Data-Driven Machine-Learning Model in District Heating System for Heat Load Prediction: A Comparison Study

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/acisc/volume-2016/3403150/figures/3403150.fig.005a.svgz" name="3403150.fig.005a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Predicted versus actual demand with SVR</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/acisc/volume-2016/3403150/figures/3403150.fig.005b.svgz" name="3403150.fig.005b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Predicted versus actual demand with PLS</td></tr><tr class="fig-image" id="c"><td><object data="https://static.hindawi.com/articles/acisc/volume-2016/3403150/figures/3403150.fig.005c.svgz" name="3403150.fig.005c" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(c) </b>Predicted versus actual demand with RF</td></tr></table>

<div>Hourly heat load prediction based on SVR, PLS, and RF for one week.</div>

Applied Computational Intelligence and Soft Computing

fig5

Figure 5

Figure 5: Data-Driven Machine-Learning Model in District Heating System for Heat Load Prediction: A Comparison Study 