Optimization Method for Regulating Resource Capacity Allocation in Power Grids with High Penetration of Renewable Energy Based on Seq2Seq Transformer
Abstract
1. Introduction
2. Problem Modeling
2.1. System Power Difference Model
2.2. Proportional Allocation of Flexible Resources
2.3. Multi-Objective Loss Function Design
3. Seq2Seq Transformer Model Structure Design
3.1. Seq2Seq Transformer Architecture
3.2. Positional Encoding
3.3. Encoder Structure
- Multi-Head Self-Attention;
- Residual Connection;
- Position-wise Feed-Forward Network;
- Layer Normalization (LayerNorm).
3.4. Decoder Structure
- (1)
- Masked Multi-Head Attention: prevents information leakage from future time steps;
- (2)
- Encoder–Decoder Cross Attention: captures dependencies between the Encoder outputs and the current decoding state;
- (3)
- Feed-Forward Network with Residual Connection: the outputs are mapped to grid power flow calculations to check whether actual constraints are satisfied, with the residuals representing power flow deviations.
3.5. Output Layer and Constraint Handling
4. Input Data Generation and Attention Mechanism
4.1. Input Data Generation
4.2. Multi-Feature Attention Mechanism for Input Data
- (1)
- Definition of Temporal Physical Features
- (2)
- Feature Embedding and Backbone Representation
- (3)
- Feature-Aware Attention Scoring
5. Pareto-Based Multi-Solution Output Series
5.1. Multi-Objective Analysis of Outputs
- (1)
- Economic Efficiency
- (2)
- Dynamic Coordination
- (3)
- Supply Reliability
5.2. Multi-Solution Output Structure Design
- (1)
- Cost Min: The regulating resources achieve the lowest cost, which can meet steady-state operation requirements. However, ramping capability is insufficient under sudden power variations, potentially reducing system reliability.
- (2)
- Ramp Min: Ensures source–load balance even under significant renewable and load fluctuations, but requires a high proportion of fast-response resources (e.g., battery storage), leading to higher costs.
- (3)
- Risk Min: Guarantees the highest system stability and user supply reliability, minimizing operational risk. However, it may involve renewable curtailment and under-utilization of regulating resources, thereby increasing costs.
- (4)
- Cost–Risk Trade-off: Balances regulating resource cost and reliability requirements, with lower ramping speed demands. However, its ability to handle strong renewable fluctuations is limited.
- (5)
- Cost–Coordination Trade-off: Balances regulating resource cost and ramping response requirements. However, curtailment of highly volatile renewable generation may occur, reducing economic efficiency.
- (6)
- Cost–Coordination–Risk Trade-off: A comprehensive optimization considering all three objectives simultaneously. This represents the most ideal outcome but is difficult to achieve in practice.
6. Case Study
6.1. Case Introduction
6.2. Model Parameter Settings
6.3. Results
7. Conclusions
- (1)
- A Seq2Seq Transformer large model structure is constructed, which incorporates the stochastic nature of new energy sources, the response characteristics of various adjustable resources, and grid constraints. A multi-objective function is established that includes loss minimization, ramping response matching, and cost minimization.
- (2)
- A multi-feature-aware attention mechanism for stochastic new energy is proposed, enabling better alignment of ramping speeds of different resources and various grid constraints, such as power flow balance, during model training and output generation.
- (3)
- A multi-solution output scheme based on Pareto-optimal filtering is proposed, generating multiple combinations of regulation resource proportions that are diverse and balanced. These combinations correspond to different planning and operation objectives and can adapt to the stochastic nature of operations in new-type power systems.
