Journal of Modern Power Systems and Clean Energy

ISSN 2196-5625 CN 32-1884/TK

Building Load Forecasting Using Deep Neural Network with Efficient Feature Fusion
Author:
Affiliation:

1.Department of Electrical, Computer, and System Engineering at Case Western Reserve University, Cleveland, USA;2.College of Aeronautics and Engineering, Kent State University, Kent, USA;3.Software College, Northeastern University, Shenyang, China

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
    Abstract:

    The energy consumption of buildings has risen steadily in recent years. It is vital for the managers and owners of the building to manage the electric energy demand of the buildings. Forecasting electric energy consumption of the buildings will bring great profits, which is influenced by many factors that make it very difficult to provide an advanced forecasting. Recently, deep learning techniques are widely adopted to solve this problem. Deep neural network offers an excellent capability in handling complex non-linear relationships and competence in exploring regular patterns and uncertainties of consumption behaviors at the building level. In this paper, we propose a deep convolutional neural network based on ResNet for hour-ahead building load forecasting. In addition, we design a branch that integrates the temperature per hour into the forecasting branch. To enhance the learning capability of the model, an innovative feature fusion is presented. At last, sufficient ablation studies are conducted on the point forecasting, probabilistic forecasting, fusion method, and computation efficiency. The results show that the proposed model has the state-of-the-art performance, which reflects a promising prospect in application of the electricity market.

    表 4 Table 4
    表 6 Table 6
    表 7 Table 7
    表 5 Table 5
    表 2 Table 2
    图1 Structure of ResNet.Fig.1
    图2 Architecture of our proposed model.Fig.2
    图3 Illustration of one residual block as baseline of proposed forecasting branch.Fig.3
    图4 Scatter plot of five models for building A. (a) ResNet. (b) GCNN. (c) LSTM. (d) GRU. (e) Proposed model.Fig.4
    图5 MAPE heat map of single-step forecasting on 300 buildings.Fig.5
    图6 MAPE heat map of 24-step forecasting on 300 buildings.Fig.6
    图7 Pinball scores of probabilistic load forecasting for three buildings.Fig.7
    图8 Learning curves of training error for building A with five models.Fig.8
    表 8 Table 8
    表 3 Table 3
    表 1 Table 1
    Reference
    Related
    Cited by
Get Citation
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:May 21,2020
  • Revised:
  • Adopted:
  • Online: January 22,2021
  • Published: