Análise comparativa do consumo energético de diferentes arquiteturas de software: Monolito vs. microsserviços vs. serverless
DOI:
https://doi.org/10.5281/zenodo.21829497Palavras-chave:
Consumo energético, Arquitetura de software, Microsserviços, Serverless, SustentabilidadeResumo
As decisões de arquitetura de software afetam diretamente o consumo energético dos sistemas, mas esse aspecto raramente é considerado no processo de projeto. O setor de TIC consome entre 6% e 9% da eletricidade global, e a forma como o código é estruturado influencia esse número. Este trabalho reuniu estudos experimentais recentes para comparar o consumo de energia de três arquiteturas: monolítica, microsserviços e serverless. Microsserviços apresentaram economia de aproximadamente 5% em relação a monolitos sob cargas elevadas, segundo experimentos com aplicações Java. Modelos serverless otimizados alcançaram reduções de até 30%. Cada abordagem apresenta custos próprios: microsserviços com granularidade excessiva consomem 13% mais energia devido ao tráfego de rede entre serviços, e o modelo serverless dificulta a contabilização de carbono em razão do compartilhamento de infraestrutura entre funções.
Referências
ANDERSON, T. et al. Treehouse: a case for carbon-aware datacenter software. In: INTERNATIONAL WORKSHOP ON SUSTAINABLE COMPUTER SYSTEMS (HotCarbon), 1., 2022. Proceedings... [S. l.]: ACM, 2022. Disponível em: https://arxiv.org/abs/2201.02120. Acesso em: 20 mar. 2026.
ARAÚJO, G. et al. Energy consumption in microservices architectures: a systematic literature review. IEEE Access, v. 12, p. 186710-186729, 2024. Disponível em: https://doi.org/10.1109/ACCESS.2024.3412789. Acesso em: 20 mar. 2026.
BELKHIR, L.; ELMELIGI, A. Assessing ICT global emissions footprint: trends to 2040 & recommendations. Journal of Cleaner Production, v. 177, p. 448-463, 2018. Disponível em: https://www.electronicsilentspring.com/wp-content/uploads/2015/02/ICT-Global-Emissions-Footprint-Online-version.pdf. Acesso em: 22 mar. 2026.
BERRY, V. et al. Is it worth migrating a monolith to microservices? An experience report on performance, availability and energy usage. In: IEEE INTERNATIONAL CONFERENCE ON WEB SERVICES (ICWS), 2024, Shenzhen. Proceedings... Shenzhen: IEEE, 2024. p. 944-954. Disponível em: https://inria.hal.science/hal-04781943v1. Acesso em: 22 mar. 2026.
BLINOWSKI, G.; OJDOWSKA, A.; PRZYBYŁEK, A. Monolithic vs. microservice architecture: a performance and scalability evaluation. IEEE Access, v. 10, p. 20357-20374, 2022. Disponível em: https://doi.org/10.1109/ACCESS.2022.3152803. Acesso em: 18 mar. 2026.
CAPUANO, R.; O'DEA, E.; MUCCINI, H. A comparative analysis of monolith vs microservices energy consumption. In: EUROPEAN CONFERENCE ON SOFTWARE ARCHITECTURE (ECSA), 2025. Proceedings... [S. l.]: Springer, 2026. (LNCS, vol. 15929). Disponível em: https://link.springer.com/chapter/10.1007/978-3-032-02138-0_17. Acesso em: 20 mar. 2026.
CASTRO, P. et al. The rise of serverless computing. Communications of the ACM, v. 62, n. 12, p. 44-54, 2019. Disponível em: https://cacm.acm.org/research/the-rise-of-serverless-computing/. Acesso em: 10 mar. 2026.
CERNY, T. et al. On maintainability and microservice dependencies. In: INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND SERVICES SCIENCE (CLOSER), 14., 2024, Angers. Proceedings... Angers: SCITEPRESS, 2024. p. 277-286. Disponível em: https://www.researchgate.net/publication/380149312. Acesso em: 11 mar. 2026.
CHADHA, M. et al. GreenCourier: carbon-aware scheduling for serverless functions. In: INTERNATIONAL WORKSHOP ON SERVERLESS COMPUTING (WoSC), 9., 2023, Bologna. Proceedings... Bologna: ACM, 2023. p. 18-23. Disponível em: https://arxiv.org/abs/2310.20375. Acesso em: 12 mar. 2026.
DA SILVA, A. A. et al. FOA-Energy: a multi-objective energy-aware scheduling policy for serverless-based edge-cloud continuum. In: ACM SYMPOSIUM ON APPLIED COMPUTING (SAC), 40., 2025, Catania. Proceedings... Catania: ACM, 2025. Disponível em: https://hal.science/hal-05156857/document. Acesso em: 13 mar. 2026.
