Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free A deep learning approach for power system knowledge discovery based on multitask learning

© The Institution of Engineering and Technology
Received 12/03/2018, Accepted 18/12/2018, Revised 02/11/2018, Published 19/12/2018

Power system security assessment is an important and challenging problem. Large variations in loads and power generation present increased risks to the secure operation of power systems. This study proposes a distributed deep network structure for power system security knowledge discovery based on multitask learning to monitor and control power grids more properly and effectively. First, a deep neural network structure based on the deep belief network (DBN) is designed to non-linearly extract deep and abstract features layer-by-layer for total transfer capability (TTC) regression tasks. Then, a distributed training algorithm for the deep structure is developed to accelerate the training process. Furthermore, multitask learning is adopted by grouping and training-related tasks together to improve the task performance. Finally, the accuracy and efficiency of the deep structure are evaluated using the Guangdong Power Grid in China. The simulation results demonstrate that the proposed model can outperform the existing shallow models in terms of accuracy and stability and can meet the requirements of online computing efficiency.

Inspec keywords: neural nets; learning (artificial intelligence); power grids; regression analysis; data mining; power engineering computing; power generation protection; power system security; belief networks

Other keywords: power generation; total transfer capability regression tasks; power system security knowledge discovery; power system security assessment; deep learning; deep neural network structure; China; deep belief network; multitask learning; TTC regression tasks; Guangdong Power Grid; distributed training algorithm; distributed deep network structure; DBN

Subjects: Neural computing techniques; Other topics in statistics; Knowledge engineering techniques; Power system protection; Other topics in statistics; Data handling techniques; Power engineering computing