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Zhao, B.; Ren, J.; Chen, J.; Lin, D.; Qin, R. Tri-level robust planning-operation co-optimization of distributed energy storage in distribution networks with high PV penetration. Appl. Energy 2020, 279, 115768. [Google Scholar] [CrossRef]
- Zhang, Y.; Ma, C.; Yang, Y.; Pang, X.; Lian, J.; Wang, X. Capacity configuration and economic evaluation of a power system integrating hydropower, solar, and wind. Energy 2022, 259, 125012. [Google Scholar] [CrossRef]
- Dunn, B.; Kamath, H.; Tarascon, J.-M. Electrical energy storage for the grid: A battery of choices. Science 2011, 334, 928–935. [Google Scholar] [CrossRef]
- Wang, Z.; Fang, G.; Wen, X.; Tan, Q.; Zhang, P.; Liu, Z. Coordinated operation of conventional hydropower plants as hybrid pumped storage hydropower with wind and photovoltaic plants. Energy Convers. Manag. 2023, 277, 116654. [Google Scholar] [CrossRef]
- Wu, S.; Li, H.; Liu, Y.; Lu, Y.; Wang, Z.; Liu, Y. A two-stage rolling optimization strategy for park-level integrated energy system considering multi-energy flexibility. Int. J. Electr. Power Energy Syst. 2022, 145, 108600. [Google Scholar] [CrossRef]
- Arani, A.K.; Karami, H.; Gharehpetian, G.; Hejazi, M. Review of Flywheel Energy Storage Systems structures and applications in power systems and microgrids. Renew. Sustain. Energy Rev. 2017, 69, 9–18. [Google Scholar] [CrossRef]
- Wang, Y.; Zhao, M.; Chang, J.; Wang, X.; Tian, Y. Study on the combined operation of a hydro-thermal-wind hybrid power system based on hydro-wind power compensating principles. Energy Convers. Manag. 2019, 194, 94–111. [Google Scholar] [CrossRef]
- Sun, K.; Li, K.-J.; Pan, J.; Liu, Y.; Liu, Y. An optimal combined operation scheme for pumped storage and hybrid wind-photovoltaic complementary power generation system. Appl. Energy 2019, 242, 1155–1163. [Google Scholar] [CrossRef]
- Liu, Z.; Liu, B.; Ding, X.; Wang, F. Research on optimization of energy storage regulation model considering wind–solar and multi-energy complementary intermittent energy interconnection. Energy Rep. 2022, 8, 490–501. [Google Scholar] [CrossRef]
- Li, J.; Guo, B.; Niu, M.; Xiu, X.Q.; Tian, L.T. Optimal configuration strategy of energy storage capacity in wind/PV/storage hybrid system. Trans. China Electrotech. Soc. 2018, 33, 1189–1196. [Google Scholar]
- Ren, Y.; Yao, X.; Liu, D.; Qiao, R.; Zhang, L.; Zhang, K.; Jin, K.; Li, H.; Ran, Y.; Li, F. Optimal design of hydro-wind-PV multi-energy complementary systems considering smooth power output. Sustain. Energy Technol. Assessments 2022, 50, 101832. [Google Scholar] [CrossRef]
- Xu, X.; Hu, W.; Cao, D.; Huang, Q.; Chen, C.; Chen, Z. Optimized sizing of a standalone PV-wind-hydropower station with pumped-storage installation hybrid energy system. Renew. Energy 2020, 147, 1418–1431. [Google Scholar] [CrossRef]
- Huang, K.; Liu, P.; Ming, B.; Kim, J.-S.; Gong, Y. Economic operation of a wind-solar-hydro complementary system considering risks of output shortage, power curtailment and spilled water. Appl. Energy 2021, 290, 116805. [Google Scholar] [CrossRef]
- Galindo Padilha, G.A.; Ko, J.; Jung, J.J.; de Mattos Neto, P.S.G. Transformer-based hybrid forecasting model for multivariate renewable energy. Appl. Sci. 2022, 12, 10985. [Google Scholar] [CrossRef]
- Li, P.; Zhou, K.; Lu, X.; Yang, S. A hybrid deep learning model for short-term PV power forecasting. Appl. Energy 2020, 259, 114216. [Google Scholar] [CrossRef]
- Al-Ali, E.M.; Hajji, Y.; Said, Y.; Hleili, M.; Alanzi, A.M.; Laatar, A.H.; Atri, M. Solar energy production forecasting based on a hybrid CNN-LSTM-transformer model. Mathematics 2023, 11, 676. [Google Scholar] [CrossRef]
- Rocha, O.D.A.; Morozovska, K.; Laneryd, T.; Ivarsson, O.; Ahlrot, C.; Hilber, P. Dynamic rating assists cost-effective expansion of wind farms by utilizing the hidden capacity of transformers. Int. J. Electr. Power Energy Syst. 2020, 123, 106188. [Google Scholar] [CrossRef]
- Angelis, G.F.; Timplalexis, C.; Salamanis, A.I.; Krinidis, S.; Ioannidis, D.; Kehagias, D.; Tzovaras, D. Energformer: A new transformer model for energy disaggregation. IEEE Trans. Consum. Electron. 2023, 69, 308–320. [Google Scholar] [CrossRef]
