Operational HVAC energy load prediction: Edge-oriented forecasting models

Contemporary office building standards require the installation of advanced HVAC systems, which, alongside industrial processes, are significantly responsible for energy consumption. While the literature describes numerous multi-parameter, deep artificial neural networks that are highly complex but poorly explainable (black box), commercial control systems must be based on simple-to-implement, easily adaptable intelligent predictive models whose reliability stems from their monitorability and explainability. The study verified several edge-oriented approaches using machine learning techniques for short- and medium-term predictions (1 day) with relatively high granularity (15 minutes). High granularity of time intervals, combined with high prediction reliability, not only provide a practical opportunity to optimize energy consumption, but also to increase the efficiency of renewable energy sources exploitation. Operational, high granularity predictions can also be used to detect anomalies and attacks, as required by modern cybersecurity rules.