Optimization Strategies for Deploying Symbolic Regression Models on Embedded Hardware for Energy Management

Alexander Prielinger; Christoph Dalpiaz; Florian Eibensteiner; Kathrin Preiner; Josef Langer

Optimization Strategies for Deploying Symbolic Regression Models on Embedded Hardware for Energy Management

Alexander Prielinger^*
, Christoph Dalpiaz
, Florian Eibensteiner
, Kathrin Preiner
, Josef Langer

^*Korrespondierende/r Autor/-in für diese Arbeit

Publikation: Konferenzbeitrag › Papier › Begutachtung

Abstract

In this paper, we propose an optimization for deploying symbolic
regression-based energy management algorithms on embedded hardware.
We investigate two strategies: parameter reduction using Spearman
correlation analysis, and the use of fixed-point arithmetic to replace
floating-point operations. Both approaches are evaluated on an ARM
Cortex-A55 platform using real household power measurements. The results
show significant reductions in computational effort with minimal
loss in control performance, enabling efficient embedded deployment of
symbolic regression energy management systems.

Originalsprache	Englisch
Publikationsstatus	Angenommen/Im Druck - 2026
Veranstaltung	20th International Conference on Computer Aided Systems Theory - Museo Elder de la Ciencia y la Tecnología, Las Palmas de Gran Canaria, Spanien Dauer: 23 Feb. 2026 → 27 Feb. 2026 https://eurocast2026.fulp.es/

Konferenz

Konferenz	20th International Conference on Computer Aided Systems Theory
Kurztitel	Eurocast 2026
Land/Gebiet	Spanien
Ort	Las Palmas de Gran Canaria
Zeitraum	23.02.2026 → 27.02.2026
Internetadresse	https://eurocast2026.fulp.es/

Zitieren

@conference{0b0904eb85054096b337625d62c7f944,

title = "Optimization Strategies for Deploying Symbolic Regression Models on Embedded Hardware for Energy Management",

abstract = "In this paper, we propose an optimization for deploying symbolic regression-based energy management algorithms on embedded hardware. We investigate two strategies: parameter reduction using Spearman correlation analysis, and the use of fixed-point arithmetic to replace floating-point operations. Both approaches are evaluated on an ARM Cortex-A55 platform using real household power measurements. The results show significant reductions in computational effort with minimal loss in control performance, enabling efficient embedded deployment of symbolic regression energy management systems.",

keywords = "Symbolic Regression, Energy Management System, Optimization, Embedded Systems",

author = "Alexander Prielinger and Christoph Dalpiaz and Florian Eibensteiner and Kathrin Preiner and Josef Langer",

year = "2026",

language = "English",

note = "20th International Conference on Computer Aided Systems Theory, Eurocast 2026 ; Conference date: 23-02-2026 Through 27-02-2026",

url = "https://eurocast2026.fulp.es/",

}

TY - CONF

T1 - Optimization Strategies for Deploying Symbolic Regression Models on Embedded Hardware for Energy Management

AU - Prielinger, Alexander

AU - Dalpiaz, Christoph

AU - Eibensteiner, Florian

AU - Preiner, Kathrin

AU - Langer, Josef

PY - 2026

Y1 - 2026

N2 - In this paper, we propose an optimization for deploying symbolic regression-based energy management algorithms on embedded hardware. We investigate two strategies: parameter reduction using Spearman correlation analysis, and the use of fixed-point arithmetic to replace floating-point operations. Both approaches are evaluated on an ARM Cortex-A55 platform using real household power measurements. The results show significant reductions in computational effort with minimal loss in control performance, enabling efficient embedded deployment of symbolic regression energy management systems.

AB - In this paper, we propose an optimization for deploying symbolic regression-based energy management algorithms on embedded hardware. We investigate two strategies: parameter reduction using Spearman correlation analysis, and the use of fixed-point arithmetic to replace floating-point operations. Both approaches are evaluated on an ARM Cortex-A55 platform using real household power measurements. The results show significant reductions in computational effort with minimal loss in control performance, enabling efficient embedded deployment of symbolic regression energy management systems.

KW - Symbolic Regression

KW - Energy Management System

KW - Optimization

KW - Embedded Systems

M3 - Paper

T2 - 20th International Conference on Computer Aided Systems Theory

Y2 - 23 February 2026 through 27 February 2026

ER -

Optimization Strategies for Deploying Symbolic Regression Models on Embedded Hardware for Energy Management

Abstract

Konferenz

Fingerprint

Zitieren