Abstract
Optimal capacity planning for energy devices is significantly crucial for saving economic costs and enhancing operational efficiency in an integrated energy system (IES). In this study, a reinforcement learning (RL)-based capacity planning approach for IES is proposed, where a multistage decision-making strategy is designed to reduce the action dimensionality for improving computational efficiency. Besides, to evaluate each capacity configuration scheme in RL process, a sound multi-criteria system from aspects of economy, environment, efficiency and safety is built. Within it, some new indicators are innovatively developed, including a capacity factor criterion, an installed capacity ratio and generation ratio of renewable energy devices as well as an adjust rate of energy generators. To verify the effectiveness of the proposed approach, a case study for an industrial park is carried out. The experimental results demonstrate that the proposed approach outperforms the conventional mixed integer linear programming (MILP) and multi-objective optimization (MOO) -based methods on planning the optimal capacity. Furthermore, comparative experiments with separate production systems are conducted to further study the advantages of IES, and sensitive analyses are also performed to verify the robustness of determining the optimal capacity configuration of this proposed method.
Similar content being viewed by others
Data availability
The data that support the findings of this study are available on request from the corresponding author, [Jun Zhao], upon reasonable request.
Abbreviations
- IES:
-
integrated energy system
- T:
-
transformer
- PV:
-
transformer
- WT:
-
wind turbine
- GICE:
-
gas internal combustion engine
- GB:
-
gas boiler
- EHP:
-
electric heat pump
- AC:
-
absorption chiller
- EC:
-
electric chiller
- PS:
-
power storage
- HS:
-
heat storage
- \(N_{d}\) :
-
number of typical scenarios
- \(T_{d}\) :
-
time period in one day
- \(D_{d}\) :
-
dth scenario duration
- \(c_{c}^{e}\) :
-
electricity carbon emission cost
- \(c_{c}^{ng}\) :
-
natural gas carbon emission cost
- \(c_{e}\) :
-
electricity purchased cost
- \(c_{ng}\) :
-
natural gas purchased cost
- \(c_{g,m}\) :
-
maintenance cost of generation g
- \(c_{s,m}\) :
-
maintenance cost of storage s
- \(\eta_{g}^{k}\) :
-
efficiency of generation g for kth system
- \(\varpi_{g,\max }^{k}\) :
-
maximum range coefficient of generation g
- \(\varpi_{g,\min }^{k}\) :
-
minimum range coefficient of generation g
- \(\varpi_{s,\max }^{k}\) :
-
maximum range coefficient of storage s
- \(\varpi_{s,\min }^{k}\) :
-
minimum range coefficient of storage s
- \(\overline{P}_{g}^{k}\) :
-
maximum output of generation g
- \(\underline {P}_{g}^{k}\) :
-
minimum output of generation g
- \(\overline{E}_{s}^{k}\) :
-
maximum energy of storage s
- \(\underline {E}_{s}^{k}\) :
-
minimum energy of storage s
- \(P_{dem}^{k} (t)\) :
-
k energy demand at the time t
- \(V_{g}\) :
-
capacity variable of generation g
- \(V_{s}\) :
-
capacity variable of storage s
- \(P_{T}^{e} (t)\) :
-
Transformer ouput at the time t
- \(P_{g}^{k} (t)\) :
-
output of generation g
- \(E_{s}^{k} (t)\) :
-
stored k energy of storage s
- \(P_{s,chg}^{k} (t)\) :
-
charging power of storage s
- \(P_{s,dchg}^{k} (t)\) :
-
discharging power of storage s
- \(\alpha_{s}^{k} (t)\) :
-
working mode of storage s
- \({\mathbf{s}}\) :
-
state of RL
- \({\mathbf{a}}\) :
-
action set
- \({\mathbf{A}}\) :
-
action spaces
- \({\mathbf{S}}\) :
-
state spaces
- k :
-
energy sub-system index
- g :
-
energy generation index
- s :
-
energy storage index
- d :
-
the typical scenario index
- t :
-
time step
- i :
-
step of RL
References
Rifkin, J.: The third industrial revolution: how lateral power is transforming energy, the economy, and the world. Macmillan (2011)
Zhang, C., Peng, K., Han, Y., Wang, L., Zeng, S.Q., Dong, W.J.: Key technologies and system development for regional integrated energy system. Energy Rep. 6, 374–379 (2020)
Wu, J.Z., Yan, J.Y., Jia, H.J., Hatziargyriou, N., Djilali, N., Sun, H.B.: Integrated energy systems. Appl. Energy. 167, 155–157 (2016)
Xiong, J.J., Sun, Y.H., Wang, J.X., Li, Z.P., Xu, Z., Zhai, S.W.: Multi-stage equipment optimal configuration of park-level integrated energy system considering flexible loads. Int. J. Electr. Power Energy Syst. 140, 108050 (2022)
