Maintaining flexibility in smart grid consumption through deep learning and deep reinforcement learning

Gallego, Fernando; Martin, Charles L.; Díáz, Manuel; Garrido, Daniel

doi:10.1016/j.egyai.2023.100241

Cited by 17 publications

(4 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Through continuous interaction with the grid and analysis of consumption patterns, RL models can predict peak-load periods and adjust demand accordingly, either by directly controlling smart appliances or through pricing incentives to consumers [30]. The best DRL model, as identified by Gallego et al [31], achieves a complete listing of optimal actions for the forthcoming hour 90% of the time. This level of precision underscores the potential of DRL in enhancing the flexibility of smart grids, providing a robust mechanism for adjusting grid operations in response to real-time conditions and forecasts.…”

Section: Smart Grid Applicationsmentioning

confidence: 99%

“…By dynamically adjusting the dispatch of DERs based on current grid conditions and forecasted demand, RL contributes to a more flexible and responsive grid system [32]. Gallego et al [31] illustrate the application of deep reinforcement learning techniques, specifically Deep Q-Networks (DQNs), to select optimal actions for managing grid components.…”

Section: Smart Grid Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning Techniques in Optimizing Energy Systems

Stavrev,

Ginchev

2024

Electronics

View full text Add to dashboard Cite

Reinforcement learning (RL) techniques have emerged as powerful tools for optimizing energy systems, offering the potential to enhance efficiency, reliability, and sustainability. This review paper provides a comprehensive examination of the applications of RL in the field of energy system optimization, spanning various domains such as energy management, grid control, and renewable energy integration. Beginning with an overview of RL fundamentals, the paper explores recent advancements in RL algorithms and their adaptation to address the unique challenges of energy system optimization. Case studies and real-world applications demonstrate the efficacy of RL-based approaches in improving energy efficiency, reducing costs, and mitigating environmental impacts. Furthermore, the paper discusses future directions and challenges, including scalability, interpretability, and integration with domain knowledge. By synthesizing the latest research findings and identifying key areas for further investigation, this paper aims to inform and inspire future research endeavors in the intersection of reinforcement learning and energy system optimization.

show abstract

Section: Smart Grid Applicationsmentioning

confidence: 99%

Section: Smart Grid Applicationsmentioning

confidence: 99%

Reinforcement Learning Techniques in Optimizing Energy Systems

Stavrev,

Ginchev

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…In recent years, researchers have begun to apply deep reinforcement learning-related technologies to the field of financial investment. RL is an adaptive model, and dynamic self-improving trading strategies can be developed by using RL [6], [7], [8]. Some literatures have studied the application of RL methods in stock trading.…”

Section: Introductionmentioning

confidence: 99%

Multi-Feature Supervised Reinforcement Learning for Stock Trading

2023

IEEE Access

View full text Add to dashboard Cite

Deep reinforcement learning (DRL) algorithm is often used to find the best trading strategy in algorithmic trading. However, the classical DRL model is difficult to achieve rapid convergence, and the features extracted from the market data are relatively simple, resulting in incomplete DRL learning information. In this paper, we propose a supervised reinforcement learning method, a hybrid optimal investment strategy formation method consisting of long short-term memory neural network (LSTM) and deep deterministic policy gradient (DDPG). By participating in reinforcement learning in the early stage of supervised learning, agents can obtain guiding prior experience, thus reducing the cost of agent learning and accelerating convergence. In addition, multi-feature state input is added to the model to optimize the agent's learning of the environment. Compared with DDPG algorithm, LSTM-DDPG algorithm achieves convergence faster. Experiments on three regional stock markets in China, the United States and Europe show that LSTM-DDPG algorithm has higher profit and lower risk than B&H, MACD and LSTM trading strategies.INDEX TERMS Supervised reinforcement learning, finance and operations, reinforcement learning, deep deterministic policy gradient, long short-term memory.

show abstract

“…It also reflects the ability of a power network to maintain a consistent supply during temporary and significant imbalances. Although reference [20] has a new definition of flexibility in smart grids: "possibility of maintaining consumption within specific ranges". According to reference [21], the definition of flexibility varies among research groups and is often based on the primary field of study.…”

Section: Introductionmentioning

confidence: 99%

Simultaneous energy hub operation and construction for investigating quantitative flexibility considering uncertain supply and demand side resources

Rashedi,

Abdollahi,

Rashidinejad

2023

Scientia Iranica

View full text Add to dashboard Cite

In this paper, the quantitative flexibility of EH is evaluated considering a flexibility index which is based upon available maximum capacity as well as the response time of generating units. Here, the impact of simultaneous EH operation and construction are investigated on quantitative flexibility considering both uncertain supply and demand side resources. Hence, a new structure so-called multi-objective simultaneous operation/construction optimization of multi-carrier EH is presented ( soco MC MOF-EH ) which consists of a decrease in operation and construction costs as well increase in power system flexibility. The demand side uncertainties, including thermal/electrical demand, are implemented by the Gaussian distribution function, and uncertainty on the supply side, including gas pressure uncertainty (GPU), is modeled by the probabilistic-possibilistic Znumber method. Also, in multifarious cases, the performance of the proposed index is evaluated.It is shown how flexible resources like electrical storage systems (ESS), thermal storage systems (TSS), electrical demand response programs (EDRP), and thermal demand response programs (TDRP) can increase the flexibility of the EH. It is also conducted that how the flexibility enhancement can increase construction costs.

show abstract

Maintaining flexibility in smart grid consumption through deep learning and deep reinforcement learning

Cited by 17 publications

References 49 publications

Reinforcement Learning Techniques in Optimizing Energy Systems

Reinforcement Learning Techniques in Optimizing Energy Systems

Multi-Feature Supervised Reinforcement Learning for Stock Trading

Simultaneous energy hub operation and construction for investigating quantitative flexibility considering uncertain supply and demand side resources

Contact Info

Product

Resources

About