Abstract
This paper proposes a Deep Reinforcement Learning approach for optimally managing multi-energy systems in smart grids. The optimal control problem of the production and storage units within the smart grid is formulated as a Partially Observable Markov Decision Process (POMDP), and is solved using an actor-critic Deep Reinforcement Learning algorithm. The framework is tested on a novel multi-energy residential microgrid model that encompasses electrical, heating and cooling storage as well as thermal production systems and renewable energy generation. One of the main challenges faced when dealing with real-time optimal control of such multi-energy systems is the need to take multiple continuous actions simultaneously. The proposed Deep Deterministic Policy Gradient (DDPG) agent has shown to handle well the continuous state and action spaces and learned to simultaneously take multiple actions on the production and storage systems that allow to jointly optimize the electrical, heating and cooling usages within the smart grid. This allows the approach to be applied for the real-time optimal energy management of larger scale multi-energy Smart Grids like eco-distrits and smart cities where multiple continuous actions need to be taken simultaneously.
Supported by the program Investissement d’Avenir, operated by l’Agence de l’Environnement et de la Maitrise de l’Energie ADEME, France.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Abbreviations
- \(P_\text {Grid}\) :
-
Grid power consumption
- \(P_\text {gen}\) :
-
Distributed power generation
- \(C_\text {Grid}\) :
-
Cost of power purchase from the grid
- \(C_\text {gen}\) :
-
Cost of distributed power generation
- \(P_\text {Load}\) :
-
Load power
- \(P_\text {pv}\) :
-
PV power generation
- \(P_\text {Bat}\) :
-
Battery power
- \(P_\text {H2}\) :
-
Hydrogen storage power
- \(P_\text {TRHP}\) :
-
Electric power consumed by TRHP
- \(Q_{\text {TRHP},t}^{H-prod}\) :
-
Heat produced by TRHP
- \(Q_{\text {TRHP},t}^{C-prod}\) :
-
Cold produced by TRHP
- \(COP_{TRHP}\) :
-
Coefficient of performance of TRHP
- \(Q_{H-load}\) :
-
Heating load
- \(Q_{C-load}\) :
-
Cooling load
- t :
-
Time step
- \(P_\text {(i)}\) :
-
Power of a storage system i
- \(P_\text {Ch}^{(i)}\) :
-
Charging power of a storage system i
- \(P_\text {Disch}^{(i)}\) :
-
Discharging power of a storage system i
- \(P_\text {min}^{(i)}\) :
-
Minimum power of storage system i
- \(P_\text {max}^{(i)}\) :
-
Maximum power of storage system i
- \(\eta _\text {Ch}^{(i)}\) :
-
Charging efficiency of a storage system i
- \(\eta _\text {Disch}^{(i)}\) :
-
Discharging efficiency of a storage system i
- \(k_\text {sd}^{(i)}\) :
-
Self-discharge rate of a storage system i
- \(E_{init}^{(i)}\) :
-
Energy initially stored in storage system i
- \(E^{(i)}\) :
-
Energy stored in storage system i
- PV :
-
Photo-voltaic
- SoC :
-
State of Charge
- MG :
-
Microgrid
- SG :
-
Smart Grid
- TRHP :
-
Thermo-Refrigerating Heat Pump
- SDHS :
-
Smart District Heating System
- MPC :
-
Model Predictive Control
- MDP :
-
Markov Decision Process
- ML :
-
Machine Learning
- DL :
-
Deep Learning
- RL :
-
Reinforcement Learning
- DRL :
-
Deep Reinforcement Learning
- DQN :
-
Deep Q-Networks
- DQL :
-
Deep Q-Learning
- DPG :
-
Deep Policy Gradient
- DDPG :
-
Deep Deterministic Policy Gradient
References
Bousnina, D., de Oliveira, W., Pflaum, P.: A stochastic optimization model for frequency control and energy management in a microgrid. In: Nicosia, G., et al. (eds.) LOD 2020. LNCS, vol. 12565, pp. 177–189. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-64583-0_17
de Bruin, T., Kober, J., Tuyls, K., Babuška, R.: Improved deep reinforcement learning for robotics through distribution-based experience retention. In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3947–3952. IEEE (2016)
Carta, S., Ferreira, A., Podda, A.S., Recupero, D.R., Sanna, A.: Multi-DQN: An ensemble of deep q-learning agents for stock market forecasting. Expert Syst. Appl. 164, 113820 (2021)
van den Ende, M., Lukszo, Z., Herder, P.M.: Smart thermal grid. In: 2015 IEEE 12th International Conference on Networking, Sensing and Control, pp. 432–437. IEEE (2015)
Fang, X., Misra, S., Xue, G., Yang, D.: Smart grid-the new and improved power grid: a survey. IEEE Commun. Surv. Tutorials 14(4), 944–980 (2011)
François-Lavet, V.: Contributions to deep reinforcement learning and its applications in smartgrids. Ph.D. thesis, Université de Liège, Liège, Belgique (2017)
François-Lavet, V., Henderson, P., Islam, R., Bellemare, M.G., Pineau, J.: An introduction to deep reinforcement learning. arXiv preprint arXiv:1811.12560 (2018)
François-Lavet, V., Taralla, D., Ernst, D., Fonteneau, R.: Deep reinforcement learning solutions for energy microgrids management. In: European Workshop on Reinforcement Learning (EWRL 2016) (2016)
Gao, G., Li, J., Wen, Y.: Energy-efficient thermal comfort control in smart buildings via deep reinforcement learning. arXiv preprint arXiv:1901.04693 (2019)
Garcia, C.E., Prett, D.M., Morari, M.: Model predictive control: theory and practice-a survey. Automatica 25(3), 335–348 (1989)
Gelleschus, R., Böttiger, M., Stange, P., Bocklisch, T.: Comparison of optimization solvers in the model predictive control of a PV-battery-heat pump system. Energ. Procedia 155, 524–535 (2018)
