Seasonal thermal energy storage systems (STESSs) can shift the delivery of renewable energy sources and mitigate their uncertainty problems. However, to maximize the operational profit of STESSs and ensure their long-term profitability, control strategies that allow them to trade on wholesale electricity markets are required. While control strategies for STESSs have been proposed before, none of them addressed electricity market interaction and trading. In particular, due to the seasonal nature of STESSs, accounting for the long-term uncertainty in electricity prices has been very challenging. In this article, we develop the first control algorithms to control STESSs when interacting with different wholesale electricity markets. As different control solutions have different merits, we propose solutions based on model predictive control and solutions based on reinforcement learning. We show that this is critical since different markets require different control strategies: MPC strategies are better for day-ahead markets due to the flexibility of MPC, whereas reinforcement learning (RL) strategies are better for real-time markets because of fast computation times and better risk modeling. To study the proposed algorithms in a real-life setup, we consider a real STESS interacting with the day-ahead and imbalance markets in The Netherlands and Belgium. Based on the obtained results, we show that: 1) the developed controllers successfully maximize the profits of STESSs due to market trading and 2) the developed control strategies make STESSs important players in the energy transition: by optimally controlling STESSs and reacting to imbalances, STESSs help to reduce grid imbalances.

In this paper, we propose a data-driven methodology to identify the optimal placement of sensors in a multi-zone building. The proposed methodology is based on statistical tests that study the (in) dependence of measurements from various available sensors. The tests advice on a set of most dissimilar sensors to be retained, as they would convey the maximum information. The method starts with an initial setup that can provide measurements of every building zone to carry out this study; any of these sensors can be removed eventually to decrease costs in normal operation. The method has the advantages of being purely data driven and computationally efficient, as against several methods proposed in the scientific literature, that operate under the premise that detailed building models are available, to evaluate the number/position of the required sensors. This property makes the method scale to different buildings, in an expert free manner. The methodology can help towards better characterization of a building for optimal control and monitoring applications. It is validated against a widely used method – Kalman filtering with Grey-box models, using two different case studies. In both cases, the proposed approach agrees with the results using grey box models, suggesting that the method is reliable, while being quick and efficient.

To correct grid imbalances and avoid grid failures, the transmission system operator (TSO) deploys balancing reserves and settles these imbalances by penalizing the market actors that caused them. In several countries, it is forbidden to influence the grid imbalances in order to let the TSO retain full control of grid regulation. In this paper, we argue that this approach is not optimal as market actors that trade imbalances under the supervision of the TSO can help balancing the grid more efficiently. For instance, some systems such as solar farms cannot participate in the standard balancing market but do have economic incentives to help regulate the grid by trading with imbalances. Based on this argument, we propose a new market framework where any market actor is allowed to trade with imbalances. We show that, using the new market mechanism, the TSO can keep full control of the grid balance while decreasing the balancing cost. This is of primary importance as: 1) novel approaches to reduce grid imbalances are needed as, while renewable sources are generally not used for grid balancing, the increasing integration of renewable energy sources creates higher imbalances. 2) While long-term storage of energy is key in the energy transition, it needs to become an attractive investment to ensure its widespread use; as we show, the proposed market can guarantee that. Based on a real case study, we show that the new market can provide 10–20% of the total balancing energy needed and reduce the balancing costs.

Due to the increasing integration of renewable sources in the electrical grid, electricity generation is expected to become more uncertain. In this context, seasonal thermal energy storage systems (STESSs) are key to shift the delivery of renewable energy sources and tackle their uncertainty problems. In this paper, we propose an optimal controller for STESSs that, using reinforcement learning, builds bidding functions for the day-ahead market. In detail, considering that there is an uncertain energy demand that the STESS has to satisfy, the controller buys energy in the day-ahead market so that the uncertain demand is satisfied while the profits are maximized. Since prices are low during periods of large renewable energy generation (and vice versa), maximizing the profit of a STESS indirectly shifts the delivery of renewable energy to periods of high energy demand while reducing their uncertainty problems. To evaluate the proposed algorithm, we consider a real STESS providing different yearly-demand levels; then, we compare the performance of the controller to the theoretical upper bound, i.e. the optimal cost of buying energy given perfect knowledge of the demand and prices. The results indicate that the proposed controller performs reasonably well: despite the large uncertainty in prices and demand, the proposed controller obtains 70%-50% of the maximum gains given by the theoretical bound.

Recent research has seen several forecasting methods being applied for heat load forecasting of district heating networks. This paper presents two methods that gain significant improvements compared to the previous works. First, an automated way of handling non-linear dependencies in linear models is presented. In this context, the paper implements a new method for feature selection based on [1], resulting in computationally efficient models with higher accuracies. The three main models used here are linear, ridge, and lasso regression. In the second approach, a deep learning method is presented. Although computationally more intensive, the deep learning model provides higher accuracy than the linear models with automated feature selection. Finally, we compare and contrast the proposed methods with earlier work for day-ahead forecasting of heat load in two different district heating networks.