Abstract
This article regards the dependency structure of wind power and load time series at each moment as the conditional probability of a high-dimensional discrete stochastic process. A dynamic Bayesian network (DBN) model is proposed to calculate the joint probability distribution of high-dimensional stochastic processes, which can completely describe the potential dependency structure of wind power and load at each time. The DBN model is based on a data-driven approach, using Bayesian information criteria (BICs) as the scoring function, and using a greedy search algorithm to determine the initial network and transmission network DBN structure. Maximum likelihood estimation (MLE) is used to estimate the parameters of the initial network and the transmission network. The DBN model is established from these two networks, and the joint probability distribution of the stochastic process is obtained. Sequential Monte Carlo (SMC) sampling is performed on the DBN model to generate the dependent simulation sequence of wind power and load. Using probability density, mean value, maximum output fluctuation, and autocorrelation and cross-correlation functions as evaluation indicators, the statistical characteristics of the historical sequence, simulation sequence based on the DBN model, and simulation sequence based on the hidden Markov model (HMM) are comprehensively compared and analyzed to verify the effectiveness of the DBN model.
Similar content being viewed by others
References
Fang X, Sedzro KS, Yuan HY, Ye HX, Hodge BM (2020) Deliverable Flexible Ramping Products Considering Spatiotemporal Correlation of Wind Generation and Demand Uncertainties. IEEE Trans Power Syst 35(4):2561–2574
Vysocky J, Misak S (2020) Review of Trends and Targets of Complex Systems for Power System Optimization. Energies 13(5)
Pluta M, Wyrwa A, Suwala W, Zysk J, Raczynski M, Tokarski S (2020) A Generalized Unit Commitment and Economic Dispatch Approach for Analysing the Polish Power System under High Renewable Penetration. Energies 13(8)
Liu J, Ji XQ, Li KJ, Zhang KY (2020) Multi-time scale optimal dispatch for AC/DC distribution networks based on a markov chain dynamic scenario method and MPC. J Electric Comput Eng, vol. 2020
Huo YC, Bouffard F, Joos G (2020) Spatio-Temporal Flexibility Management in Low-Carbon Power Systems. IEEE Trans Sustain Energy 11(4):2593–2605
D’Amico G, Masala G, Petroni F, Sobolewski RA (2020) Managing Wind Power Generation via Indexed Semi-Markov Model and Copula. Energies 13(16)
Zhong JJ, Li Y, CaoYJ, Tan Y, Peng YJ, Zeng ZL, Cao LH (2020) Stochastic optimization of integrated energy system considering network dynamic characteristics and psychological preference. J Clean Product, vol. 275
Laslett D, Creagh C, Jennings P (2016) A simple hourly wind power simulation for the South-West region of Western Australia using MERRA data. Renew Energy 96:1003–1014
Verdejo H, Awerkin A, Kliemann W, Becker C (2019) Modelling uncertainties in electrical power systems with stochastic differential equations. Int J Electric Power Energy Syst 113:322–332
Ma R, Fouladirad M, Grall A (2018) Flexible wind speed generation model: Markov chain with an embedded diffusion process. Energy 164:316–328
Loukatou A, Howell S, Johnson P, Duck P (2018) Stochastic wind speed modelling for estimation of expected wind power output. Appl Energy 228:1328–1340
Cai DF, Shi DY, Chen JF (2014) Probabilistic load flow computation using Copula and Latin hypercube sampling. Iet Gen Trans Distribut 8(9):1539–1549
Othman MM, Abdelaziz AY, Hegazi YG, El-Khattam W (2015) Approach for modelling stochastically dependent renewable energy-based generators using diagonal band copula. Iet Renew Power Gen 9(7):809–820
Cao J, Yan Z (2017) Probabilistic optimal power flow considering dependences of wind speed among wind farms by pair-copula method. Int J Electric Power Energy Syst 84:296–307
Papaefthymiou G, Klockl B (2008) MCMC for wind power simulation. Ieee Trans Energy Convers 23(1):234–240
Xie KG, Liao QL, Tai HM, Hu B (2017) Non-Homogeneous Markov Wind Speed Time Series Model Considering Daily and Seasonal Variation Characteristics. Ieee Transa Sustain Energy 8(3):1281–1290
Martinez EN, Cutululis N, Sorensen P (2018) High dimensional dependence in power systems: A review. Renew Sustain Energy Review 94:197–213
Xu SZ, Xu B (2019) Time series generation and complex correlation assessment for multiple wind farms. 2019 5th International Conference on Energy Materials and Environment Engineering, vol. 295