- Şencan, A.; Kızılkan, Ö.; Bezir, N.Ç.; Kalogirou, S.A. Different methods for modeling absorption heat transformer powered by solar pond. Energy Convers. Manag. 2007, 48, 724–735. [Google Scholar] [CrossRef]
- Dang, J.; Wang, Y.; Jia, R.; Wang, X.; Cao, G. Dual-layer loss reduction strategy for virtual distribution transformer integrating energy storage converter. J. Energy Storage 2024, 90, 111889. [Google Scholar] [CrossRef]
- Laayati, O.; El Hadraoui, H.; El Magharaoui, A.; El-Bazi, N.; Bouzi, M.; Chebak, A.; Guerrero, J.M. An AI-layered with multi-agent systems architecture for prognostics health management of smart transformers: A novel approach for smart grid-ready energy management systems. Energies 2022, 15, 7217. [Google Scholar] [CrossRef]
- Fang, H.; Liao, J.; Huang, S.; Zhang, M. Research on Status Assessment and Operation and Maintenance of Electric Vehicle DC Charging Stations Based on XGboost. Smart Cities 2024, 7, 3055–3070. [Google Scholar] [CrossRef]
- Fang, H.; Shang, L.; Dong, X.; Tian, Y. High Proportion of Distributed PV Reliability Planning Method Based on Big Data. Energies 2023, 16, 7692. [Google Scholar] [CrossRef]
- Fang, H.; Li, D.; Peng, H.; Hou, H. Distributed Solar Energy Planning Method based on Internet Plus. Proc. CSEE 2017, 37, 1316–1324. [Google Scholar]
No | Type | Capacity (kW) |
---|---|---|
A | PV | 500 |
B | PV | 500 |
C | Wind | 600 |
D | Wind | 600 |
E | Wind | 500 |
F | Load | 1500 |
Parameter | Description | Value |
---|---|---|
d_model | Hidden layer dimension | 128 |
nhead | Number of attention head | 4 |
num_encoder_layers | Number of Encoder layers | 3 |
num_decoder_layers | Number of Decoder layers | 3 |
fn_dim | Feed-forward network dimension | 2 × d_model |
dropout | Dropout rate | 0.1 |
max_seq_len | Sequence length (time steps) | 96 |
output_dim | Output dimension | K × 3 |
No | Scheme | Jcost (k$) | Jramp | Jrel (%) |
---|---|---|---|---|
1 | (0.22,0.51,0.27) | 112 | 1.82 | 10.22 |
2 | (0.28,0.57,0.15) | 99 | 2.55 | −5.31 |
3 | (0.23,0.54,0.23) | 109 | 1.65 | 7.63 |
4 | (0.24,0.54,0.22) | 106 | 1.72 | 5.37 |
5 | (0.22,0.51,0.20) | 107 | 1.97 | 3.42 |
6 | (0.23,0.58,0.19) | 103 | 1.74 | 1.93 |
No | Scheme | Jcost (k$) | Jramp | Jrel (%) |
---|---|---|---|---|
1 | (0.20,0.49,0.31) | 121 | 2.80 | 9.32 |
2 | (0.19,0.53,0.28) | 115 | 2.45 | 5.71 |
3 | (0.21,0.57,0.22) | 109 | 2.15 | 5.64 |
4 | (0.24,0.54,0.22) | 106 | 1.93 | −2.25 |
5 | (0.22,0.48,0.30) | 117 | 1.87 | 4.52 |
6 | (0.25,0.54,0.21) | 104 | 2.09 | −5.67 |
No | Scheme | Jcost (k$) | Jramp | Jrel (%) |
---|---|---|---|---|
1 | (0.22,0.52,0.16) | 95 | 2.83 | −2.91 |
2 | (0.18,0.49,0.33) | 125 | 3.35 | 11.52 |
3 | (0.23,0.53,0.24) | 106 | 2.28 | 5.71 |
4 | (0.21,0.61,0.18) | 102 | 3.22 | 2.38 |
5 | (0.28,0.51,0.21) | 104 | 1.85 | 7.65 |
6 | (0.26,0.58,0.16) | 97 | 1.97 | −4.77 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Nie, C.; Fang, H.; Xiang, X.; Xu, W.; Lei, Q.; Li, Y.; Wang, Y.; Yang, W. Optimization Method for Regulating Resource Capacity Allocation in Power Grids with High Penetration of Renewable Energy Based on Seq2Seq Transformer. Energies 2025, 18, 5218. https://doi.org/10.3390/en18195218
Nie C, Fang H, Xiang X, Xu W, Lei Q, Li Y, Wang Y, Yang W. Optimization Method for Regulating Resource Capacity Allocation in Power Grids with High Penetration of Renewable Energy Based on Seq2Seq Transformer. Energies. 2025; 18(19):5218. https://doi.org/10.3390/en18195218
Chicago/Turabian StyleNie, Chunyuan, Hualiang Fang, Xuening Xiang, Wei Xu, Qingsheng Lei, Yan Li, Yawen Wang, and Wei Yang. 2025. "Optimization Method for Regulating Resource Capacity Allocation in Power Grids with High Penetration of Renewable Energy Based on Seq2Seq Transformer" Energies 18, no. 19: 5218. https://doi.org/10.3390/en18195218
APA StyleNie, C., Fang, H., Xiang, X., Xu, W., Lei, Q., Li, Y., Wang, Y., & Yang, W. (2025). Optimization Method for Regulating Resource Capacity Allocation in Power Grids with High Penetration of Renewable Energy Based on Seq2Seq Transformer. Energies, 18(19), 5218. https://doi.org/10.3390/en18195218