References

    1. 1)
      • 23. Caruana, R.: ‘Multitask learning’, Mach. Learn., 1997, 28, pp. 41–75.
    2. 2)
      • 19. Singh, S., Majumdar, A.: ‘Deep sparse coding for non-intrusive load monitoring’, IEEE Trans. Smart Grid, 2018, 9, (5), pp. 4669–4678.
    3. 3)
      • 15. Claessens, B., Vrancx, P., Ruelens, F.: ‘Convolutional neural networks for automatic state-time feature extraction in reinforcement learning applied to residential load control’, IEEE Trans. Smart Grid, 2018, 9, (4), pp. 3259–3269.
    4. 4)
      • 3. Wehenkel, L.: ‘Machine-learning approaches to power-system security assessment’, IEEE Expert, 1997, 12, (5), pp. 60–72.
    5. 5)
      • 33. Zhang, B., Yan, Z.: ‘Advanced electric power network analysis’ (Cengage Learning Asia Press, Singapore, 2010).
    6. 6)
      • 9. Hinton, G., Salakhutdinov, R.: ‘Reducing the dimensionality of data with neural networks’, Science, 2006, 313, (5786), pp. 504–507.
    7. 7)
      • 18. Varga, E., Beretka, S., Noce, C., et al: ‘Robust real-time load profile encoding and classification framework for efficient power systems operation’, IEEE Trans. Power Syst., 2015, 30, (4), pp. 1897–1904.
    8. 8)
      • 27. Dean, J., Corrado, G., Monga, R., et al: ‘Large scale distributed deep networks’.Proc. Int. Conf. Neural Information Processing Systems, Lake Tahoe, USA, December 2012, pp. 1223–1231.
    9. 9)
      • 34. Ilic, M., Galiana, F., Fink, L., et al: ‘Transmission capacity in power networks’, Int. J.Electr. Power Energy Syst., 1998, 20, (2), pp. 99–110.
    10. 10)
      • 31. Vapnik, V., Levin, E., Cun, Y.: ‘Measuring the VC-dimension of a learning machine’, Neural Comput., 1994, 6, (5), pp. 851–876.
    11. 11)
      • 5. He, M., Zhang, J., Vittal, V.: ‘Robust online dynamic security assessment using adaptive ensemble decision-tree learning’, IEEE Trans. Power Syst., 2013, 28, (4), pp. 4089–4098.
    12. 12)
      • 24. Fiot, J., Dinuzzo, F.: ‘Electricity demand forecasting by multi-task learning’, IEEE Trans. Smart Grid, 2018, 9, (2), pp. 544–551.
    13. 13)
      • 13. Srivastava, N., Hinton, G., Krizhevsky, A., et al: ‘Dropout: a simple way to prevent neural networks from overfitting’, J. Mach. Learn. Res., 2014, 15, (1), pp. 1929–1958.
    14. 14)
      • 21. Wang, L., Zhang, Z., Xu, J., et al: ‘Wind turbine blade breakage monitoring with deep autoencoders’, IEEE Trans. Smart Grid, 2018, 9, (4), pp. 2824–2833.
    15. 15)
      • 16. Kong, W., Dong, Z., Hill, D., et al: ‘Short-term residential load forecasting based on resident behaviour learning’, IEEE Trans. Power Syst., 2018, 33, (1), pp. 1087–1088.
    16. 16)
      • 7. Sun, H., Zhao, F., Wang, H., et al: ‘Automatic learning of fine operating rules for online power system security control’, IEEE Trans. Neural Netw. Learn. Syst., 2016, 27, (8), pp. 1708–1719.
    17. 17)
      • 30. ‘Learning Theory by Andrew Ng’. Available at https://www.stanford.edu/class/cs229/notes/cs229-notes4.ps, accessed Autumn 2017.
    18. 18)
      • 25. Karimipour, H., Dinavahi, V.: ‘Extended Kalman filter-based parallel dynamic state estimation’, IEEE Trans. Smart Grid, 2015, 6, (3), pp. 1539–1549.
    19. 19)
      • 20. Zhang, C., Chen, C., Gan, M., et al: ‘Predictive deep Boltzmann machine for multiperiod wind speed forecasting’, IEEE Trans. Sustain. Energy, 2015, 6, (4), pp. 1416–1425.
    20. 20)
      • 8. Huang, T., Guo, Q., Sun, H.: ‘A distributed computing platform supporting power system security knowledge discovery based on online simulation’, IEEE Trans. Smart Grid, 2017, 8, (3), pp. 1513–1524.
    21. 21)
      • 29. Roux, N., Bengio, Y.: ‘Representational power of restricted Boltzmann machines and deep belief networks’, Neural Comput., 2008, 20, (6), pp. 1631–1649.
    22. 22)
      • 6. Wang, T., Bi, T., Wang, H., et al: ‘Decision tree based online stability assessment scheme for power systems with renewable generations’, CSEE J. Power Energy Syst., 2015, 1, (2), pp. 53–61.
    23. 23)
      • 11. Hinton, G., Osindero, S., Teh, Y.: ‘A fast learning algorithm for deep belief nets’, Neural Comput., 2006, 18, (7), pp. 1527–1554.
    24. 24)
      • 1. Wang, J., Zhong, H., Ma, Z., et al: ‘Review and prospect of integrated demand response in the multi-energy system’, Appl. Energy, 2017, 202, pp. 772–782.
    25. 25)
      • 28. ‘Revisiting distributed synchronous SGD’.Available at http://lanl.arxiv.org/pdf/1604.00981v3, accessed 21 March 2017.
    26. 26)
      • 32. Hecht-Nielsen, R.: ‘Theory of backpropagation neural network’.Proc. Int. Joint Conf. Neural Networks, Washington, DC, USA, June 1989, pp. 593–605.
    27. 27)
      • 22. Wang, L., Zhang, Z., Chen, J.: ‘Short-term electricity price forecasting with stacked denoisingautoencoders’, IEEE Trans. Power Syst., 2017, 32, (4), pp. 2673–2681.
    28. 28)
      • 2. Morison, K., Wang, L., Kundur, P.: ‘Power system security assessment’, IEEE Power Energy Mag., 2004, 2, (5), pp. 30–39.
    29. 29)
      • 26. Asrari, A., Lotfifard, S., Ansari, M.:‘Reconfiguration of smart distribution systems with time varying loads using parallel computing’, IEEE Trans. Smart Grid, 2016, 7, (6), pp. 2713–2723.
    30. 30)
      • 17. Shi, H., Xu, M., Li, R.: ‘Deep learning for household load forecasting – a novel pooling deep RNN’, IEEE Trans. Smart Grid, 2018, 9, (5), pp. 5271–5280.
    31. 31)
      • 10. Hinton, G.: ‘Training products of experts by minimizing contrastive divergence’, Neural Comput., 2002, 14, (8), pp. 1771–1800.
    32. 32)
      • 4. Wehenkel, L., Pavella, M.: ‘Decision tree approach to power systems security assessment’, Int. J.Electr. Power Energy Syst., 1993, 15, (1), pp. 13–36.
    33. 33)
      • 14. Hinton, G.: ‘A practical guide to training restricted Boltzmann machines’, Momentum, 2012, 9, (1), pp. 599–619.
    34. 34)
      • 12. Bengio, Y., Lamblin, P., Popovici, D., et al: ‘Greedy layer-wise training of deep networks’.Proc. Int. Conf. Neural Information Processing Systems, Vancouver, Canada, December 2006, pp. 153–160.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-gtd.2018.5078
Loading

Related content

content/journals/10.1049/iet-gtd.2018.5078
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address