IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v15y2022i3p1239-d744656.html
   My bibliography  Save this article

Accelerating Energy-Economic Simulation Models via Machine Learning-Based Emulation and Time Series Aggregation

Author

Listed:
  • Alexander J. Bogensperger

    (Forschungsstelle fuer Energiewirtschaft e.V. (FFE), Am Bluetenanger 71, 80995 Munich, Germany
    TUM School of Engineering and Design, Technical University of Munich, Arcisstraße 21, 80333 Munich, Germany)

  • Yann Fabel

    (Forschungsstelle fuer Energiewirtschaft e.V. (FFE), Am Bluetenanger 71, 80995 Munich, Germany)

  • Joachim Ferstl

    (Forschungsstelle fuer Energiewirtschaft e.V. (FFE), Am Bluetenanger 71, 80995 Munich, Germany)

Abstract

Energy-economic simulation models with high levels of detail, high time resolutions, or large populations (e.g., distribution networks, households, electric vehicles, energy communities) are often limited due to their computational complexity. This paper introduces a novel methodology, combining cluster-based time series aggregation and sampling methods, to efficiently emulate simulation models using machine learning and significantly reduce both simulation and training time. Machine learning-based emulation models require sufficient and high-quality data to generalize the dataset. Since simulations are computationally complex, their maximum number is limited. Sampling methods come into play when selecting the best parameters for a limited number of simulations ex ante. This paper introduces and compares multiple sampling methods on three energy-economic datasets and shows their advantage over a simple random sampling for small sample-sizes. The results show that a k-means cluster sampling approach (based on unsupervised learning) and adaptive sampling (based on supervised learning) achieve the best results especially for small sample sizes. While a k-means cluster sampling is simple to implement, it is challenging to increase the sample sizes if the emulation model does not achieve sufficient accuracy. The iterative adaptive sampling is more complex during implementation, but can be re-applied until a certain accuracy threshold is met. Emulation is then applied on a case study, emulating an energy-economic simulation framework for peer-to-peer pricing models in Germany. The evaluated pricing models are the “supply and demand ratio” (SDR) and “mid-market rate pricing” (MMR). A time series aggregation can reduce time series data of municipalities by 99.4% with less than 5% error for 98.2% (load) and 95.5% (generation) of all municipalities and hence decrease the simulation time needed to create sufficient training data. This paper combines time series aggregation and emulation in a novel approach and shows significant acceleration by up to 88.9% of the model’s initial runtime for the simulation of the entire population of around 12,000 municipalities. The time for re-calculating the population (e.g., for different scenarios or sensitivity analysis) can be increased by a factor of 1100 while still retaining high accuracy. The analysis of the simulation time shows that time series aggregation and emulation, considered individually, only bring minor improvements in the runtime but can, however, be combined effectively. This can significantly speed up both the simulation itself and the training of the emulation model and allows for flexible use, depending on the capabilities of the models and the practitioners. The results of the peer-to-peer pricing for approximately 12,000 German municipalities show great potential for energy communities. The mechanisms offer good incentives for the addition of necessary flexibility.

Suggested Citation

  • Alexander J. Bogensperger & Yann Fabel & Joachim Ferstl, 2022. "Accelerating Energy-Economic Simulation Models via Machine Learning-Based Emulation and Time Series Aggregation," Energies, MDPI, vol. 15(3), pages 1-42, February.
  • Handle: RePEc:gam:jeners:v:15:y:2022:i:3:p:1239-:d:744656
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/15/3/1239/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1996-1073/15/3/1239/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Maximilian Hoffmann & Leander Kotzur & Detlef Stolten & Martin Robinius, 2020. "A Review on Time Series Aggregation Methods for Energy System Models," Energies, MDPI, vol. 13(3), pages 1-61, February.
    2. Timo Kern & Patrick Dossow & Serafin von Roon, 2020. "Integrating Bidirectionally Chargeable Electric Vehicles into the Electricity Markets," Energies, MDPI, vol. 13(21), pages 1-30, November.
    3. Mohamed Ibrahim & Saad Al-Sobhi & Rajib Mukherjee & Ahmed AlNouss, 2019. "Impact of Sampling Technique on the Performance of Surrogate Models Generated with Artificial Neural Network (ANN): A Case Study for a Natural Gas Stabilization Unit," Energies, MDPI, vol. 12(10), pages 1-12, May.
    4. Jayaraman J. Thiagarajan & Bindya Venkatesh & Rushil Anirudh & Peer-Timo Bremer & Jim Gaffney & Gemma Anderson & Brian Spears, 2020. "Designing accurate emulators for scientific processes using calibration-driven deep models," Nature Communications, Nature, vol. 11(1), pages 1-10, December.
    5. Zhou, Yue & Wu, Jianzhong & Long, Chao, 2018. "Evaluation of peer-to-peer energy sharing mechanisms based on a multiagent simulation framework," Applied Energy, Elsevier, vol. 222(C), pages 993-1022.
    6. Mathias Müller & Florian Biedenbach & Janis Reinhard, 2020. "Development of an Integrated Simulation Model for Load and Mobility Profiles of Private Households," Energies, MDPI, vol. 13(15), pages 1-33, July.
    7. Lotta Kannari & Jussi Kiljander & Kalevi Piira & Jouko Piippo & Pekka Koponen, 2021. "Building Heat Demand Forecasting by Training a Common Machine Learning Model with Physics-Based Simulator," Forecasting, MDPI, vol. 3(2), pages 1-13, April.
    8. Ahmad, Tanveer & Chen, Huanxin, 2018. "Potential of three variant machine-learning models for forecasting district level medium-term and long-term energy demand in smart grid environment," Energy, Elsevier, vol. 160(C), pages 1008-1020.
    9. Etemadi, Nasrollah, 1983. "On the laws of large numbers for nonnegative random variables," Journal of Multivariate Analysis, Elsevier, vol. 13(1), pages 187-193, March.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Müller, Mathias & Blume, Yannic & Reinhard, Janis, 2022. "Impact of behind-the-meter optimised bidirectional electric vehicles on the distribution grid load," Energy, Elsevier, vol. 255(C).
    2. de Guibert, Paul & Shirizadeh, Behrang & Quirion, Philippe, 2020. "Variable time-step: A method for improving computational tractability for energy system models with long-term storage," Energy, Elsevier, vol. 213(C).
    3. Pia Szichta & Ingela Tietze, 2020. "Sharing Economy in der Elektrizitätswirtschaft: Treiber und Hemmnisse [Title sharing economy in the electricity sector: drivers and barriers]," Sustainability Nexus Forum, Springer, vol. 28(3), pages 109-125, December.
    4. Siemroth, Christoph, 2014. "Why prediction markets work : The role of information acquisition and endogenous weighting," Working Papers 14-02, University of Mannheim, Department of Economics.
    5. Zhou, Yuekuan & Lund, Peter D., 2023. "Peer-to-peer energy sharing and trading of renewable energy in smart communities ─ trading pricing models, decision-making and agent-based collaboration," Renewable Energy, Elsevier, vol. 207(C), pages 177-193.
    6. Lyu, Cheng & Jia, Youwei & Xu, Zhao, 2021. "Fully decentralized peer-to-peer energy sharing framework for smart buildings with local battery system and aggregated electric vehicles," Applied Energy, Elsevier, vol. 299(C).
    7. Lucio Ciabattoni & Stefano Cardarelli & Marialaura Di Somma & Giorgio Graditi & Gabriele Comodi, 2021. "A Novel Open-Source Simulator Of Electric Vehicles in a Demand-Side Management Scenario," Energies, MDPI, vol. 14(6), pages 1-16, March.
    8. Theresa Liegl & Simon Schramm & Philipp Kuhn & Thomas Hamacher, 2023. "Considering Socio-Technical Parameters in Energy System Models—The Current Status and Next Steps," Energies, MDPI, vol. 16(20), pages 1-19, October.
    9. Min-Hwi Kim & Dong-Won Lee & Deuk-Won Kim & Young-Sub An & Jae-Ho Yun, 2021. "Energy Performance Investigation of Bi-Directional Convergence Energy Prosumers for an Energy Sharing Community," Energies, MDPI, vol. 14(17), pages 1-17, September.
    10. Oreshkin, Boris N. & Dudek, Grzegorz & Pełka, Paweł & Turkina, Ekaterina, 2021. "N-BEATS neural network for mid-term electricity load forecasting," Applied Energy, Elsevier, vol. 293(C).
    11. Ahmad, Tanveer & Chen, Huanxin, 2019. "Deep learning for multi-scale smart energy forecasting," Energy, Elsevier, vol. 175(C), pages 98-112.
    12. Ma, Li & Wang, Lingfeng & Liu, Zhaoxi, 2021. "Multi-level trading community formation and hybrid trading network construction in local energy market," Applied Energy, Elsevier, vol. 285(C).
    13. Lefeng, Shi & Shengnan, Lv & Chunxiu, Liu & Yue, Zhou & Cipcigan, Liana & Acker, Thomas L., 2020. "A framework for electric vehicle power supply chain development," Utilities Policy, Elsevier, vol. 64(C).
    14. Byeongtae Ahn, 2022. "Implementation and Early Adoption of an Ethereum-Based Electronic Voting System for the Prevention of Fraudulent Voting," Sustainability, MDPI, vol. 14(5), pages 1-16, March.
    15. João Mello & Cristina de Lorenzo & Fco. Alberto Campos & José Villar, 2023. "Pricing and Simulating Energy Transactions in Energy Communities," Energies, MDPI, vol. 16(4), pages 1-22, February.
    16. Ibrahim, Muhammad Sohail & Dong, Wei & Yang, Qiang, 2020. "Machine learning driven smart electric power systems: Current trends and new perspectives," Applied Energy, Elsevier, vol. 272(C).
    17. Wang, Zibo & Yu, Xiaodan & Mu, Yunfei & Jia, Hongjie, 2020. "A distributed Peer-to-Peer energy transaction method for diversified prosumers in Urban Community Microgrid System," Applied Energy, Elsevier, vol. 260(C).
    18. Sara Khan & Uzma Amin & Ahmed Abu-Siada, 2024. "P2P Energy Trading of EVs Using Blockchain Technology in Centralized and Decentralized Networks: A Review," Energies, MDPI, vol. 17(9), pages 1-17, April.
    19. Tania Cerquitelli & Giovanni Malnati & Daniele Apiletti, 2019. "Exploiting Scalable Machine-Learning Distributed Frameworks to Forecast Power Consumption of Buildings," Energies, MDPI, vol. 12(15), pages 1-18, July.
    20. Wallsten, Thomas S. & Diederich, Adele, 2001. "Understanding pooled subjective probability estimates," Mathematical Social Sciences, Elsevier, vol. 41(1), pages 1-18, January.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:15:y:2022:i:3:p:1239-:d:744656. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.