IEAT - Institut für Energie- und Antriebstechnik
Refine
Year of publication
Document Type
- Article (26)
- conference proceeding (article) (16)
- conference proceeding (presentation) (3)
- Handout (3)
- Book (2)
- Part of a Book (1)
- conference proceeding (summary) (1)
- Doctoral Thesis (1)
- Moving Images (1)
- Report (1)
Language
- English (36)
- German (18)
- Multiple languages (1)
Publication reviewed
- begutachtet (46)
- nicht begutachtet (9)
Keywords
- Fernwärme (12)
- Lastprognose (12)
- Maschinelles Lernen (12)
- deepDHC (11)
- KWK-Flex (10)
- Biomass (5)
- CCS (4)
- Deep Learning (4)
- Brennstoffzelle (2)
- Machine Learning (2)
Institute
Die Rolle von Batteriespeichern im Kontext eines künftigen Energiesystems: Smart Energy Systems
(2023)
Welche Bedeutung haben Batteriespeicher für künftige Energiesysteme? Können wir mit Batteriespeichern eine sichere, stabile und bezahlbare Energieversorgung erreichen? Wie flexibel muss unser Stromsystem sein?
In seiner Präsentation im erläutert Prof. Dr. Holger Hesse anhand anschaulicher Beispiele und seiner jahrelangen Erfahrung, ob und wie Elektrofahrzeuge künftig auch durch "Vehicle-to-Grid" einen Beitrag leisten können, wann "Second-life" eine wirkliche Option sein kann und in welchen Bereichen es schon heute wirtschaftlich sein kann, einen Batteriespeicher zu betreiben.
Predictive battery life models are commonly utilized to extrapolate degradation trends observed during accelerated aging tests for simulation of degradation in real-world applications. Thus, fitting accelerated aging data as accurately as possible and with low uncertainty is crucial for making believable projections of battery lifetime, but it is challenging to identify algebraic expressions that accurately fit multivariate degradation trends. A review of models published in literature reveal some common expressions for fitting calendar aging data, which is only dependent on temperature and state-of-charge, but no consistency across many models for fitting cycle aging data, indicating the need for a statistically rigorous data driven approach for developing empirical models. This talk will describe a machine-learning assisted method for identification of predictive battery life models utilizing bilevel optimization and symbolic regression. Bilevel optimization with cross-validation is used to statistically determine cell- and stress-dependent model parameters, while symbolic regression identifies both linear and multiplicative candidate expressions to predict stress-dependent degradation rates by selecting low-order subsets of features from a generated feature library. Because model expressions are identified empirically, it is crucial to ensure resulting models behave according to physical expectations, so the stability of models for interpolation or extrapolation is interrogated qualitatively through simulation and quantitatively through cross-validation and uncertainty quantification via bootstrap resampling. This model identification approach substantially improves upon models identified purely using expert judgement in terms of both accuracy and uncertainty. Model simulation and validation is then conducted by deriving a state-equation form of the predictive model, enabling simulation of battery aging under dynamic stresses. This enables validation of the predictive battery model on lab-based tests with varying conditions or on drive-cycle or application-cycle testing protocols. Parameter uncertainty can be carried forward into model simulation, giving lifetime estimates and confidence windows for cell- or system-level lifetime. The financial impact of battery model uncertainty can be estimated by incorporating uncertainty into a technoeconomic model.
Das Wissen um den zukünftigen Wärmebedarf gewinnt, bei komplexer werdenden Fernwärmesystemen mit volatilen und heterogenen Erzeugungsanlagen, immer weiter an Bedeutung. Denn zur Vermeidung von ineffizienten und unwirtschaftlichen Betriebszuständen muss für eine passende Einsatzoptimierung eine möglichst präzise und zuverlässige Wärmelastprognose vorliegen. Maschinelle Lernverfahren, steigende Datengrundlagen und Verfügbarkeit von ausreichender Rechenleistung bergen hierbei erhebliches Verbesserungspotential. Das von der Hochschule für angewandte Wissenschaften Kempten durchgeführte Forschungsvorhaben „DeepDHC - Untersuchung und Weiterentwicklung modernster maschineller Lernverfahren für die hochgenaue Lastprognose in Fernwärmenetzen“ (FKZ: 03EN3017) befasste sich mit der Performance unterschiedlicher maschineller Lernverfahren zur Wärmelastprognose in Fernwärmenetzen. Unter Berücksichtigung unterschiedlicher Fernwärmenetztopologien, der Einbindung von Smart Meter Daten und der automatisierten Berücksichtigung von Veränderungen im Fernwärmenetz wurden hierbei besonders relevante Fragestellungen aufgegriffen und bearbeitet.
Decarbonisation of heat generation has become a priority for district heating network operators. In order to avoid the use of fossil-fired boilers, operators need to know peaks in heat demand in advance. Accurate thermal load forecasting is playing an increasingly important role in this respect. This paper presents the final results of the research project “deepDHC” (deep learning for district heating and cooling) funded by the German Federal Ministry for Economic Affairs and Climate Action (BMWK). The three-year project focused on systematically benchmarking thermal load forecasts for district heating networks, based on state-of-the-art machine learning methods. The analysis covers a variety of machine learning techniques, such as neural networks – including latest deep learning methods – (e.g. LSTM, TFT, ESN, RC), decision trees (random forests, adaptive boosting, XGB) and statistical methods (SARIMAX). In addition, the impact of combining methods by so-called “stacking” was investigated. Training and validation of the machine learning algorithms was based on historical operating data from the district heating network for the city of Ulm in Germany, in combination with historical weather data, and weather forecasts. Thermal load forecasts – typically for three days ahead – are presented and compared against one another. An automatic tuning routine was developed as part of the project, which enables regular re-training of the machine learning algorithms based on the latest operating data from the heating network. Furthermore, a web interface for real-time forecasting was developed and implemented at the power station.
The battery pack lifetime is severely affected by the State-of-Charge (SOC) and operating temperature. This paper proposes a real-time SoC-Temperature balance power-sharing algorithm for the battery racks to optimize the battery life. The control scheme takes into account the SoC disparity and temperature deviation simultaneously to calculate the active power set-points for battery energy storage system (BESS) units. The proposed algorithm can serve as an alternative to the state of the health (SoH) based power sharing algorithms, which require complex SoH estimation procedures and extensive data for battery age prediction. This method can be particularly useful for second-life batteries, which often show significant heterogeneity in age, internal resistance, and capacity, necessitating a generic yet robust control strategy for their optimal utilization and to minimize degradation. Simulation results demonstrate (i) the suitability of the proposed control scheme for real-time implementation, (ii) the controller efficacy to limit high battery temperatures, which can help to slow down the ageing process. Overall, this research enables the easy integration of second-life batteries for grid ancillary services, obviating the need for complex SoH estimation procedures by considering battery temperature and SoC.
The electrification of the transportation sector leads to an increased deployment of lithium-ion batteries in vehicles. Today, traction batteries are installed, for example, in electric cars, electric buses, and electric boats. These use-cases place different demands on the battery. In this work, simulated data from 60 electric cars and field data from 82 electric buses and six electric boats from Germany are used to quantify a set of stress factors relevant to battery operation and life expectancy depending on the mode of transportation. For this purpose, the open-source tool SimSES designed initially to simulate battery operation in stationary applications is extended toward analyzing mobile applications. It now allows users to simulate electric vehicles while driving and charging. The analyses of the three means of transportation show that electric buses, for example, consume between 1 and 1.5 kWh/km and that consumption is lowest at ambient temperatures around 20 °C. Electric buses are confronted with 0.4–1 equivalent full cycle per day, whereas the analyzed set of car batteries experience less than 0.18 and electric boats between 0.026 and 0.3 equivalent full cycles per day. Other parameters analyzed include mean state-of-charges, mean charging rates, and mean trip cycle depths. Beyond these evaluations, the battery parameters of the transportation means are compared with those of three stationary applications. We reveal that stationary storage systems in home storage and balancing power applications generate similar numbers of equivalent full cycles as electric buses, which indicates that similar batteries could be used in these applications. Furthermore, we simulate the influence of different charging strategies and show their severe impact on battery degradation stress factors in e-transportation. To facilitate widespread and diverse usage, all profile and analysis data relevant to this work is provided as open data as part of this work.
