Surrogate models in bidirectional optimization of coupled microgrids

Baumann, Manuel; Grundel, Sara; Sauerteig, Philipp; Worthmann, Karl

doi:10.1515/auto-2019-0075

Cited by 9 publications

(12 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are used to describe the behavior of a system that, for various reasons, is not suited to be built knowledge-based. They are used in a broad range of use cases in the energy domain: starting from the calculation and optimization of energy savings (Beisheim et al 2019;Nagpal et al 2019;Vazquez-Canteli et al 2019) and the replacement of specific simulation models Dimitrov 2019) over surrogate models for (micro)grids (Baumann et al 2019;Balduin 2018;Grundel et al 2019) to the use in uncertainty and reliability assessment (Blank and Lehnhoff 2014;Slot et al 2020;Steinbrink 2016). This list is far from complete and there are also other approaches such as in Gerster (2018) who use surrogate models to build a decoder function abstracting from technical system specifications.…”

Section: Related Workmentioning

confidence: 99%

“…Surrogate models can be found in many domains, but we will focus on the energy domain. They are used in a broad range of use cases: starting from the calculation and optimization of energy savings [8,9,10] and the replacement of specific simulation models [11,12] over surrogate models for (micro)grids [13,14,15] to the use in uncertainty and reliability assessment [16,17,2]. This list is far from complete and there are also other approaches such as in Gerster [18] who use surrogate models to build a decoder function abstracting from technical system specifications.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating different machine learning techniques as surrogate for low voltage grids

2020

View full text Add to dashboard Cite

The transition of the power grid requires new technologies and methodologies, which can only be developed and tested in simulations. Especially larger simulation setups with many levels of detail can become quite slow. Therefore, the number of possible simulation evaluations decreases. One solution to overcome this issue is to use surrogate models, i. e., data-driven approximations of (sub)systems. In a recent work, we built a surrogate model for a low voltage grid using artificial neural networks, which achieved satisfying results. However, there were still open questions regarding the assumptions and simplifications made. In this paper, we present the results of our ongoing research, which answer some of these questions. We compare different machine learning algorithms as surrogate models and exchange the grid topology and size. In a set of experiments, we show that algorithms based on linear regression and artificial neural networks yield the best results independent of the grid topology. Furthermore, adding volatile energy generation and a variable phase angle does not decrease the quality of the surrogate models.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Evaluating different machine learning techniques as surrogate for low voltage grids

2020

View full text Add to dashboard Cite

show abstract

“…Additionally, the MGs are able to exchange power with their neighbours to improve the overall peakshaving performance yielding a bilevel optimisation problem. For solving this problem, a bidirectional optimisation scheme was proposed in [2]. To this end, the exchanged power is taken into account as additional demand/supply in the lower level optimisation problem, thus, possibly changing the optimal battery control.…”

Section: Introductionmentioning

confidence: 99%

“…In Section 2, we discuss the underlying model and formulate the optimisation problem. In Section 3, we adapt the bidirectional optimisation scheme proposed in [2] to the new problem formulation. Section 4 is dedicated to a numerical cased study using real-world data before we conclude in Section 5.…”

Section: Introductionmentioning

confidence: 99%

Bidirectional Optimisation for Load Shaping within Coupled Microgrids

Sauerteig¹

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We address the problem of load shaping within a network of coupled microgrids (MGs) in a bilevel optimisation framework. To this end, we consider the charging/discharging rates of residential energy storage devices within each MG on the lower level and the power exchange among neighbouring MGs on the upper level as optimisation variables. We improve a previously developed model such that the maximal amount of exchanged power does not depend on the power demand, thus, increasing the flexibility within the network, and adapt the corresponding bidirectional optimisation scheme accordingly. For efficiency, standard distributed optimisation routines are used for the optimisation on the lower level; the power exchange problem on the upper level is replaced by parallelisable small-scale quadratic programmings. We prove global convergence of the optimisation scheme and illustrate the potential of the approach in a numerical case study based on real-world data.

show abstract

“…However, due to its linear convergence [18], the proposed ADMM variant requires many communication rounds between the grid operator and the residential energy systems to achieve a desired accuracy. To this end, Baumann et al proposed to replace the expensive optimization routine by surrogate models in [25].…”

Section: Introductionmentioning

confidence: 99%

Distributed Optimization using ALADIN for MPC in Smart Grids

Jiang

Sauerteig

Houska

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

This paper presents a distributed optimization algorithm tailored to solve optimization problems arising in smart grids. In detail, we propose a variant of the Augmented Lagrangian based Alternating Direction Inexact Newton (ALADIN) method, which comes along with global convergence guarantees for the considered class of linear-quadratic optimization problems. We establish local quadratic convergence of the proposed scheme and elaborate its advantages compared to the Alternating Direction Method of Multipliers (ADMM). In particular, we show that, at the cost of more communication, ALADIN requires fewer iterations to achieve the desired accuracy. Furthermore, it is numerically demonstrated that the number of iterations is independent of the number of subsystems. The effectiveness of the proposed scheme is illustrated by running both an ALADIN and an ADMM based model predictive controller on a benchmark case study.

show abstract

Surrogate models in bidirectional optimization of coupled microgrids

Cited by 9 publications

References 26 publications

Evaluating different machine learning techniques as surrogate for low voltage grids

Evaluating different machine learning techniques as surrogate for low voltage grids

Bidirectional Optimisation for Load Shaping within Coupled Microgrids

Distributed Optimization using ALADIN for MPC in Smart Grids

Contact Info

Product

Resources

About