Xiang, Y., Cai, H.H., Gu, C.H., Shen, X.D.: Cost-benefit analysis of integrated energy system planning considering demand response. Energy. 192, 116632 (2020)
Ma, T.F., Wu, J.Y., Hao, L.L., Lee, W.J., Yan, H.G., Li, D.Z.: The optimal structure planning and energy management strategies of smart multi energy systems. Energy 160, 122–141 (2018)
Gu, W., Wang, J., Lu, S., Luo, Z., Wu, C.Y.: Optimal operation for integrated energy system considering thermal inertia of district heating network and buildings. Appl. Energy. 199, 234–246 (2017)
Ding, Y.X., Xu, Q.S., Yang, B., Zhou, H., Lu, L., Shen, L., Zhang, H.Y., Jiang, L., Liao, K.: Integrated location and capacity coordination planning scheme for multi-power complementary generation system. Energy Rep. 8, 10–18 (2022)
Liu, Z.F., Chen, Y.X., Zhuo, R.Q., Jia, H.J.: Energy storage capacity optimization for autonomy microgrid considering CHP and EV scheduling. Appl. Energy. 210, 1113–1125 (2018)
Wu, Q., Ren, H.B., Gao, W.J., Ren, J.X.: Modeling and optimization of distributed energy supply network with power and hot water interchanges. Appl. Therm. Eng. 94, 635–664 (2016)
Wang, Y.L., Wang, Y.D., Huang, Y.J., Li, F., Zeng, M., Li, J.P., Wang, X.H., Zhang, F.W.: Planning and operation method of the regional integrated energy system considering economy and environment. Energy 171, 731–750 (2019)
Sun, J.Q., Ruze, N., Zhang, J.J., Shi, J., Shen, B.Y.: Capacity planning and optimization for integrated energy system in industrial park considering environmental externalities. Renew. Energy. 167, 56–65 (2021)
Khiareddine, A., Salah, C.B., Rekioua, D., Mimouni, M.F.: Sizing methodology for hybrid photovoltaic /wind/ hydrogen/battery integrated to energy management strategy for pumping system. Energy 153, 743–762 (2018)
He, S.J., Gao, H.J., Wang, L.F., Xiang, Y.M., Liu, J.Y.: Distributionally robust planning for integrated energy systems incorporating electric-thermal demand response. Energy. 213, 1187 (2020)
Yan, R.J., Wang, J.J., Lu, S.K., Ma, Z.R., Zhou, Y., Zhang, L.D., Cheng, Y.L.: Multi-objective two-stage adaptive robust planning method for an integrated energy system considering load uncertainty. Energy Build. 235, 110741 (2021)
Bhattacharjee, S., Sioshansi, R., Zareipour, H.: Benefits of strategically sizing wind-integrated energy storage and transmission. IEEE Trans. Power Syst. 36, 1141–1151 (2020)
Yousefi, H., Ghodusinejad, M.H., Noorollahi, Y.: GA/AHP-based optimal design of a hybrid CCHP system considering economy, energy and emission. Energy Build. 138, 309–317 (2017)
Lorestani, A., Ardehali, M.M.: Optimal integration of renewable energy sources for autonomous tri-generation combined cooling, heating and power system based on evolutionary particle swarm optimization algorithm. Energy 145, 839–855 (2018)
Guo, L., Liu, W.J., Cai, J.J., Hong, B.W., Wang, C.S.: A two-stage optimal planning and design method for combined cooling, heat and power microgrid system. Energy Conv. Manag. 74, 433–445 (2013)
Zhang, L., Zhou, P., Newton, S., Fang, J.X., Zhou, D.Q., Zhang, L.P.: Evaluating clean energy alternatives for Jiangsu, China: an improved multi-criteria decision making method. Energy 90(1), 953–964 (2015)
Çelikbilek, Y., Tüysüz, F.: An integrated grey based multi-criteria decision making approach for the evaluation of renewable energy sources. Energy 115(1), 1246–1258 (2016)
Karatas, M., Sulukan, E., Karacan, I.: Assessment of Turkey’s energy management performance via a hybrid multi-criteria decision-making methodology. Energy 153, 890–912 (2018)
Supciller, A.A., Toprak, F.: Selection of wind turbines with multi-criteria decision making techniques involving neutrosophic numbers: a case from Turkey. Energy 207, 118237 (2020)
Muhsen, D.H., Khatib, T., Abdulabbas, T.E.: Sizing of a standalone photovoltaic water pumping system using hybrid multi-criteria decision making methods. Sol. Energy 159, 1003–1015 (2018)
Hajibandeh, N., Shafie-khah, M., Osório, G.J., Aghaei, J., Catalão, J.P.S.: A heuristic multi-objective multi-criteria demand response planning in a system with high penetration of wind power generators. Appl. Energy. 212, 721–732 (2018)
Ebrahimi, M., Keshavarz, A.: Sizing the prime mover of a residential micro-combined cooling heating and power (CCHP) system by multi-criteria sizing method for different climates. Energy 54, 291–301 (2013)
