Figure 5
A prediction error plot shows minimal average error at 0.00 kilowatt-hours.The scatter plot is titled “Prediction Error Plot - Edge A I (Random Forest).” The vertical axis is labeled “Prediction Error (kilowatt-hour),” ranging from negative 0.05 to 0.10, in increments of 0.05. The horizontal axis is labeled “Predicted Energy Consumption (kilowatt-hour),” ranging from 4.0 to 5.5, in increments of 0.5. Data points are clustered between (4.536, 0.003) and (5.054, 0.004). Some of the data points are (4.432, 0.002), (4.630, 0.047), (4.966, 0.018), (5.335, 0.005), and (5.28, 0.045). A few points extend upward to around (4.350, 0.14) and downward to about (4.5, negative 0.05). A horizontal dashed reference line is drawn at the zero error, around which most points are densely scattered. Note: All numerical data values are approximated.

Prediction error distribution relative to predicted energy consumption using edge AI model. Source(s): Author’s work

or Create an Account

Close Modal
Close Modal