Personal research portfolio

Ayodele Benjamin Esan, Ph.D.

AI for Energy Systems | Deep Reinforcement Learning | Microgrid Optimization | Smart Grids | Data Engineering

I develop data-driven decision frameworks that help networked energy systems operate reliably under varying levels of renewable generation and load uncertainty.

Explore research View GitHub

Technical stack

PyPython MMATLAB GGAMS GHOMER SQLSQL AZAzure Cloud BIPower BI DBDatabricks PSPySpark KApache Kafka AFAirflow SFSnowflake

Research Profile

Dr. Ayodele Benjamin Esan works at the intersection of artificial intelligence, optimization, data science, and resilient power systems. His research focuses on practical decision intelligence for microgrids and networked energy systems operating under renewable uncertainty, carbon constraints, and complex coordination requirements.

He combines deep reinforcement learning, multi-agent control, stochastic modeling, mathematical optimization, and data engineering to move ideas from theory into reproducible code. Beyond energy systems, his portfolio also demonstrates applied machine learning, SQL warehousing, analytics-ready pipelines, and cloud-aware data workflows.

Energy & AIMicrogrid EMSDeep reinforcement learningSmart GridsOptimizationData engineeringMachine learning
Ayodele Benjamin Esan in a research workspace
Research, engineering, and data science for intelligent energy systems.

PhD research highlights

Uncertainty-aware intelligence for networked energy systems

Visual summary for Lean multi-agent deep reinforcement learning for uncertainty handling in the energy management of networked microgrids

Applied Energy | 2026

Lean multi-agent deep reinforcement learning for uncertainty handling in the energy management of networked microgrids

A lean multi-agent DRL framework for networked microgrid energy management under uncertainty.

A. B. Esan, H. Shareef, and A. K. ALAhmad, “Lean multi-agent deep reinforcement learning for uncertainty handling in the energy management of networked microgrids,” Applied Energy, vol. 408, Art. no. 127354, 2026. doi:10.1016/j.apenergy.2026.127354

Lean MA-DRLNetworked microgridsUncertainty
Open DOI
Visual summary for Network-aware coordinated multi-microgrid energy management with carbon emission considerations under uncertainty: A multi-agent double deep Q networks approach

Electric Power Systems Research | 2026

Network-aware coordinated multi-microgrid energy management with carbon emission considerations under uncertainty: A multi-agent double deep Q networks approach

A network-aware coordination strategy that brings emissions into multi-microgrid decision-making.

A. B. Esan and H. Shareef, “Network-aware coordinated multi-microgrid energy management with carbon emission considerations under uncertainty: A multi-agent double deep Q networks approach,” Electric Power Systems Research, vol. 254, Art. no. 112683, 2026. doi:10.1016/j.epsr.2025.112683

Carbon-aware EMSMulti-agent DDQNCoordination
Open DOI
Visual summary for Augmented deep reinforcement learning for the energy management of microgrids considering renewable stochastic parameters

Engineering Applications of Artificial Intelligence | 2025

Augmented deep reinforcement learning for the energy management of microgrids considering renewable stochastic parameters

An augmented DRL approach for renewable uncertainty in microgrid energy management.

A. B. Esan and H. Shareef, “Augmented deep reinforcement learning for the energy management of microgrids considering renewable stochastic parameters,” Engineering Applications of Artificial Intelligence, vol. 162, Art. no. 112785, 2025. doi:10.1016/j.engappai.2025.112785

Augmented DRLRenewablesStochastic inputs
Open DOI
Visual summary for Analysis and impact of data-driven hourly probability distribution functions in microgrids day-ahead energy management under uncertainties: A case study in New South Wales, Australia

IET Renewable Power Generation | 2025

Analysis and impact of data-driven hourly probability distribution functions in microgrids day-ahead energy management under uncertainties: A case study in New South Wales, Australia

A data-driven look at hourly PDFs for day-ahead microgrid energy management under uncertainty.

A. B. Esan, H. Shareef, A. K. ALAhmad, and O. Oghorada, “Analysis and impact of data-driven hourly probability distribution functions in microgrids day-ahead energy management under uncertainties: A case study in New South Wales, Australia,” IET Renewable Power Generation, vol. 19, no. 1, Art. no. e70146, 2025. doi:10.1049/rpg2.70146

Hourly PDFsDay-ahead EMSNSW case study
Open DOI

GitHub portfolios

Selected projects with codes

Visual summary for Augmented Deep Reinforcement Learning for Microgrid Energy Management

GitHub project

Augmented Deep Reinforcement Learning for Microgrid Energy Management

Research code and experiments for augmented DRL in renewable-aware microgrid energy management.

Deep RLMicrogrid EMSPython
View repository
Visual summary for Data-Driven Hourly PDF in Day-Ahead Microgrid Energy Management

GitHub project

Data-Driven Hourly PDF in Day-Ahead Microgrid Energy Management

A statistical and optimization workflow for uncertainty modeling in day-ahead microgrid decisions.

Data engineeringPDF modelingOptimization
View repository
Visual summary for 30-Bus Lean Multi-Agent DRL Framework for Networked Microgrids

GitHub project

30-Bus Lean Multi-Agent DRL Framework for Networked Microgrids

A multi-agent DRL project for networked microgrid energy management under uncertain operating conditions.

Multi-agent DRL30-bus networkCoordination
View repository
Visual summary for SQL Data Warehouse Project

GitHub project

SQL Data Warehouse Project

A data engineering project covering warehouse modeling, SQL workflows, and analytics-ready data structures.

SQLETLData warehouse
View repository

Medium blogs

Selected blog articles

Visual summary for Demystifying Value and Policy Iteration Algorithms in Reinforcement Learning: Part 1

Medium article

Demystifying Value and Policy Iteration Algorithms in Reinforcement Learning: Part 1

A practical introduction to dynamic programming concepts in reinforcement learning.

Reinforcement learningValue iterationTeaching
Read article
Visual summary for Demystifying Value and Policy Iteration Algorithms in Reinforcement Learning: Part 2

Medium article

Demystifying Value and Policy Iteration Algorithms in Reinforcement Learning: Part 2

A continuation that deepens the value and policy iteration explanation with applied intuition.

Policy iterationDynamic programmingRL basics
Read article
Visual summary for Reinforcement Learning Application in Power Systems Management: The Unit Commitment Problem

Medium article

Reinforcement Learning Application in Power Systems Management: The Unit Commitment Problem

A bridge between reinforcement learning and operational planning challenges in power systems.

Power systemsUnit commitmentRL applications
Read article
Visual summary for Illuminating the Future: Transforming Africa’s Energy Landscape with Local Energy Markets

Medium article

Illuminating the Future: Transforming Africa’s Energy Landscape with Local Energy Markets

A perspective article on local energy markets and the future of African energy systems.

Local energy marketsAfricaEnergy transition
Read article

Contact

Collaborations, research discussions, and opportunities