Abstract
Optimal management of demand-side flexibility in buildings is important for properly integrating large amounts of intermittent generation from windmills and photovoltaics. This paper proposes a novel Energy Management Agent (EMA) concept that can optimize building’s energy costs with respect to external prices while at the same time allow building’s flexibility to be used via explicit demand response. The EMA combines Artificial Neural Networks (ANN) and model predictive control for modelling and optimization of building’s flexibility. It continuously manages building’s flexibility with respect to external prices and provides forecasts of the load and available flexibility for a defined time window. A proof-of-concept (PoC) of the EMA is implemented for controlling a heat pump in an apartment, located in Oulu, Finland. Two ANN-based models were implemented for modelling the energy consumption of the heat pump and the indoor temperature of the apartment. Monte Carlo Tree Search based planning and control was implemented for finding optimal control policies with the ANNs. The EMA PoC was evaluated in 16-week period between 11 November 2019 - 1 March, 2020. When compared to a fixed setpoint control strategy, the EMA achieved 14.8 % lower costs under Nord Pool spot prices for Finland. At the same time, it was also able to accurately follow the 24h load plans (NRMSE was 0.050) and activate the offered flexibilities (NRMSE was 0.074).
Highlights
The power generation of renewable energy sources (RES) such as photovoltaics (PV) and windmills is volatile and cannot be controlled in the same way as in traditional power plants
Demand-side flexibility management solutions need to support both implicit and explicit demand response programs at the same time. This is because fluctuations in the generation and demand are typically only visible in the global electricity market prices and optimizing flexibility only based on these prices can cause bottlenecks within the distribution network
The aim of the evaluation was to answer following questions: 1. How much Energy Management Agent (EMA) is able to reduce costs when compared to a baseline control strategy?
Summary
The power generation of renewable energy sources (RES) such as photovoltaics (PV) and windmills is volatile and cannot be controlled in the same way as in traditional power plants. Buildings’ HVAC systems have complex non-linear dynamics with long feedback cycles caused by the thermal mass of the building This makes it challenging to design controllers that can utilize the available flexibility in an optimal way. A popular method for learning optimal control policies in buildings is model-free reinforcement learning (RL), which has been demonstrated to improve energy efficiency and reduce costs when compared to traditional rule-based control strategies [11]–[14] model-free RL has two significant limitations, which make it non-ideal solution for consumer flexibility management. We demonstrate the approach in context of heat pump control and show that it is possible to simultaneously optimize energy consumption with respect to external prices while providing accurate load forecasts and DR responses.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
