Sell or store? An ADP approach to marketing renewable energy

Gönsch, Jochen; Hassler, Michael

doi:10.1007/s00291-016-0439-x

Cited by 17 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In both works, the problem is formulated as a sequential decision-making process, where the operator adjusts its offers during the trading horizon, according to the RES forecast updates for the physical delivery of power. Additionally, in Gönsch and Hassler (2016) the use of a PHES unit is proposed to undertake energy arbitrage and to offset potential deviations. The trading process is formulated as a Markov Decision Process (MDP) where the future commitment decision in the market is based on the stochastic realization of the intraday price, the imbalance penalty, the RES production and the storage availability.…”

Section: Bidding Strategies In Literaturementioning

confidence: 99%

“…In this way, the scarcity of conventional units approaching real time is reflected. In Gönsch and Hassler (2016), real weather data and market data are used to simulate the forecast error and CID price processes.…”

Section: Bidding Strategies In Literaturementioning

confidence: 99%

“…For the sequential decision-making problem in the CID market, the offered quantity of energy is the decision variable to be optimized (Garnier and Madlener 2015). 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.…”

Section: Bidding Strategies In Literaturementioning

confidence: 99%

See 2 more Smart Citations

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

Section: Bidding Strategies In Literaturementioning

confidence: 99%

Section: Bidding Strategies In Literaturementioning

confidence: 99%

Section: Bidding Strategies In Literaturementioning

confidence: 99%

See 1 more Smart Citation

A deep reinforcement learning framework for continuous intraday market bidding

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The goal of the current control methodology is to ensure the required balance between production and consumption at all times by letting production follow the demand. However, driven by environmental targets, a large number of small-scale generation units are being introduced in the system in recent years, many of which exploit renewable, uncontrollable sources such as wind and sun (Gönsch and Hassler 2016). To offset the loss of flexibility on the production side and avoid very high investment requirements in infrastructure, flexibility on the demand side is increasingly considered as a valuable alternative (Siano 2014;Vardakas et al 2015).…”

Section: Introductionmentioning

confidence: 99%

Resource allocation problems in decentralized energy management

2017

View full text Add to dashboard Cite

Changes in our electricity supply chain are causing a paradigm shift from centralized control towards decentralized energy management. Within the framework of decentralized energy management, devices that offer flexibility in their load profile play an important role. These devices schedule their flexible load profile based on steering signals received from centralized controllers. The problem of finding optimal device schedules based on the received steering signals falls into the framework of resource allocation problems. We study an extension of the traditional problems studied within resource allocation and prove that a divide-and-conquer strategy gives an optimal solution for the considered extension. This leads to an efficient recursive algorithm, with quadratic complexity in the practically relevant case of quadratic objective functions. Furthermore, we study discrete variants of two problems common in decentralized energy management. We show that these problems are NP-hard and formulate natural relaxations of both considered discrete problems that we solve efficiently. Finally, we show that the solutions to the natural relaxations closely resemble solutions to the original, hard problems.This research is conducted within the EASI project (12700) supported by STW and Alliander and the EU FP7 project e-balance (609132).

show abstract

“…Gönsch and Hassler (2016) consider this aspect for a producer that generates energy from stochastic, renewable sources, such as solar or wind and uses a storage device with conversion losses. They model the resulting commitment problem as a Markov Decision Process and solve it using an approximate dynamic programming approach.…”

Section: Sell or Store? An Adp Approach To Marketing Renewable Energymentioning

confidence: 99%

Quantitative solutions for future energy systems and markets

2016

View full text Add to dashboard Cite

In the recent years, it has become more and more evident that anthropogenic climate change is real and happening at an accelerating pace, which is threatening modern society. The 2015 UN-climate conference in Paris brought about a global consensus that emission of climate active gases has to be drastically reduced to mitigate the effects of global warming.Players in the energy sector, therefore, face rapidly changing conditions due to technological progress, the fast growth of renewables, market liberalization, and changes in global demand and supply. Firms, governments, and consumers are confronted with new challenges connected to increased competition, decentralization of production and the globalization of energy markets. These new problems call for tailored quantitative solutions to analyze, optimize, and control the operation of energy systems and markets, taking into account the distinct economic, technological and political characteristics of the energy sector. Generally, energy systems are complex technical systems with strict real-time requirements and very high requirements in fault tolerance. Often these systems are embedded into markets that mirror the complexity of the technical system as, for example, is the case with power markets. The optimal design and operation of such

show abstract

Sell or store? An ADP approach to marketing renewable energy

Cited by 17 publications

References 19 publications

A deep reinforcement learning framework for continuous intraday market bidding

A deep reinforcement learning framework for continuous intraday market bidding

Resource allocation problems in decentralized energy management

Quantitative solutions for future energy systems and markets

Contact Info

Product

Resources

About