ASPECTS OF TEMPERATURE TAKING INTO ACCOUNT TO INCREASE THE ACCURACY OF SHORT-TERM FORECASTING OF NODE LOADS

Authors

DOI:

https://doi.org/10.20535/1813-5420.2.2021.247368

Keywords:

nodal electrical load, short-term forecasting, artificial neural network, recurrent network, multifactor forecasting

Abstract

The peculiarities of the influence of air temperature data on the accuracy of forecasting of nodal loads in power systems and how the accuracy of such forecasting changes depending on the training sample and its volume are considered. The application of the data analysis method to detect anomalous values ​​and omissions to reduce data distortion and improve forecasting results is considered. A neural network of deep learning of the LSTM type was used for multifactor prediction of nodal loads. To evaluate the effectiveness of the forecast accuracy, various variants of data samples for neural network training are considered.

References

On Electricyty Market: The Law of Ukraine. No. 2019-VIII of 13.04.2017.

Ivanov H., Blinov I., Parus Y. Simulation Model of New Electricity Market in Ukraine. IEEE 6th International Conference on Energy Smart Systems. 2019. DOI: https://doi.org/10.1109/ESS.2019.8764184

Blinov I.V. Problems of functioning and development of a new electricity market model in Ukraine (According to the scientific report at the meeting of the Presidium of NAS of Ukraine, February 3, 2021)// Visn. Nac. Acad. Nauk Ukr. 2021. No 3. Pp. 20-28.(Ukr) DOI: doi.org/10.15407/visn2021.03.020

NEURC’s Resolution “On Approval of Market Rules” No. 307 dd 14. 03.2018

I. Blinov, V. Miroshnyk, P. Shymaniuk The cost of error of "day ahead" forecast of technological losses of electrical energy. Tekhnichna elektrodynamika. 2020. No.5 pp 70-73 DOI: https://doi.org/10.15407/techned2020.05.070

I. Blinov, V. Miroshnyk, P. Shymaniuk Short-term interval forecast of total electricity generation by renewableenergy sources producers. Proceedings of the Institute of Electrodynamics of the National Academy of Sciences of Ukraine. 2019. No. 54 pp. 5-12.

Seyedeh Narjes Fallah; Mehdi Ganjkhani; Shahaboddin Shamshirband. Computational Intelligence on Short-Term Load Forecasting: A Methodological Overview. MDPI 2019.

P. Chernenko, V. Miroshnyk, P. Shymaniuk Univariable short-term forecast of nodal electrical loads of energy systems. Tekhnichna elektrodynamika. 2020. No. 2. Pp 67-73. DOI: https://doi.org/10.15407/techned2020.02.067

Aoyang Han, Bin Zhang, Zhongliang Sun, Zhiqiang Niu, Junxiong Wang Nodal load forecast model considering network topology constraints. IEEE PES Asia-Pacific Power and Energy Conference. Xi'an.China. 2016.Pp. 939-943.

G.P. Shumilova, N.Je. Gotman, T.B.Starceva Prediction of the active and reactive load of EPS units using inversion of an artificial neural network. Elektrichestvo. No 6. 2007. Pp. 7-13.

G. Hou, K. Xu, S. Yin, Y. Wang, Y. Han, Z. Wang, Y. Mao, Z. Lei A novel algorithm for multi-node load forecasting based on big data of distribution network. International Conference on Advanced Electronic Science and Technology (AEST 2016), Shenzhen, 2016, Pp 655-667.

P. Chernenko, V. Sychova. 2021. Improving the algorithm for determining the effect of air temperature on the overall electrical load of the power system to improve the accuracy of short-term forecasting. Tekhnichna elektrodynamika. 2021. №2, pp. 77-83.

S. Hochreiter, J. Schmidhuber Long Short-term Memory // Neural computation. 1997. No 9. Pp 1735-1780.

G. Klambauer, T. Unterthiner, A. Mayr, S. Hochreiter Self-Normalizing Neural Networks // Advances in Neural Information Processing Systems. 2017. № 30. Pp. 971-980.

D.P. Kingma, J. Ba Adam. A Method for Stochastic Optimization // Proc. of the 3rd International Conference on Learning Representations (ICLR).

Published

2021-12-21

Issue

Section

ENERGY SYSTEMS AND COMPLEXES