A Hybrid Deep Learning Framework for Network Flow Forecasting of Power Grid Enterprise
With the expansion of the digital business line, the network flow behind the digital power grid is also exploding. To prevent network congestion, this article proposes a novel network flow forecasting model, which is composed of variational mode decomposition (VMD), GRU-xgboost block, and a forecast...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2022/5497574 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832562296383078400 |
|---|---|
| author | Xin Huang Ting Hu Pei Pei Qin Li Xin Zhang |
| author_facet | Xin Huang Ting Hu Pei Pei Qin Li Xin Zhang |
| author_sort | Xin Huang |
| collection | DOAJ |
| description | With the expansion of the digital business line, the network flow behind the digital power grid is also exploding. To prevent network congestion, this article proposes a novel network flow forecasting model, which is composed of variational mode decomposition (VMD), GRU-xgboost block, and a forecasting adjustment block, to grasp the changing patterns and trends of network flow in advance, and to formulate reasonable and effective flow management strategies and meet the requirements of users for network service quality. The network flow series in power grid enterprise always contain complex patterns and outliers, and VMD is applied to adaptively process complex net flow time series into several subseries with simpler patterns. A GRU-xgboost block is designed to reconstruct the features of historical series. Then, xgboost model is applied to generate predictions for all decomposed subsignals. For the final predictions, we design a forecasting adjustment block to further remove the influence of random noise. Finally, the empirical results show the superior performance of the proposed model on network flow forecasting task. |
| format | Article |
| id | doaj-art-e8ff38a3afb24f418230557365fa8a2d |
| institution | Kabale University |
| issn | 1099-0526 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-e8ff38a3afb24f418230557365fa8a2d2025-02-03T01:22:58ZengWileyComplexity1099-05262022-01-01202210.1155/2022/5497574A Hybrid Deep Learning Framework for Network Flow Forecasting of Power Grid EnterpriseXin Huang0Ting Hu1Pei Pei2Qin Li3Xin Zhang4Nari Group Corporation (State Grid Electric Power Research Institute)Nari Group Corporation (State Grid Electric Power Research Institute)State Grid Jiangsu Electric Power CompanyNari Group Corporation (State Grid Electric Power Research Institute)Nari Group Corporation (State Grid Electric Power Research Institute)With the expansion of the digital business line, the network flow behind the digital power grid is also exploding. To prevent network congestion, this article proposes a novel network flow forecasting model, which is composed of variational mode decomposition (VMD), GRU-xgboost block, and a forecasting adjustment block, to grasp the changing patterns and trends of network flow in advance, and to formulate reasonable and effective flow management strategies and meet the requirements of users for network service quality. The network flow series in power grid enterprise always contain complex patterns and outliers, and VMD is applied to adaptively process complex net flow time series into several subseries with simpler patterns. A GRU-xgboost block is designed to reconstruct the features of historical series. Then, xgboost model is applied to generate predictions for all decomposed subsignals. For the final predictions, we design a forecasting adjustment block to further remove the influence of random noise. Finally, the empirical results show the superior performance of the proposed model on network flow forecasting task.http://dx.doi.org/10.1155/2022/5497574 |
| spellingShingle | Xin Huang Ting Hu Pei Pei Qin Li Xin Zhang A Hybrid Deep Learning Framework for Network Flow Forecasting of Power Grid Enterprise Complexity |
| title | A Hybrid Deep Learning Framework for Network Flow Forecasting of Power Grid Enterprise |
| title_full | A Hybrid Deep Learning Framework for Network Flow Forecasting of Power Grid Enterprise |
| title_fullStr | A Hybrid Deep Learning Framework for Network Flow Forecasting of Power Grid Enterprise |
| title_full_unstemmed | A Hybrid Deep Learning Framework for Network Flow Forecasting of Power Grid Enterprise |
| title_short | A Hybrid Deep Learning Framework for Network Flow Forecasting of Power Grid Enterprise |
| title_sort | hybrid deep learning framework for network flow forecasting of power grid enterprise |
| url | http://dx.doi.org/10.1155/2022/5497574 |
| work_keys_str_mv | AT xinhuang ahybriddeeplearningframeworkfornetworkflowforecastingofpowergridenterprise AT tinghu ahybriddeeplearningframeworkfornetworkflowforecastingofpowergridenterprise AT peipei ahybriddeeplearningframeworkfornetworkflowforecastingofpowergridenterprise AT qinli ahybriddeeplearningframeworkfornetworkflowforecastingofpowergridenterprise AT xinzhang ahybriddeeplearningframeworkfornetworkflowforecastingofpowergridenterprise AT xinhuang hybriddeeplearningframeworkfornetworkflowforecastingofpowergridenterprise AT tinghu hybriddeeplearningframeworkfornetworkflowforecastingofpowergridenterprise AT peipei hybriddeeplearningframeworkfornetworkflowforecastingofpowergridenterprise AT qinli hybriddeeplearningframeworkfornetworkflowforecastingofpowergridenterprise AT xinzhang hybriddeeplearningframeworkfornetworkflowforecastingofpowergridenterprise |