This paper presents a case study where a model predictive control (MPC) logic is developed for energy flexible operation of a space heating system in an educational building. A Long Short-Term Memory Neural Network (LSTM) surrogate model is trained on the output of an EnergyPlus building simulation model. This LSTM model is used within an MPC framework where a genetic algorithm is used to optimize setpoint sequences. The EnergyPlus model is used to validate the performance of the control logic. The MPC approach leads to a substantial reduction in energy consumption (7%) and energy costs (13%) with improved comfort performance. Additional energy costs savings are possible (7–16%) if a sacrifice in indoor thermal comfort is accepted. The presented method is useful for developing MPC systems in the design stages where measured data is typically not available. Additionally, this study illustrates that LSTM models are promising for MPC for buildings.
DOCUMENT
This report has been established within the Flexiheat project. Flexiheat has focused on increasing flexibility in district heating systems. The intelligent district heating network is a dynamic network: an open network where different waste heat and renewable energy sources are connected, that has multiple producers and groups of consumers and facilitates the connection between different energy infrastructures (gas, heat and electricity). Eventually this will lead to an optimal deployment of the available heat sources and an increased cost-efficiency of district heating. Flexiheat aims to develop new concepts for these intelligent, flexible district heating networks. One of the strategies is to allow third party access to the network. A smart control system is developed to manage the heat flows across the network. This system makes use of dynamic pricing. In this exploration the concept of third party access in relation to the Flexiheat project will be discussed. The development of new business and price models based on the Flexiheat approach has led to an analysis of possible alternative price models for consumers.
DOCUMENT
gains and internal gains from appliances,heat gains from occupants are an importantsource contributing to space heating indomestic buildings. It is necessary toconsciously consider all of these heat gainswhen aiming at accurately estimating theheat loss coefficient (HLC) of a building.Whilst sensor technology and algorithms areavailable to quantify the contribution of theheating system, solar gains and electricalappliances, the accurate estimation of thesensible heat gain from occupants ischallenging due to its stochastic character.
MULTIFILE
