A Human-on-the-Loop Optimization Autoformalism Approach for Sustainability

TL;DR

This paper presents a human-on-the-loop optimization approach using large language models to automatically translate natural language specifications into energy-related optimization problems, enabling personalized and sustainable energy solutions.

Contribution

It introduces a novel human-guided autoformalism method that enhances LLMs with optimization capabilities for personalized energy management tasks.

Findings

Successfully applied to EV charging, HVAC control, and solar PV planning.

Demonstrates improved understanding and response to user preferences.

Enables automated translation of natural language into optimization models.

Abstract

This paper outlines a natural conversational approach to solving personalized energy-related problems using large language models (LLMs). We focus on customizable optimization problems that necessitate repeated solving with slight variations in modeling and are user-specific, hence posing a challenge to devising a one-size-fits-all model. We put forward a strategy that augments an LLM with an optimization solver, enhancing its proficiency in understanding and responding to user specifications and preferences while providing nonlinear reasoning capabilities. Our approach pioneers the novel concept of human-guided optimization autoformalism, translating a natural language task specification automatically into an optimization instance. This enables LLMs to analyze, explain, and tackle a variety of instance-specific energy-related problems, pushing beyond the limits of current prompt-based techniques. Our research encompasses various commonplace tasks in the energy sector, from electric vehicle charging and Heating, Ventilation, and Air Conditioning (HVAC) control to long-term planning problems such as cost-benefit evaluations for installing rooftop solar photovoltaics (PVs) or heat pumps. This pilot study marks an essential stride towards the context-based formulation of optimization using LLMs, with the potential to democratize optimization processes. As a result, stakeholders are empowered to optimize their energy consumption, promoting sustainable energy practices customized to personal needs and preferences.