Research Article
A High-Frequency Data-Driven Machine Learning Approach for Demand Forecasting in Smart Cities
Table 1
Related work comparison with respect to frequency, forecast horizon, and other factors or complex estimation needed to apply the approach.
| Work | Related work comparison | Frequency | Forecast horizon | Other factors |
| Adamowski et al. [20] | 1 for each day | 24 hours | Weather data during summer | Herrera et al. [21] | 1 for each hour | 1 hour | Weather data | Odan and Reis [22] | 1 for each hour | 24 hours | Weather data | Ji et al. [23] | 1 for each hour | 24 hours | Weather, holidays, and incident data | Hutton and Kapelan [24] | 1 for each hour | 24 hours | Annual calendar data | Candelieri et al. [25–27] | 1 for each hour | 24 hours | Working days and seasons of the year | Alvisi and Franchini [28] | 1 for each hour | 24 hours | Weekly seasonality and seasons of the year | Brentan et al. [29] | 1 for each hour | 24 hours | Annual calendar data | Romano and Kapelan [30] | 1 for each hour | 24 hours | Weekly seasonality | Gagliardi et al. [31] | 1 for each hour | 24 hours | Weekly seasonality | Pacchin et al. [32] | 1 for each hour | 24 hours | Weekly seasonality | Arandia et al. [33] | 1 for each 15 minutes | 24 hours | Daily and weekly seasonality | Bakker et al. [34] | 1 for each 15 minutes | 48 hours | Annual calendar data | Our proposal | 1 for each minute | 24 hours | Weekly seasonality |
|
|