On the Potential of ChatGPT to Generate Distribution Systems for Load Flow Studies Using OpenDSS

Autor(es)

Bonadia, Rodrigo S. ; Trindade, Fernanda C. L. ; Freitas, Walmir ; Venkatesh, Bala

• Tipo de documento: Artigo Científico
• Fonte: IEEE Transactions on Power Systems; v. 38, n. 6, p. 4-pg., 2023-11-01.

Resumo

In recent years, the Large Language Models have developed at an unprecedented pace with the potential to transform various fields, including power system analysis. This letter illustrates the current status and potential use of ChatGPT, (ready-to-use) pretrained chatbot, to create test distribution systems modeled as DSS files for load flow studies using OpenDSS, focusing on educational purposes. A performance comparison of GPT-3.5 and GPT-4 large language models (with the ChatGPT frontend) has been conducted. More specifically, the ability of ChatGPT to generate simple test circuits to run in OpenDSS is verified, including elements such as lines, loads, transformers, and photovoltaic generators. The ability of ChatGPT to identify and solve simple engineering problems applied to the generated circuits is also briefly discussed. The results demonstrate that GPT-4 has the potential to support educational activities by creating functional circuits and propose solutions for engineering problems if adequate guidance and examples are provided. (AU)

• Processo FAPESP: 21/11380-5 - CPTEn - Centro Paulista de Estudos da Transição Energética
• Beneficiário: Luiz Carlos Pereira da Silva
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Ciência para o Desenvolvimento
• Processo FAPESP: 23/01719-0 - Tecnologias distribuídas de rede: mudanças de paradigmas para promover a transição energética e o conceito de 3D - descentralização, descarbonização e digitalização
• Beneficiário: Walmir de Freitas Filho
• Modalidade de apoio: Bolsas no Exterior - Pesquisa
• Processo FAPESP: 22/11517-3 - Proposta de modelagem agregada de recursos energéticos distribuídos em regime permanente
• Beneficiário: Fernanda Caseño Trindade Arioli
• Modalidade de apoio: Bolsas no Exterior - Pesquisa