Alessandro Salatiello
ABSTRACT
The generation of time-series profiles of building operation requires expensive and time-consuming data consolidation and modeling efforts that rely on extensive domain knowledge and need frequent revisions due to evolving energy systems, user behavior, and environmental conditions. Generative deep learning may be used to provide an automatic, scalable, data-source-agnostic, and efficient method to synthesize these artificial time-series profiles by learning the distribution of the original data. While a range of generative neural networks have been proposed, generative adversarial networks (GANs) and variational autoencoders (VAEs) are most popular models; GANs typically require considerable customization to stabilize the training procedure, while VAEs are often reported to generate lower-quality samples compared to GANs.
In this paper, we propose a network architecture and training procedure that combines the strengths of VAEs and GANs by incorporating Regularized Adversarial Fine-Tuning (RAFT). We imbue the architecture with conditional inputs to reflect ambient/outdoor conditions and operating conditions, and demonstrate its effectiveness by using operational data collected over 585 days from SUSTIE: Mitsubishi Electric’s net-zero energy building. Comparing against classical GAN, VAE, Wasserstein-GAN, and VAE-GAN, our proposed conditional RAFT-VAE-GAN outperforms its competitors in terms of mean accuracy, training stability, and several metrics that ascertain how close the synthetic distribution is to the measured data distribution.
- Martin Arjovsky and Leon Bottou. 2017. Towards Principled Methods for Training Generative Adversarial Networks. In International Conference on Learning Representations.Google Scholar
- Martin Arjovsky, Soumith Chintala, and Léon Bottou. 2017. Wasserstein generative adversarial networks. In International conference on machine learning. PMLR, 214–223.Google Scholar
- Gaby Baasch, Guillaume Rousseau, and Ralph Evins. 2021. A Conditional Generative adversarial Network for energy use in multiple buildings using scarce data. Energy and AI 5 (2021), 100087.Google ScholarCross Ref
- Gianni Bianchini, Marco Casini, Daniele Pepe, Antonio Vicino, and Giovanni Gino Zanvettor. 2019. An integrated model predictive control approach for optimal HVAC and energy storage operation in large-scale buildings. Applied Energy 240 (2019), 327–340.Google ScholarCross Ref
- Sam Bond-Taylor, Adam Leach, Yang Long, and Chris G Willcocks. 2021. Deep generative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models. IEEE transactions on pattern analysis and machine intelligence (2021).Google Scholar
- Taylan Cemgil, Sumedh Ghaisas, Krishnamurthy Dj Dvijotham, and Pushmeet Kohli. 2020. Adversarially robust representations with smooth encoders. In International Conference on Learning Representations.Google Scholar
- Zhenghua Chen and Chaoyang Jiang. 2018. Building occupancy modeling using generative adversarial network. Energy and Buildings 174 (2018), 372–379.Google ScholarCross Ref
- Hari Prasanna Das, Ryan Tran, Japjot Singh, Xiangyu Yue, Geoffrey Tison, Alberto Sangiovanni-Vincentelli, and Costas J Spanos. 2022. Conditional synthetic data generation for robust machine learning applications with limited pandemic data. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 11792–11800.Google Scholar
- Jeff Donahue, Philipp Krähenbühl, and Trevor Darrell. 2017. Adversarial Feature Learning. In International Conference on Learning Representations.Google Scholar
- Wei Dong, Xianqing Chen, and Qiang Yang. 2022. Data-driven scenario generation of renewable energy production based on controllable generative adversarial networks with interpretability. Applied Energy 308 (2022), 118387.Google ScholarCross Ref
- Vincent Dumoulin, Ishmael Belghazi, Ben Poole, Olivier Mastropietro, Alex Lamb, Martin Arjovsky, and Aaron Courville. 2017. Adversarially Learned Inference. arxiv:1606.00704 [stat.ML]Google Scholar
- Cheng Fan, Meiling Chen, Rui Tang, and Jiayuan Wang. 2022. A novel deep generative modeling-based data augmentation strategy for improving short-term building energy predictions. In Building Simulation, Vol. 15. Tsinghua University Press, 197–211.Google Scholar
- Cheng Fan, Yongjun Sun, Yang Zhao, Mengjie Song, and Jiayuan Wang. 2019. Deep learning-based feature engineering methods for improved building energy prediction. Applied energy 240 (2019), 35–45.Google Scholar
- Marta Fochesato, Fazel Khayatian, Doris Fonseca Lima, and Zoltan Nagy. 2022. On the use of conditional TimeGAN to enhance the robustness of a reinforcement learning agent in the building domain. In Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation. 208–217.Google ScholarDigital Library
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672–2680. http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdfGoogle Scholar
- Yuxuan Gu, Qixin Chen, Kai Liu, Le Xie, and Chongqing Kang. 2019. GAN-based model for residential load generation considering typical consumption patterns. In 2019 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT). IEEE, 1–5.Google ScholarCross Ref
- Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron Courville. 2017. Improved Training of Wasserstein GANs. arxiv:1704.00028 [cs.LG]Google Scholar
- Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA) (NIPS’17). Curran Associates Inc., Red Hook, NY, USA, 6629–6640.Google ScholarDigital Library
- Yassine Himeur, Khalida Ghanem, Abdullah Alsalemi, Faycal Bensaali, and Abbes Amira. 2021. Artificial intelligence based anomaly detection of energy consumption in buildings: A review, current trends and new perspectives. Applied Energy 287 (2021), 116601.Google ScholarCross Ref
- Achin Jain, Francesco Smarra, Madhur Behl, and Rahul Mangharam. 2018. Data-driven model predictive control with regression trees—an application to building energy management. ACM Transactions on Cyber-Physical Systems 2, 1 (2018), 1–21.Google ScholarDigital Library
- Fazel Khayatian, Zoltán Nagy, and Andrew Bollinger. 2021. Using generative adversarial networks to evaluate robustness of reinforcement learning agents against uncertainties. Energy and Buildings 251 (2021), 111334.Google ScholarCross Ref
- Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings. arXiv:http://arxiv.org/abs/1312.6114v10 [stat.ML]Google Scholar
- Anders Boesen Lindbo Larsen, Søren Kaae Sønderby, Hugo Larochelle, and Ole Winther. 2016. Autoencoding beyond pixels using a learned similarity metric. In International conference on machine learning. PMLR, 1558–1566.Google Scholar
- Wonkwang Lee, Donggyun Kim, Seunghoon Hong, and Honglak Lee. 2020. High-fidelity synthesis with disentangled representation. In Proc. of the 16th European Conference on Computer Vision. Springer, 157–174.Google ScholarDigital Library
- Bingxu Li, Fanyong Cheng, Hui Cai, Xin Zhang, and Wenjian Cai. 2021. A semi-supervised approach to fault detection and diagnosis for building HVAC systems based on the modified generative adversarial network. Energy and Buildings 246 (2021), 111044.Google ScholarCross Ref
- Bingxu Li, Fanyong Cheng, Xin Zhang, Can Cui, and Wenjian Cai. 2021. A novel semi-supervised data-driven method for chiller fault diagnosis with unlabeled data. Applied Energy 285 (2021), 116459.Google ScholarCross Ref
- Zinan Lin, Alankar Jain, Chen Wang, Giulia Fanti, and Vyas Sekar. 2020. Using GANs for sharing networked time series data: Challenges, initial promise, and open questions. In Proceedings of the ACM Internet Measurement Conference. 464–483.Google ScholarDigital Library
- Chujie Lu, Sihui Li, and Zhengjun Lu. 2022. Building energy prediction using artificial neural networks: A literature survey. Energy and Buildings 262 (2022), 111718.Google ScholarCross Ref
- Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, Ian Goodfellow, and Brendan Frey. 2016. Adversarial autoencoders. In International Conference on Learning Representations.Google Scholar
- Lars Mescheder, Sebastian Nowozin, and Andreas Geiger. 2017. Adversarial variational Bayes: Unifying variational autoencoders and generative adversarial networks. In International conference on machine learning. 2391–2400.Google Scholar
- Mehdi Mirza and Simon Osindero. 2014. Conditional Generative Adversarial Nets. arXiv preprint arXiv:1411.1784. http://arxiv.org/abs/1411.1784Google Scholar
- Takeru Miyato, Toshiki Kataoka, Masanori Koyama, and Yuichi Yoshida. 2018. Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957.Google Scholar
- Zoltán Nagy, Fah Yik Yong, Mario Frei, and Arno Schlueter. 2015. Occupant centered lighting control for comfort and energy efficient building operation. Energy and Buildings 94 (2015), 100–108.Google ScholarCross Ref
- Augustus Odena, Christopher Olah, and Jonathon Shlens. 2017. Conditional image synthesis with auxiliary classifier GANs. In International conference on machine learning. PMLR, 2642–2651.Google Scholar
- Mina Razghandi, Hao Zhou, Melike Erol-Kantarci, and Damla Turgut. 2022. Variational autoencoder generative adversarial network for Synthetic Data Generation in smart home. In ICC 2022-IEEE International Conference on Communications. IEEE, 4781–4786.Google ScholarCross Ref
- Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved Techniques for Training GANs. In Proceedings of the 30th International Conference on Neural Information Processing Systems (Barcelona, Spain) (NIPS’16). Curran Associates Inc., Red Hook, NY, USA, 2234–2242.Google ScholarDigital Library
- Connor Shorten and Taghi M Khoshgoftaar. 2019. A survey on image data augmentation for deep learning. Journal of big data 6, 1 (2019), 1–48.Google ScholarCross Ref
- Kihyuk Sohn, Xinchen Yan, and Honglak Lee. 2015. Learning Structured Output Representation Using Deep Conditional Generative Models. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2 (Montreal, Canada) (NIPS’15). MIT Press, Cambridge, MA, USA, 3483–3491.Google Scholar
- Adarsh Subbaswamy, Roy Adams, and Suchi Saria. 2021. Evaluating model robustness and stability to dataset shift. In International Conference on Artificial Intelligence and Statistics. PMLR, 2611–2619.Google Scholar
- Ying Sun, Fariborz Haghighat, and Benjamin CM Fung. 2020. A review of the-state-of-the-art in data-driven approaches for building energy prediction. Energy and Buildings 221 (2020), 110022.Google ScholarCross Ref
- Chenlu Tian, Chengdong Li, Guiqing Zhang, and Yisheng Lv. 2019. Data driven parallel prediction of building energy consumption using generative adversarial nets. Energy and Buildings 186 (2019), 230–243.Google ScholarCross Ref
- Chenguang Wang, Ensieh Sharifnia, Zhi Gao, Simon H Tindemans, and Peter Palensky. 2022. Generating multivariate load states using a conditional variational autoencoder. Electric Power Systems Research 213 (2022), 108603.Google ScholarCross Ref
- Yi Wang, Qixin Chen, Tao Hong, and Chongqing Kang. 2018. Review of smart meter data analytics: Applications, methodologies, and challenges. IEEE Transactions on Smart Grid 10, 3 (2018), 3125–3148.Google ScholarCross Ref
- Zhe Wang and Tianzhen Hong. 2020. Generating realistic building electrical load profiles through the Generative Adversarial Network. Energy & Buildings 224 (2020), 110299.Google ScholarCross Ref
- Danlan Wu, Kyeon Hur, and Zhifeng Xiao. 2021. A GAN-enhanced ensemble model for energy consumption forecasting in large commercial buildings. IEEE Access 9 (2021), 158820–158830.Google ScholarCross Ref
- Yaniv Yacoby, Weiwei Pan, and Finale Doshi-Velez. 2020. Failure modes of variational autoencoders and their effects on downstream tasks. arXiv preprint arXiv:2007.07124.Google Scholar
- Ke Yan, Jing Huang, Wen Shen, and Zhiwei Ji. 2020. Unsupervised learning for fault detection and diagnosis of air handling units. Energy and Buildings 210 (2020), 109689.Google ScholarCross Ref
- Yunyang Ye, Matthew Strong, Yingli Lou, Cary A Faulkner, Wangda Zuo, and Satish Upadhyaya. 2022. Evaluating performance of different generative adversarial networks for large-scale building power demand prediction. Energy and Buildings 269 (2022), 112247.Google ScholarCross Ref
- Jinsung Yoon, Daniel Jarrett, and Mihaela van der Schaar. 2019. Time-series Generative Adversarial Networks. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc.Google Scholar
- Yufei Zhang, Arno Schlueter, and Christoph Waibel. 2023. SolarGAN: Synthetic annual solar irradiance time series on urban building facades via Deep Generative Networks. Energy and AI 12 (2023), 100223.Google ScholarCross Ref
Index Terms
- Synthesizing Building Operation Data with Generative Models: VAEs, GANs, or Something In Between?
Recommendations
Augmenting data with GANs to segment melanoma skin lesions
AbstractThis paper presents a novel strategy that employs Generative Adversarial Networks (GANs) to augment data in the skin lesion segmentation task, which is a fundamental first step in the automated melanoma detection process. The proposed framework ...
Auto-encoder-based generative models for data augmentation on regression problems
AbstractRecently, auto-encoder-based generative models have been widely used successfully for image processing. However, there are few studies on the realization of continuous input–output mappings for regression problems. Lack of a sufficient amount of ...
Deep Generative Models for Weakly-Supervised Multi-Label Classification
Computer Vision – ECCV 2018AbstractIn order to train learning models for multi-label classification (MLC), it is typically desirable to have a large amount of fully annotated multi-label data. Since such annotation process is in general costly, we focus on the learning task of ...
Comments