Tang J, Brouste A, Tsui KL (2015) Some improvements of wind speed Markov chain modeling. Renew Energy 81:52–56
Zhu CX, Zhang Y, Yan Z, Zhu JZ (2019) Markov chain-based wind power time series modelling method considering the influence of the state duration on the state transition probability. Iet Renew Power Gen 13(12):2051–2061
Bhaumik D, Crommelin D, Kapodistria S, Zwart B (2019) Hidden Markov Models for Wind Farm Power Output. Ieee Trans Sustain Energy 10(2):533–539
Sun WG, Zamani M, Hesamzadeh MR, Zhang HT (2020) Data-Driven Probabilistic Optimal Power Flow With Nonparametric Bayesian Modeling and Inference. Ieee Trans Smart Grid 11(2):1077–1090
Lin XY, Jiang YY, Peng S, Chen HX, Tang JJ, Li WY (2020) An efficient Nataf transformation based probabilistic power flow for high-dimensional correlated uncertainty sources in operation. International Journal of Electrical Power & Energy Systems 116
Yuan S, Dai CH, Guo A, Chen WR (2019) A novel multi-objective robust optimization model for unit commitment considering peak load regulation ability and temporal correlation of wind powers. Electric Power Syst Res 169:115–123
Zakaria A, Ismail FB, Lipu MSH, Hannan MA (2020) Uncertainty models for stochastic optimization in renewable energy applications. Renew Energy 145:1543–1571
Naghdalian S, Amraee T, Kamali S, Capitanescu F (2020) Stochastic Network-Constrained Unit Commitment to Determine Flexible Ramp Reserve for Handling Wind Power and Demand Uncertainties. Ieee Trans Ind Inform 16(7):4580–4591
AbuElrub A, Al-Masri HMK, Singh C (2020) Hybrid wind-solar grid-connected system planning using scenario aggregation method. International Transactions on Electrical Energy Systems 30(9)
Jamali A, Aghaei J, Esmaili M, Nikoobakht A, Niknam T, Shafie-khah M, Catalao JPS (2020) Self-Scheduling Approach to Coordinating Wind Power Producers With Energy Storage and Demand Response. Ieee Trans Sustain Energy 11(3):1210–1219
Murphy KP, Paskin MA (2002) Linear time inference in hierarchical HMMs. Advances in Neural Information Processing Systems 14, Vols 1 and 2, vol. 14, pp. 833–840
Perrin BE, Ralaivola L, Mazurie A, Bottani S, Mallet J, d’Alche-Buc F (2003) Gene networks inference using dynamic Bayesian networks. Bioinformatics, vol. 19, pp. Ii138–Ii148
Xiao QK (2017) Recurrent neural network system using probability graph model optimization. Appl Intell 46(4):889–897
Chickering DM, Heckerman D, Meek C (2004) Large-sample learning of Bayesian networks is NP-hard. J Mach Learn Res 5:1287–1330
Kwisthout J (2015) Most frugal explanations in Bayesian networks. Artificial Intell 218:56–73
Ramos-Lopez D, Masegosa AR, Martinez AM, Salmeron A, Nielsen TD, Langseth H, Madsen AL (2017) MAP inference in dynamic hybrid Bayesian networks. Prog Artificial Intell 6(2):133–144
Wang X. Y,Ji Q (2012) Learning Dynamic Bayesian Network Discriminatively for Human Activity Recognition. 2012 21st International Conference on Pattern Recognition (Icpr 2012), pp. 3553-3556
Amari S, Park H, Ozeki T (2006) Singularities affect dynamics of learning in neuromanifolds. Neural Comput 18(5):1007–1065
Peraza LR, Halliday DM (2010) Fourier Bayesian Information Criterion for Network Structure and Causality Estimation. pp 33–36
Yang Y, Gao XG, Guo ZG (2019) Finding optimal Bayesian networks by a layered learning method. J Syst Eng Electron 30(5):946–958
Sato M (2001) Online model selection based on the variational bayes. Neural Comput 13(7):1649–1681
Xie LX, Chang SF, Divakaran A, Sun HF (2003) Unsupervised mining of statistical temporal structures in video. Video Mining 6:279–307
He ZW, Gao MY, Ma GJ, Liu YY, Chen SX (2014) Online state-of-health estimation of lithium-ion batteries using Dynamic Bayesian Networks. J Power Sources 267:576–583
Historical Market Data: Elspot prices\_2019\_hourly\_eur. XLS [EB/OL]. [2020-09-09]. https://www.nordpoolgroup.com/historical-market-data/
Acknowledgements
This work was supported by the Natural Science Fund of Fujian Province (Nos. 2019J01845, 2020J01429, 2020J01433, 2020J01434) and the Research and Innovation Team of Ningde Normal University (No. 2018T05).
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
About this article
Cite this article
Wang, H., Zou, B. Wind power and load temporal dependence model based on dynamic Bayesian network. Electr Eng 104, 1265–1276 (2022). https://doi.org/10.1007/s00202-021-01375-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00202-021-01375-6