Electricity Price Forecasting in Smart Grid: A Novel E-CNN Model
- 769 Downloads
The vital part of the smart grid is electricity price forecasting because it makes grid cost saving. Although, existing systems for price forecasting may be challenging to manage with enormous price data in the grid. As repetition from the feature cannot be avoided and an integrated system is needed for regulating the plans in price. To handle this problem, a new price forecasting system is developed. This proposed model particularly integrated with three systems. Initially, features are selected from the random data by combining the Mutual Information (MI) and Random Forest (RF). The Grey Correlation Analysis (GCA) is used to remove the redundancy from the selected features. Secondly, the Recursive Feature Elimination (RFE) scheme is used to reduce the dimensions. Finally, classification is done based on Enhanced-Convolutional Neural Network (E-CNN) classifier to forecast the price. The simulation results show that our accuracy of the proposed system is higher than existing benchmark schemes.
- 1.Ahmad, W., Javaid, N., Sajjad, M.Z., Awan, T., Amir, M.: A new memory updation heuristic scheme for energy management in smart grid (2018)Google Scholar
- 2.Varshney, H., Sharma, A., Kumar, R.: A hybrid approach to price forecasting incorporating exogenous variables for a day ahead electricity market. In: IEEE International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), pp. 1–6. IEEE (2017)Google Scholar
- 14.Nayab, A., Javaid, N.: Load and price forecasting in smart grids using enhanced support vector machineGoogle Scholar
- 17.Wang, Z., Yan, W., Oates, T.: Time series classification from scratch with deep neural networks: a strong baseline. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 1578–1585. IEEE (2017)Google Scholar
- 20.ISO New England Energy Offer Data [Online] (2016). www.iso-ne.com/isoexpress/web/reports/pricing/-/tree/dayahead-energy-offer-data