Ji, Y., Wang, J., Xu, J., Fang, X., Zhang, H.: Real-time energy management of a microgrid using deep reinforcement learning. Energies 12(12), 2291 (2019)
Knight, W.: Google just gave control over data center cooling to an AI (2018)
Konda, V.R., Tsitsiklis, J.N.: Actor-critic algorithms. In: Advances in Neural Information Processing Systems, pp. 1008–1014 (2000)
Kuang, Y., Wang, X., Zhao, H., Huang, Y., Chen, X., Wang, X.: Agent-based energy sharing mechanism using deep deterministic policy gradient algorithm. Energies 13(19), 5027 (2020)
Liaw, R., Krishnan, S., Garg, A., Crankshaw, D., Gonzalez, J.E., Goldberg, K.: Composing meta-policies for autonomous driving using hierarchical deep reinforcement learning. arXiv preprint arXiv:1711.01503 (2017)
Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)
Lin, S., Yu, H., Chen, H.: On-line optimization of microgrid operating cost based on deep reinforcement learning. In: IOP Conference Series: Earth and Environmental Science, vol. 701, p. 012084. IOP Publishing (2021)
Liu, H., Yu, C., Wu, H., Duan, Z., Yan, G.: A new hybrid ensemble deep reinforcement learning model for wind speed short term forecasting. Energy 202, 117794 (2020)
Lopez-Martin, M., Carro, B., Sanchez-Esguevillas, A.: Application of deep reinforcement learning to intrusion detection for supervised problems. Expert Syst. Appl. 141, 112963 (2020)
Ma, T., Wu, J., Hao, L., Lee, W.J., Yan, H., Li, D.: The optimal structure planning and energy management strategies of smart multi energy systems. Energy 160, 122–141 (2018)
Mancarella, P.: Smart multi-energy grids: concepts, benefits and challenges. In: 2012 IEEE Power and Energy Society General Meeting, pp. 1–2. IEEE (2012)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Mocanu, E., et al.: On-line building energy optimization using deep reinforcement learning. IEEE Trans. Smart Grid 10(4), 3698–3708 (2018)
Morari, M., Lee, J.H.: Model predictive control: past, present and future. Comput. Chem. Eng. 23(4–5), 667–682 (1999)
Parisio, A., Rikos, E., Glielmo, L.: A model predictive control approach to microgrid operation optimization. IEEE Trans. Control Syst. Technol. 22(5), 1813–1827 (2014)
Pflaum, P., Alamir, M., Lamoudi, M.Y.: Comparison of a primal and a dual decomposition for distributed MPC in smart districts. In: 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm), pp. 55–60. IEEE (2014)
Qin, J., Han, X., Liu, G., Wang, S., Li, W., Jiang, Z.: Wind and storage cooperative scheduling strategy based on deep reinforcement learning algorithm. In: Journal of Physics: Conference Series, vol. 1213, p. 032002. IOP Publishing (2019)
Sallab, A.E., Abdou, M., Perot, E., Yogamani, S.: Deep reinforcement learning framework for autonomous driving. Electron. Imaging 2017(19), 70–76 (2017)
Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)
Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387–395. PMLR (2014)
Sogabe, T., et al.: Smart grid optimization by deep reinforcement learning over discrete and continuous action space. In: 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC)(A Joint Conference of 45th IEEE PVSC, 28th PVSEC & 34th EU PVSEC), pp. 3794–3796. IEEE (2018)
Stănişteanu, C.: Smart thermal grids-a review. The Scientific Bulletin of Electrical Engineering Faculty 1(ahead-of-print) (2017)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)
Sutton, R.S., Barto, A.G., et al.: Introduction to Reinforcement Learning, vol. 135. MIT Press, Cambridge (1998)
Tuballa, M.L., Abundo, M.L.: A review of the development of smart grid technologies. Renew. Sustain. Energ. Rev. 59, 710–725 (2016)
Vecerik, M., et al.: Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards. arXiv preprint arXiv:1707.08817 (2017)
Wang, T., Kamath, H., Willard, S.: Control and optimization of grid-tied photovoltaic storage systems using model predictive control. IEEE Trans. Smart Grid 5(2), 1010–1017 (2014)
Yang, L., Entchev, E., Rosato, A., Sibilio, S.: Smart thermal grid with integration of distributed and centralized solar energy systems. Energy 122, 471–481 (2017)
Yu, L., et al.: Deep reinforcement learning for smart home energy management. IEEE Internet Things J. 7(4), 2751–2762 (2019)
Zhang, B., Hu, W., Cao, D., Huang, Q., Chen, Z., Blaabjerg, F.: Deep reinforcement learning-based approach for optimizing energy conversion in integrated electrical and heating system with renewable energy. Energ. Convers. Manage. 202, 112199 (2019)
Zhang, T., Luo, J., Chen, P., Liu, J.: Flow rate control in smart district heating systems using deep reinforcement learning. arXiv preprint arXiv:1912.05313 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Bousnina, D., Guerassimoff, G. (2022). Deep Reinforcement Learning for Optimal Energy Management of Multi-energy Smart Grids. In: Nicosia, G., et al. Machine Learning, Optimization, and Data Science. LOD 2021. Lecture Notes in Computer Science(), vol 13164. Springer, Cham. https://doi.org/10.1007/978-3-030-95470-3_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-95470-3_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95469-7
Online ISBN: 978-3-030-95470-3
eBook Packages: Computer ScienceComputer Science (R0)