Load Balance Forecasting Based on Hybrid Deep Neural Network

Year 2024, Volume: 39 Issue: 1, 167 - 174, 28.03.2024

Hajir Khalaf Nezihe Yıldıran

https://doi.org/10.21605/cukurovaumfd.1459425

Abstract

Load forecasting is the foundation of utility design, and it is a fundamental business problem in the utility industry. Load forecasting, mainly referring to forecasting electricity demand and energy, is being used throughout all segments of the electric power industry, including generation, transmission, distribution, and retail. In this paper, a long short-term memory network with a hybrid approach is improved with a dense algorithm and proposed for electricity load forecasting. A long short-term memory network is designed to effectively exhibit the dynamic behavior of load time series. The proposed model is tested for Panama study including historical data and weather variables. The prediction accuracy is validated by performance metrics, and the best of the metrics are attained when mean absolute error is 5.262, mean absolute percentage error 0.0000376, and root mean square error 18.243. The experimental results show a high prediction rate for load balance forecasting of electric power consumption.

Keywords

Dense layer, Load forecasting, Long short-term memory, Machine learning

Hibrit Derin Sinir Ağına Dayalı Yük Dengesi Tahmini

Abstract

Yük tahmini, hizmet tasarımının temelidir ve hizmet sektöründe temel bir iş sorunudur. Ağırlıklı olarak elektrik talebini ve enerjiyi tahmin etmeye atıfta bulunan yük tahmini, üretim, iletim, dağıtım ve perakende dahil olmak üzere elektrik enerjisi endüstrisinin tüm segmentlerinde kullanılmaktadır. Bu bildiride, hibrit bir yaklaşıma sahip uzun bir kısa süreli bellek ağı, yoğun bir algoritma ile geliştirilmiş ve elektrik yükü tahmini için önerilmiştir. Uzun bir kısa süreli bellek ağı, yükleme süresi serilerinin dinamik davranışını etkili bir şekilde sergilemek için tasarlanmıştır. Önerilen model, tarihsel verileri ve hava durumu değişkenlerini içeren Panama çalışması için test edilmiştir. Tahmin doğruluğu, performans ölçümleriyle doğrulanır ve ölçümlerin en iyisi, ortalama mutlak hata 5,262, ortalama mutlak yüzde hatası 0,0000376 ve kök ortalama kare hatası 18,243 olduğunda elde edilir. Deneysel sonuçlar, elektrik gücü tüketiminin yük dengesi tahmini için yüksek bir tahmin oranı göstermektedir.

Keywords

Makine öğrenimi, Uzun kısa süreli bellek, Yük tahmini, Yoğun katman

References

• 1. Kuster, C., Rezgui, Y., Mourshed, M., 2017. Electrical Load Forecasting Models: A Critical Systematic Review. Sustainable Cities and Society, 35, 257-270.
• 2. Fiot, J., Dinuzzo, F., 2016. Electricity Demand Forecasting by Multi-task Learning. IEEE Transactions on Smart Grid, 9(2), 544-551.
• 3. Dedinec, A., Filiposka, S., Dedinec, A., Kocarev, L., 2016. Deep Belief Network Based Electricity Load Forecasting: An Analysis of Macedonian Case. Energy, 115, 1688-1700.
• 4. Armstrong, J., 2001. Selecting Forecasting Methods. In Principles of Forecasting, Springer, 365-386.
• 5. Idowu, S., Saguna, S., Ahlund, C., Schelen, O., 2016. Applied Machine Learning: Forecasting Heat Load in District Heating System. Energy and Buildings, 133, 478-488.
• 6. Ertugrul, Ö., 2016. Forecasting Electricity Load by a Novel Recurrent Extreme Learning Machines Approach. International Journal of Electrical Power and Energy Systems, 78, 429-435.
• 7. Zahid, M., Ahmed, F., Javaid, N., Abbasi, R., Kazmi, H., Javaid, A., Bilal, M., Akbar, M., Ilahi, M., 2019. Electricity Price and Load Forecasting Using Enhanced Convolutional Neural Network and Enhanced Support Vector Regression in Smart Grids. Electronics, 8(2), 122.
• 8. Bouktif, S., Fiaz, A., Ouni, S., Serhani, M., 2018. Optimal Deep Learning LSTM Model for Electric Load Forecasting Using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches. Energies, 11(7), 1636.
• 9. Bouktif, S., Fiaz, A., Ouni, S., Serhani, M., 2019. Single and Multi-sequence Deep Learning Models for Short and Medium Term Electric Load Forecasting. Energies, 12(1), 149.
• 10. Wen, L., Zhou, K., Yang, S., Lu, X., 2019. Optimal Load Dispatch of Community Microgrid with Deep Learning Based Solar Power and Load Forecasting. Energy, 171, 1053-1065.
• 11. Shrestha A., Mahmood, A., 2019. Review of Deep Learning Algorithms and Architectures. IEEE Access, 7, 53040-53065.
• 12. Ryu, S., Noh, J., Kim, H., 2016. Deep Neural Network Based Demand Side Short Term Load Forecasting. Energies, 10(1), 3.
• 13. Hochreiter H., Schmidhuber, J., 1997. Long Short-term Memory. Neural Computation, 9(8), 1735-1780.
• 14. Dalton, B., 2019. Data mining: A Preprocessing Engine. Solid State Technology, 62(4), 9-16.
• 15. Liu, Z., 2011. A Method of SVM with Normalization in Intrusion Detection. Procedia Environmental Sciences, 11, 256-262.