Enhancing Battery Storage Energy Arbitrage with Deep Reinforcement Learning and Time-Series Forecasting

• URL: http://arxiv.org/abs/2410.20005v1
• Date: Fri, 25 Oct 2024 23:18:43 GMT
• Title: Enhancing Battery Storage Energy Arbitrage with Deep Reinforcement Learning and Time-Series Forecasting
• Authors: Manuel Sage, Joshua Campbell, Yaoyao Fiona Zhao,
• Abstract summary: We conduct a case study using price data from Alberta, Canada that is characterized by irregular price spikes and highly non-stationary. This data is challenging to forecast even when state-of-the-art deep learning models are deployed. Our results show that energy arbitrage with DRL-enabled battery control still significantly benefits from these imperfect predictions.
• Score: 3.0382033111760576
• License:
• Abstract: Energy arbitrage is one of the most profitable sources of income for battery operators, generating revenues by buying and selling electricity at different prices. Forecasting these revenues is challenging due to the inherent uncertainty of electricity prices. Deep reinforcement learning (DRL) emerged in recent years as a promising tool, able to cope with uncertainty by training on large quantities of historical data. However, without access to future electricity prices, DRL agents can only react to the currently observed price and not learn to plan battery dispatch. Therefore, in this study, we combine DRL with time-series forecasting methods from deep learning to enhance the performance on energy arbitrage. We conduct a case study using price data from Alberta, Canada that is characterized by irregular price spikes and highly non-stationary. This data is challenging to forecast even when state-of-the-art deep learning models consisting of convolutional layers, recurrent layers, and attention modules are deployed. Our results show that energy arbitrage with DRL-enabled battery control still significantly benefits from these imperfect predictions, but only if predictors for several horizons are combined. Grouping multiple predictions for the next 24-hour window, accumulated rewards increased by 60% for deep Q-networks (DQN) compared to the experiments without forecasts. We hypothesize that multiple predictors, despite their imperfections, convey useful information regarding the future development of electricity prices through a "majority vote" principle, enabling the DRL agent to learn more profitable control policies.

Related papers

• Optimal Scheduling of Electric Vehicle Charging with Deep Reinforcement Learning considering End Users Flexibility [1.3812010983144802]
  This work aims to identify households' EV cost-reducing charging policy under a Time-of-Use tariff scheme, with the use of Deep Reinforcement Learning, and more specifically Deep Q-Networks (DQN) A novel end users flexibility potential reward is inferred from historical data analysis, where households with solar power generation have been used to train and test the algorithm.
  arXiv  Detail & Related papers  (2023-10-13T12:07:36Z)
• Combining predictive distributions of electricity prices: Does minimizing the CRPS lead to optimal decisions in day-ahead bidding? [0.0]
  We study whether using CRPS learning, a novel weighting technique, leads to optimal decisions in day-ahead bidding. We find that increasing the diversity of an ensemble can have a positive impact on accuracy. The higher computational cost of using CRPS learning compared to an equal-weighted aggregation of distributions is not offset by higher profits.
  arXiv  Detail & Related papers  (2023-08-29T17:10:38Z)
• Price-Aware Deep Learning for Electricity Markets [58.3214356145985]
  We propose to embed electricity market-clearing optimization as a deep learning layer. Differentiating through this layer allows for balancing between prediction and pricing errors. We showcase the price-aware deep learning in the nexus of wind power forecasting and short-term electricity market clearing.
  arXiv  Detail & Related papers  (2023-08-02T21:16:05Z)
• Benchmarks and Custom Package for Energy Forecasting [55.460452605056894]
  Energy forecasting aims to minimize the cost of subsequent tasks such as power grid dispatch. In this paper, we collected large-scale load datasets and released a new renewable energy dataset. We conducted extensive experiments with 21 forecasting methods in these energy datasets at different levels under 11 evaluation metrics.
  arXiv  Detail & Related papers  (2023-07-14T06:50:02Z)
• Deep Learning for Energy Time-Series Analysis and Forecasting [42.617834983479796]
  Energy time-series analysis describes the process of analyzing past energy observations and possibly external factors so as to predict the future. Following the exceptional performance of Deep Learning (DL) in a broad area of vision tasks, DL models have successfully been utilized in time-series forecasting tasks. This paper aims to provide insight into various DL methods geared towards improving the performance in energy time-series forecasting tasks.
  arXiv  Detail & Related papers  (2023-06-15T13:41:59Z)
• Distributed Energy Management and Demand Response in Smart Grids: A Multi-Agent Deep Reinforcement Learning Framework [53.97223237572147]
  This paper presents a multi-agent Deep Reinforcement Learning (DRL) framework for autonomous control and integration of renewable energy resources into smart power grid systems. In particular, the proposed framework jointly considers demand response (DR) and distributed energy management (DEM) for residential end-users.
  arXiv  Detail & Related papers  (2022-11-29T01:18:58Z)
• Electricity Price Forecasting Model based on Gated Recurrent Units [0.0]
  This paper presents a model for electricity price forecasting based on Gated Recurrent Units. Noise in electricity price seriously reduces the efficiency and effectiveness of analysis. The proposed methodology can perform effectively in prediction of electricity price.
  arXiv  Detail & Related papers  (2022-07-28T16:49:03Z)
• Using Google Trends as a proxy for occupant behavior to predict building energy consumption [0.0]
  This study proposes an approach that utilizes the search volume of topics on the Google Trends platform as a proxy of occupant behavior and use of buildings. Results show that highly correlated Google Trends data can effectively reduce the overall RMSLE error for a subset of the buildings to the level of the GEPIII competition's top five winning teams' performance.
  arXiv  Detail & Related papers  (2021-10-31T08:05:23Z)
• Compute and Energy Consumption Trends in Deep Learning Inference [67.32875669386488]
  We study relevant models in the areas of computer vision and natural language processing. For a sustained increase in performance we see a much softer growth in energy consumption than previously anticipated.
  arXiv  Detail & Related papers  (2021-09-12T09:40:18Z)
• The impact of online machine-learning methods on long-term investment decisions and generator utilization in electricity markets [69.68068088508505]
  We investigate the impact of eleven offline and five online learning algorithms to predict the electricity demand profile over the next 24h. We show we can reduce the mean absolute error by 30% using an online algorithm when compared to the best offline algorithm. We also show that large errors in prediction accuracy have a disproportionate error on investments made over a 17-year time frame.
  arXiv  Detail & Related papers  (2021-03-07T11:28:54Z)
• A Deep Learning Forecaster with Exogenous Variables for Day-Ahead Locational Marginal Price [0.0]
  We propose a deep learning model to forecast day-ahead locational marginal price (daLMP) in deregulated energy markets. This article shows how the proposed model outperforms traditional time series techniques while supporting risk-based analysis of shutdown decisions.
  arXiv  Detail & Related papers  (2020-10-13T16:34:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.