Heuristic decision rules for short-term trading of renewable energy with co-located energy storage

Hassler, Michael

doi:10.1016/j.cor.2016.12.027

Cited by 19 publications

(14 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scholars are actively engaged in developing tools and algorithms for price and load forecasting [9,10]; while load forecasting has reached advanced stages of development, price forecasting techniques are still in their early stages of maturity [5]. Aggarwal, Saini [5] provide a comprehensive review of the main methodologies used in electricity price forecasting and a detailed analysis of extant studies based on the time horizon for prediction, the input and output variables used, the obtained results, the data points used for analysis, and the preprocessing technique/model architecture employed.…”

Section: Introductionmentioning

confidence: 99%

Forecasting Electricity Prices: A Machine Learning Approach

2020

View full text Add to dashboard Cite

The electricity market is a complex, evolutionary, and dynamic environment. Forecasting electricity prices is an important issue for all electricity market participants. In this study, we shed light on how to improve electricity price forecasting accuracy through the use of a machine learning technique—namely, a novel genetic programming approach. Drawing on empirical data from the largest EU energy markets, we propose a forecasting model that considers variables related to weather conditions, oil prices, and CO2 coupons and predicts energy prices 24 hours ahead. We show that the proposed model provides more accurate predictions of future electricity prices than existing prediction methods. Our important findings will assist the electricity market participants in forecasting future price movements.

show abstract

Section: Introductionmentioning

confidence: 99%

Forecasting Electricity Prices: A Machine Learning Approach

2020

View full text Add to dashboard Cite

show abstract

“…The optimization is carried out using Approximate Dynamic Programming (ADP) methods, where a parameterised policy is obtained based on the observed stochastic processes for the price, the RES error and the level of the reservoir (Gönsch and Hassler 2016). The ADP approach presented in Gönsch and Hassler (2016) is compared in Hassler (2017) to some threshold-based heuristic decision rules. The parameters are updated according to simulationbased experience and the obtained performance is comparable to the ADP algorithm.…”

Section: Bidding Strategies In Literaturementioning

confidence: 99%

A deep reinforcement learning framework for continuous intraday market bidding

et al. 2021

View full text Add to dashboard Cite

The large integration of variable energy resources is expected to shift a large part of the energy exchanges closer to real-time, where more accurate forecasts are available. In this context, the short-term electricity markets and in particular the intraday market are considered a suitable trading floor for these exchanges to occur. A key component for the successful renewable energy sources integration is the usage of energy storage. In this paper, we propose a novel modelling framework for the strategic participation of energy storage in the European continuous intraday market where exchanges occur through a centralized order book. The goal of the storage device operator is the maximization of the profits received over the entire trading horizon, while taking into account the operational constraints of the unit. The sequential decision-making problem of trading in the intraday market is modelled as a Markov Decision Process. An asynchronous version of the fitted Q iteration algorithm is chosen for solving this problem due to its sample efficiency. The large and variable number of the existing orders in the order book motivates the use of high-level actions and an alternative state representation. Historical data are used for the generation of a large number of artificial trajectories in order to address exploration issues during the learning process. The resulting policy is back-tested and compared against a number of benchmark strategies. Finally, the impact of the storage characteristics on the total revenues collected in the intraday market is evaluated.

show abstract

“…According to that progress, a short-term scale analyses should be applied in future energy planning studies. Studies [8] and [9] analyzed short-term electricity markets in order to enhance RES integration into the power system. Many studies are done dealing with energy planning on 1 h time scales for different energy systems.…”

Section: Introductionmentioning

confidence: 99%

Vehicle-to-Grid in Standard and Fast Electric Vehicle Charging: Comparison of Renewable Energy Source Utilization and Charging Costs

2020

View full text Add to dashboard Cite

Croatia aims to achieve 10% of its energy production from the renewable energy sources in the total energy consumption in the transport sector. One of the ways to achieve this goal is by the use of electric vehicles. This work comparatively analyses the financial and social aspects of vehicle-to-grid charging in standard and fast charging mode, their impact on the renewable electricity production and the total electricity consumption regulated through variable electricity prices. Data were taken for the wider urban area of the Dubrovnik region. The assumption is that the Dubrovnik region will be self-sufficient by the year 2050 with 100% renewable electricity production and that all conventional vehicles will be replaced by electric vehicles. This work aims to show that the fast charging based on 10 min time steps offers more opportunities for flexibility and utilization of renewable generation in the energy system than the standard charging based on hourly time step. The results of this work showed the opposite, where in most of the scenarios standard charging provided better results. Replacement of the existing two tariff model in electricity prices with variable electricity prices contributes to the stability of the energy system, providing better regulation of charging and higher opportunities for renewable electricity utilization in standard and fast charging and reduction of charging costs. According to the financial aspects, fast charging is shown to be more expensive, but for the social aspects, it provides electric vehicles with more opportunities for better competition in the market.

show abstract

Heuristic decision rules for short-term trading of renewable energy with co-located energy storage

Cited by 19 publications

References 27 publications

Forecasting Electricity Prices: A Machine Learning Approach

Forecasting Electricity Prices: A Machine Learning Approach

A deep reinforcement learning framework for continuous intraday market bidding

Vehicle-to-Grid in Standard and Fast Electric Vehicle Charging: Comparison of Renewable Energy Source Utilization and Charging Costs

Contact Info

Product

Resources

About