Yang, K., Ding, Y., Zhu, N., Yang, F., Wang, Q.C.: Multi-criteria integrated evaluation of distributed energy system for community energy planning based on improved grey incidence approach: a case study in Tianjin. Appl. Energy. 229, 352–363 (2018)
Hua, H., Qin, Y.C., Hao, C.T., Cao, J.W.: Optimal energy management strategies for energy Internet via deep reinforcement learning approach. Appl. Energy. 239, 598–609 (2019)
Han, X.F., He, H.W., Wu, J.D., Peng, J.K., Li, Y.C.: Energy management based on reinforcement learning with double deep Q-learning for a hybrid electric tracked vehicle. Appl. Energy. 254, 113708 (2019)
Yousefi, N., Tsianikas, S., Coit, D.W.: Reinforcement learning for dynamic condition-based maintenance of a system with individually repairable components. Qual. Eng. 32, 388–408 (2020)
Liu, W.R., Zhuang, P., Liang, H., Peng, J., Huang, Z.W.: Distributed economic dispatch in microgrids based on cooperative reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. 29(6), 2192–2203 (2018)
Foruzan, E., Soh, L.K., Asgarpoor, S.: Reinforcement learning approach for optimal distributed energy management in a microgrid. IEEE Trans. Power Syst. 33(5), 5749–5758 (2018)
Ebell, N., Heinrich, F., Schlund, J., Pruckner, M.: Reinforcement Learning Control Algorithm for a PV-Battery-System Providing Frequency Containment Reserve Power, 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Aalborg, Denmark (2018)
Tuchnitz, F., Ebell, N., Schlund, J., Pruckner, M.: Development and evaluation of a smart charging strategy for an electric vehicle fleet based on reinforcement learning. Appl. Energy. 285, 116382 (2021)
Du, G.D., Zou, Y., Zhang, X.D., Liu, T., Wu, J.L., He, D.B.: Deep reinforcement learning based energy management for a hybrid electric vehicle. Energy 201, 117591 (2020)
Wu, J.D., Wei, Z.B., Li, W.H., Wang, Y., Li, Y.W., Sauer, D.U.: Battery thermal- and health-constrained energy management for hybrid electric bus based on soft actor-critic DRL algorithm. IEEE Trans. Ind. Inform. 17(6), 3751–3761 (2021)
Wu, J.D., Wei, Z.B., Liu, K.L., Quan, Z.Y., Li, Y.W.: Battery-involved energy management for hybrid electric bus based on expert-assistance deep deterministic policy gradient algorithm. IEEE Trans. Veh. Technol. 69(11), 12786–12796 (2020)
Tsianikas, S., Yousefi, N., Yang, J., Rodgers, M., Coit, D.W.: A Sequential Resource Investment Planning Framework using Reinforcement Learning and Simulation-Based Optimization. Appl. Energy (2021).
Perera, A.T.D., Wickramasinghe, P.U., Nik, V.M., Scartezzini, J.L.: Introducing reinforcement learning to the energy system design process. Appl. Energy. 262, 114580 (2020)
Çolak, M., Kaya, I.: Prioritization of renewable energy alternatives by using an integrated fuzzy MCDM model: a real case application for Turkey. Renew. Sust. Energ. Rev. 80, 840–853 (2017)
Yang, Y., Zhang, S.J., Xiao, Y.H.: Optimal design of distributed energy resource systems coupled with energy distribution networks. Energy 85, 433–448 (2015)
Mi, X.M., Liu, R., Cui, H.Z., Memon, S.A., Xing, F., Lo, Y.: Energy and economic analysis of building integrated with PCM in different cities of China. Appl. Energy. 175, 324–336 (2016)
Stein, E.W.: A comprehensive multi-criteria model to rank electric energy production technologies. Renew. Sust. Energ. Rev. 22, 640–654 (2013)
Yang, H.M., Xiong, T.L., Qiu, J., Qiu, D., Dong, Y.Z.: Optimal operation of DES/CCHP based regional multi-energy prosumer with demand response. Appl. Energy. 167, 353–365 (2016)
Lofberg, J.: YALMIP: a toolbox for modeling and optimization in MATLAB, IEEE International Symposium on Computer Aided Control Systems Design. IEEE (2005).
Yang, X.H., Chen, Z.X., Huang, X., Li, R.X., Xu, S.P., Yang, C.S.: Robust capacity optimization methods for integrated energy systems considering demand response and thermal comfort. Energy 221, 119727 (2021)
Acknowledgements
This work was supported by the National Key R&D Program of China under Grant 2017YFA0700300, the National Natural Sciences Foundation of China under Grant 61833003, Grant 61533005, Grant U1908218, 62003072, and the Outstanding Youth Sci-Tech Talent Program of Dalian under Grant 2018RJ01.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhou, F., Chen, L., Zhao, J. et al. Capacity planning for integrated energy system based on reinforcement learning and multi-criteria evaluation. Energy Syst (2023). https://doi.org/10.1007/s12667-023-00603-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12667-023-00603-1