FONTANA DE NARDIN, I. et al. On revisiting energy and performance in microservices applications: a cloud elasticity-driven approach. Parallel Computing, v. 108, 2021. Disponível em: https://www.researchgate.net/publication/355389070. Acesso em: 10 mar. 2026.
GREEN SOFTWARE FOUNDATION. Software Carbon Intensity (SCI) Specification v1.0. 2021. Disponível em: https://sci.greensoftware.foundation/. Acesso em: 12 mar. 2026.
GREENWHISK. Emission-aware computing for serverless platform. arXiv preprint, 2024. Disponível em: https://arxiv.org/abs/2409.03029. Acesso em: 10 mar. 2026.
JIANG, Y. et al. EcoLife: carbon-aware serverless function scheduling for sustainable computing. In: INTERNATIONAL CONFERENCE FOR HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS (SC), 2024, Atlanta. Proceedings... Atlanta: IEEE/ACM, 2024. Disponível em: https://arxiv.org/abs/2409.02085. Acesso em: 20 mar. 2026.
KITCHENHAM, B.; CHARTERS, S. Guidelines for performing systematic literature reviews in software engineering. Keele: Keele University, 2007. Disponível em: https://www.researchgate.net/publication/302924724. Acesso em: 23 mar. 2026.
MDPI SUSTAINABILITY. Reducing environmental impact with sustainable serverless computing. Sustainability, v. 17, n. 7, art. 2999, 2025. Disponível em: https://www.mdpi.com/2071-1050/17/7/2999. Acesso em: 22 mar. 2026.
ROY, R. B. et al. The hidden carbon footprint of serverless computing. In: ACM SYMPOSIUM ON CLOUD COMPUTING (SoCC), 2024, Redmond. Proceedings... Redmond: ACM, 2024. p. 570-579. Disponível em: https://www.researchgate.net/publication/386411655. Acesso em: 23 mar. 2026.
SEO, C. et al. A framework for estimating the impact of a distributed software system's architectural style on its energy consumption. In: WORKING IEEE/IFIP CONFERENCE ON SOFTWARE ARCHITECTURE (WICSA), 2008. Proceedings... [S. l.]: IEEE, 2008. p. 277-280. Disponível em: https://www.researchgate.net/publication/221179490. Acesso em: 22 mar. 2026.
SHARMA, P. Challenges and opportunities in sustainable serverless computing. ACM SIGENERGY Energy Informatics Review, v. 3, n. 3, p. 53-58, 2023. Disponível em: https://www.researchgate.net/publication/375399610. Acesso em: 21 mar. 2026.
SHARMA, P.; FUERST, A. Accountable carbon footprints and energy profiling for serverless functions. In: ACM SYMPOSIUM ON CLOUD COMPUTING (SoCC), 2024, Redmond. Proceedings... Redmond: ACM, 2024. p. 522-541. Disponível em: https://www.researchgate.net/publication/386411506. Acesso em: 20 mar. 2026.
STOJKOVIC, J. et al. EcoFaaS: rethinking the design of serverless environments for energy efficiency. In: INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA), 51., 2024, Buenos Aires. Proceedings... Buenos Aires: IEEE/ACM, 2024. p. 471-486. Disponível em: https://iacoma.cs.uiuc.edu/iacoma-papers/PRES/present_isca24_2.pdf. Acesso em: 18 mar. 2026.
VERDECCHIA, R. et al. Green IT and Green Software. IEEE Software, v. 38, n. 6, p. 7-15, 2021. Disponível em: https://www.researchgate.net/publication/355389574. Acesso em: 20 mar. 2026.
XIAO, X.; GAO, C.; BOGNER, J. On the effectiveness of microservices tactics and patterns to reduce energy consumption: an experimental study on trade-offs. In: IEEE INTERNATIONAL CONFERENCE ON SOFTWARE ARCHITECTURE (ICSA), 2025, Odense. Proceedings... Odense: IEEE, 2025. p. 164-175. Disponível em: https://arxiv.org/abs/2501.14402. Acesso em: 14 mar. 2026.
ZHAO, Y.; DE MATTEIS, T.; BOGNER, J. How does microservice granularity impact energy consumption and performance? arXiv preprint, 2025. Disponível em: https://arxiv.org/abs/2502.00482. Acesso em: 15 mar. 2026.
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Copyright (c) 2026 Eduardo Netto Freyer, Sandir Rodrigues Campos
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