Battery systems are extensively used in smart energy systems in many different applications, such as Frequency Containment Reserve or Self-Consumption Increase. The behavior of a battery in a particular operation scenario is usually summarized using different key performance indicators (KPIs). Some of these indicators such as efficiency indicate how much of the total electric power supplied to the battery is actually used. Other indicators, such as the number of charging-discharging cycles or the number of charging-discharging swaps, are of relevance for deriving the aging and degradation of a battery system. Obtaining these indicators is very time-demanding: either a set of lab experiments is run, or the battery system is simulated using a battery simulation model. This work instead proposes a machine learning (ML) estimation of battery performance indicators derived from time series input data. For this purpose, a random forest regressor has been trained using the real data of electricity grid frequency evolution, household power demand, and photovoltaic power generation. The results obtained in the research show that the required KPIs can be estimated rapidly with an average relative error of less than 10%. The article demonstrates that the machine learning approach is a suitable alternative to obtain a very fast rough approximation of the expected behavior of a battery system and can be scaled and adapted well for estimation queries of entire fleets of battery systems
Lithium-ion cells are subject to degradation due to a multitude of cell-internal aging effects, which can significantly influence the economics of battery energy storage systems (BESS). Since the rate of degradation depends on external stress factors such as the state-of-charge, charge/discharge-rate, and depth of cycle, it can be directly influenced through the operation strategy. In this contribution, we propose a model predictive control (MPC) framework for designing aging aware operation strategies. By simulating the entire BESS lifetime on a digital twin, different aging aware optimization models can be benchmarked and the optimal value for aging cost can be determined. In a case study, the application of generating profit through arbitrage trading on the EPEX SPOT intraday electricity market is investigated. For that, a linearized model for the calendar and cyclic capacity loss of a lithium iron phosphate cell is presented. The results show that using the MPC framework to determine the optimal aging cost can significantly increase the lifetime profitability of a BESS, compared to the prevalent approach of selecting aging cost based on the cost of the battery system. Furthermore, the lifetime profit from energy arbitrage can be increased by an additional 24.9% when using the linearized calendar degradation model and by 29.3% when using both the linearized calendar and cyclic degradation model, compared to an energy throughput based aging cost model. By examining price data from 2019 to 2022, the case study demonstrates that the recent increases in prices and price fluctuations on wholesale electricity markets have led to a substantial increase of the achievable lifetime profit.
KI-Anwendung in der Energietechnik: Einsatz maschineller Lernverfahren für die Wärmelastprognose
(2021)
Maschinelles Lernen gilt als eines der vielversprechendsten Teilgebiete der künstlichen Intelligenz (KI). Sein Einsatz hat in den vergangenen Jahren zu enormen Fortschritten sowohl in der Bild- und Texterkennung als auch bei Zeitreihenprognosen geführt.
Der Vortrag demonstriert dies am Beispiel von Wärmelastprognosen für die Fernwärmebranche. Dabei werden maschinelle Lernverfahren genutzt, um den Wärmebedarf in Fernwärme-netzen über mehrere Tage im Voraus hochgenau vorherzusagen. Auf diese Weise können Energieversorger den Einsatz ihrer Wärmeerzeugungsanlagen optimal planen. Beispielsweise können bei vorhersehbaren Lastspitzen Wärmespeicher frühzeitig mit erneuerbar erzeugter Wärme gefüllt und so der Betrieb fossiler Spitzenlastkraftwerke vermieden werden. Als Folge kann der Betreiber sowohl CO2-Emissionen als auch Emissions-, Brennstoff- sowie An- und Abfahrkosten einsparen.
Der Vortrag basiert auf Ergebnissen aus mehreren Forschungsprojekten, die an der Hochschule Kempten seit 2016 gemeinsam mit Fernwärmeversorgern durchgeführt wurden. Dabei wurden maschinelle Lernverfahren sehr unterschiedlicher Komplexität systematisch untersucht und bewertet – von „einfachen“ bis hin zu anspruchsvollen Verfahren aus dem Bereich des sogenannten „Deep Learning“. Die Wärmelastprognosen werden unter Verwendung historischer Betriebs- und Wetterdaten sowie von Wetterprognosen vollautomatisiert erstellt und dem Betreiber über eine Web-Schnittstelle zur Verfügung gestellt, die auch im Vortrag gezeigt wird.
Die vorgestellte Methode bietet erhebliche Einsparpotenziale für den Anlagenbetreiber. Sie ist zudem auch auf andere Branchen mit ähnlichen Zielgrößen bzw. Fragestellungen übertragbar.