a real-world PV and battery system. The designproblem is first formulated as a mixed-integer linear programming problem(MILP). The optimal MILP solution is then used to evaluate the performance ofan RL agent trained in a surrogate environment designed for applying anexisting data-driven algorithm. The main difference between the two models liesin their optimization approaches: while MILP finds a solution that minimizesthe total costs for a one-year operation given the deterministic historicaldata, RL is a stochastic method that searches for an optimal strategy over oneweek of data on expectation over all weeks in the historical dataset. Bothmethods were applied on a toy example using one-week data and on a case studyusing one-year data. In both cases, models were found to converge to similarcontrol solutions, but their investment decisions differed. Overall, theseoutcomes are an initial step illustrating benefits and challenges of using RLfor the joint design and control of energy systems.

Reinforcement Learning for Joint Design and Control of Battery-PV Systems