Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Deep Reinforcement Learning Approach to Battery Management in Dairy Farming via Proximal Policy Optimization

Nawazish Ali, Rachael Shaw, Karl Mason

TL;DR

This work addresses the energy management challenge in dairy farming by applying proximal policy optimization (PPO), a deep reinforcement learning (DRL) method, to optimize battery storage in a PV-enabled dairy farm setup. The methodology combines a PV–battery–grid environment with a PPO agent operating on a state space $(\text{hour},\text{SOC},\text{load},\text{PV})$ and actions \{Charge, Discharge, Idle\}, aiming to minimize grid imports via a reward that penalizes costly energy and unsafe SOC states. Key findings show PPO reduces grid electricity import by 13.11% compared to the no-battery baseline and outperforms both Q-learning (1.62% gain) and a rule-based approach (2.56% gain), with performance influenced by solar availability across seasons. This demonstrates the practical potential of DRL-driven battery management for dairy farms, suggesting future extensions to wind generation, regional tests, and comparisons with additional DRL methods for broader applicability.

Abstract

Dairy farms consume a significant amount of electricity for their operations, and this research focuses on enhancing energy efficiency and minimizing the impact on the environment in the sector by maximizing the utilization of renewable energy sources. This research investigates the application of Proximal Policy Optimization (PPO), a deep reinforcement learning algorithm (DRL), to enhance dairy farming battery management. We evaluate the algorithm's effectiveness based on its ability to reduce reliance on the electricity grid, highlighting the potential of DRL to enhance energy management in dairy farming. Using real-world data our results demonstrate how the PPO approach outperforms Q-learning by 1.62% for reducing electricity import from the grid. This significant improvement highlights the potential of the Deep Reinforcement Learning algorithm for improving energy efficiency and sustainability in dairy farms.

A Deep Reinforcement Learning Approach to Battery Management in Dairy Farming via Proximal Policy Optimization

TL;DR

This work addresses the energy management challenge in dairy farming by applying proximal policy optimization (PPO), a deep reinforcement learning (DRL) method, to optimize battery storage in a PV-enabled dairy farm setup. The methodology combines a PV–battery–grid environment with a PPO agent operating on a state space and actions \{Charge, Discharge, Idle\}, aiming to minimize grid imports via a reward that penalizes costly energy and unsafe SOC states. Key findings show PPO reduces grid electricity import by 13.11% compared to the no-battery baseline and outperforms both Q-learning (1.62% gain) and a rule-based approach (2.56% gain), with performance influenced by solar availability across seasons. This demonstrates the practical potential of DRL-driven battery management for dairy farms, suggesting future extensions to wind generation, regional tests, and comparisons with additional DRL methods for broader applicability.

Abstract

Dairy farms consume a significant amount of electricity for their operations, and this research focuses on enhancing energy efficiency and minimizing the impact on the environment in the sector by maximizing the utilization of renewable energy sources. This research investigates the application of Proximal Policy Optimization (PPO), a deep reinforcement learning algorithm (DRL), to enhance dairy farming battery management. We evaluate the algorithm's effectiveness based on its ability to reduce reliance on the electricity grid, highlighting the potential of DRL to enhance energy management in dairy farming. Using real-world data our results demonstrate how the PPO approach outperforms Q-learning by 1.62% for reducing electricity import from the grid. This significant improvement highlights the potential of the Deep Reinforcement Learning algorithm for improving energy efficiency and sustainability in dairy farms.
Paper Structure (14 sections, 6 equations, 5 figures, 1 algorithm)

This paper contains 14 sections, 6 equations, 5 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background and Related Research
  3. Reinforcement Learning
  4. Proximal Policy Optimization (PPO)
  5. Related Work
  6. Methodology
  7. Environment Design
  8. Data Description
  9. Deep Reinforcement Learning for Battery Management
  10. State Space
  11. Action Space
  12. Reward
  13. Results and Discussion
  14. Conclusion

Figures (5)

  • Figure 1: Overview of the system environment.
  • Figure 2: Comparison of load imported from the grid by different algorithms.
  • Figure 3: Agent behavior for battery charging and discharging during the day.
  • Figure 4: Training reward of implemented PPO algorithm
  • Figure 5: Perforamance comaparision of algorithms.