Development of a hybrid electricity-loss forecasting model based on DBSCAN clustering and MLP neural networks

Khilola Z. Nazirova

Энергия ва ресурс тежаш муаммолари · 2026-yil

Annotatsiya

Relevance: operational data from distribution networks contain noise, outliers and locally heterogeneous operating regimes that may distort neural-network training and reduce forecast robustness. This creates a need for an integrated architecture in which density-based structural filtering and local nonlinear forecasting are treated as complementary stages of one predictive process. Aim: to develop and validate a hybrid electricity-loss forecasting architecture that combines density-based DBSCAN clustering with local multilayer perceptron models, and to quantify the accuracy gain attributable to the preliminary structural decomposition of the data. Methods: real operational data were subjected to density-based structural filtering using DBSCAN. The input feature space comprised active power, ambient temperature and relative humidity. PCA-assisted analysis was used to select ε=0.4 and minPts=5. A separate MLP was trained for each detected dense cluster, and the final forecast was generated through a composite Y_hybrid structure. Forecast accuracy was evaluated using MAPE. Results: the baseline MLP achieved a MAPE of 2.58 %, whereas the DBSCAN–MLP architecture reduced MAPE to 2.10 %, corresponding to an 18.6 % relative error reduction. Actual-versus-predicted trajectories remained closely aligned for training, validation and test subsets, supporting the robustness of the hybrid architecture.

Maqola ma’lumotlari
MualliflarKhilola Z. Nazirova
JurnalЭнергия ва ресурс тежаш муаммолари
Nashriyot«Ўзбекэнерго» АО, ТДТУ, Ўзбекистон Республикаси ФА, Энергия ва ресурслар тежаш илмий-амалий ўқув маркази, «Ўздавэнергоназорат» давлат инспекцияси, «Энергия тежамкорлиги ва қайта тикланувчи энергия манбалари» илмий-тадқиқот лабораторияси
ISSN2091-5985, 2181-1946
Nashr sanasi2026-10-18
Son3
Betlar280-287
TilIngliz
Ilmiy sohaTexnika
Indeksga qo‘shilgan2026-10-22

Maqolaning asl sahifasi

Ilmiy soha

Texnika

Iqtibos keltirish

APAKhilola Z. Nazirova (2026). Development of a hybrid electricity-loss forecasting model based on DBSCAN clustering and MLP neural networks. Энергия ва ресурс тежаш муаммолари, (3), 280-287. https://energy.tdtu.uz/index.php/journal/article/view/439
GOST (OAK)Khilola Z. Nazirova Development of a hybrid electricity-loss forecasting model based on DBSCAN clustering and MLP neural networks // Энергия ва ресурс тежаш муаммолари. – 2026. – № 3. – P. 280-287.
MLAKhilola Z. Nazirova. “Development of a hybrid electricity-loss forecasting model based on DBSCAN clustering and MLP neural networks.” Энергия ва ресурс тежаш муаммолари, (3), 280-287, 2026. https://energy.tdtu.uz/index.php/journal/article/view/439
ChicagoKhilola Z. Nazirova. “Development of a hybrid electricity-loss forecasting model based on DBSCAN clustering and MLP neural networks.” Энергия ва ресурс тежаш муаммолари, (3), 280-287 (2026). https://energy.tdtu.uz/index.php/journal/article/view/439
HarvardKhilola Z. Nazirova (2026) ‘Development of a hybrid electricity-loss forecasting model based on DBSCAN clustering and MLP neural networks’, Энергия ва ресурс тежаш муаммолари, (3), 280-287. https://energy.tdtu.uz/index.php/journal/article/view/439
BibTeX
@article{khilolaznazirova2026,
  title = {Development of a hybrid electricity-loss forecasting model based on DBSCAN clustering and MLP neural networks},
  author = {Khilola Z. Nazirova},
  journal = {Энергия ва ресурс тежаш муаммолари},
  year = {2026},
  number = {3},
  pages = {280-287},
  url = {https://energy.tdtu.uz/index.php/journal/article/view/439}
}

Boshqa maqola uchun iqtibos tayyorlash

Энергия ва ресурс тежаш муаммолари jurnalidan boshqa maqolalar

Энергия ва ресурс тежаш муаммолари — barcha maqolalar · 2026-yil arxivi

Texnika sohasidagi boshqa maqolalar

Texnika sohasidagi OAK jurnallari