No abstract

No abstract

No abstract

With uncertainty in energy markets, and the effects of climate change looming, reducing energy use and operational cost of existing building systems is more important than ever. To this end, this paper presents a grey-box modelling approach to characterise the behaviour of chilled and frozen and coldrooms using basic system specifications and measured data. An overall energy balance is used to devise a discrete state space model for each cabinet, characterised by unknown empirical parameters relating to heat capacity and heat transfer properties. Historical system data from a UK supermarket are used in combination with a genetic algorithm optimisation to determine the optimal empirical parameters for 10 display cases and 10 coldrooms. The resulting cabinet temperature predictions have a good level of accuracy, achieving a root-mean squared error (RMSE) of 0.37°C to 0.98°C. Overall this data-driven approach is effective and efficient in modelling refrigeration systems, and can be easily generalised to any system where historical data is available. Finally, the use of the proposed approach in cost minimisation or demand response application is presented.

Reliable monitoring for photovoltaic assets (PVs) is essential to ensuring uptake, long term performance, and maximum return on investment of renewable systems. To this end this paper investigates the input data and machine learning techniques required for day-behind predictions of PV generation, within the scope of conducting informed maintenance of these systems. Five years of PV generation data at hourly intervals were retrieved from four commercial building-mounted PV installations in the UK, as well as weather data retrieved from MIDAS. A support vector machine, random forest and artificial neural network were trained to predict PV power generation. Random forest performed best, achieving an average mean relative error of 2.7%. Irradiance, previous generation and solar position were found to be the most important variables. Overall, this work shows how low-cost data driven analysis of PV systems can be used to support the effective management of such assets.