Refine
Document Type
- Article (15)
- Conference Proceeding (13)
- Preprint (1)
Institute
Keywords
- Demand side management (4)
- Desalination (3)
- Bubble column humidifier (2)
- Demand response (2)
- Energy storage (2)
- Heat pump (2)
- Humidification-dehumidification (2)
- Minkowski sum (2)
- Organic Rankine Cycle (2)
- Power tracking (2)
Power plant operators increasingly rely on predictive models to diagnose and monitor their systems. Data-driven prediction models are generally simple and can have high precision, making them superior to physics-based or knowledge-based models, especially for complex systems like thermal power plants. However, the accuracy of data-driven predictions depends on (1) the quality of the dataset, (2) a suitable selection of sensor signals, and (3) an appropriate selection of the training period. In some instances, redundancies and irrelevant sensors may even reduce the prediction quality.
We investigate ideal configurations for predicting the live steam production of a solid fuel-burning thermal power plant in the pulp and paper industry for different modes of operation. To this end, we benchmark four machine learning algorithms on two feature sets and two training sets to predict steam production. Our results indicate that with the best possible configuration, a coefficient of determination of R^2 = 0.95 and a mean absolute error of MAE=1.2 t/h with an average steam production of 35.1 t/h is reached. On average, using a dynamic dataset for training lowers MAE by 32% compared to a static dataset for training. A feature set based on expert knowledge lowers MAE by an additional 32 %, compared to a simple feature set representing the fuel inputs. We can conclude that based on the static training set and the basic feature set, machine learning algorithms can identify long-term changes. When using a dynamic dataset the performance parameters of thermal power plants are predicted with high accuracy and allow for detecting short-term problems.
Verbraucherseitige Laststeuerung (Demand Side Management – DSM) wird als ein möglicher Ansatz betrachtet, um die Auswirkungen des Ausbaus von fluktuierenden Erneuerbaren im Stromnetz auszugleichen. Sollen viele verteilte Energiesysteme damit angesprochen werden, stellen zentralistische Ansätze dabei hohe Anforderungen an die Kommunikationsinfrastruktur. Als Alternative wird vielfach eine autonome Laststeuerung (ADSM) mit anreizbasierter Optimierung direkt auf dem Verbrauchergerät betrachtet. Dabei kann die Anreizfunktion mittels unidirektionaler Kommunikation übertragen werden.
Am Forschungszentrum Energie der Fachhochschule Vorarlberg wurden in den letzten Jahren Algorithmen und Prototypen für den Einsatz von ADSM auf verschiedensten verteilten Energiespeichern im elektrischen Stromnetz entwickelt. Dabei werden sowohl thermische Energiespeicher (z. B. Haushalts-Warmwasserspeicher) als auch elektrochemische Speicher (z. B. Batteriespeichersysteme oder Elektroautos) betrachtet. Außerdem werden die Auswirkungen solcher Systeme auf das elektrische Verteilnetz untersucht. Dieser Artikel gibt einen Überblick über die entwickelten Methoden und Ergebnisse aus diesem Forschungsfeld mit dem Ziel, ein weitreichendes Verständnis für die Chancen und Grenzen des ADSM zu schaffen.
Increasing electric vehicle penetration leads to undesirable peaks in power if no proper coordination in charging is implemented. We tested the feasibility of electric vehicles acting as flexible demands responding to power signals to minimize the system peaks. The proposed hierarchical autonomous demand side management algorithm is formulated as an optimal power tracking problem. The distribution grid operator determines a power signal for filling the valleys in the non-electric vehicle load profile using the electric vehicle demand flexibility and sends it to all electric vehicle controllers. After receiving the control signal, each electric vehicle controller re-scales it to the expected individual electric vehicle energy demand and determines the optimal charging schedule to track the re-scaled signal. No information concerning the electric vehicles are reported back to the utility, hence the approach can be implemented using unidirectional communication with reduced infrastructural requirements. The achieved results show that the optimal power tracking approach has the potential to eliminate additional peak demands induced by electric vehicle charging and performs comparably to its central implementation. The reduced complexity and computational overhead permits also convenient deployment in practice.
The electricity demand due to the increasing number of EVs presents new challenges for the operation of the electricity network, especially for the distribution grids. The existing grid infrastructure may not be sufficient to meet the new demands imposed by the integration of EVs. Thus, EV charging may possibly lead to reliability and stability issues, especially during the peak demand periods. Demand side management (DSM) is a potential and promising approach for mitigation of the resulting impacts. In this work, we developed an autonomous DSM strategy for optimal charging of EVs to minimize the charging cost and we conducted a simulation study to evaluate the impacts to the grid operation. The proposed approach only requires a one way communicated incentive. Real profiles from an Austrian study on mobility behavior are used to simulate the usage of the EVs. Furthermore, real smart meter data are used to simulate the household base load profiles and a real low voltage grid topology is considered in the load flow simulation. Day-ahead electricity stock market prices are used as the incentive to drive the optimization. The results for the optimum charging strategy is determined and compared to uncontrolled EV charging. The results for the optimum charging strategy show a potential cost saving of about 30.8% compared to uncontrolled EV charging. Although autonomous DSM of EVs achieves a shift of load as pursued, distribution grid operation may be substantially affected by it. We show that in the case of real time price driven operation, voltage drops and elevated peak to average powers result from the coincident charging of vehicles during favourable time slots.