---

Hi! I am Moinul Morshed Porag Chowdhury. Currently, I am a Postdoc at the New Mexico State University (NMSU) working with Dr. Son Tran. I hold a Ph.D. (2020) and M.Sc. (2016) in Computer Science from the University of Texas at El Paso (UTEP), TX, USA, and a B.Sc. in Computer Science and Engineering from the Bangladesh University of Engineering and Technology (BUET). Before my current appointment, I served at the University of Texas at El Paso as a Research Associate. My research interest focuses on reinforcement learning, artificial intelligence, game theory, and multi-agent systems.

I have more than three years of software development and six years of research experience in multiple IT industries and research institutions. I like to continuously improve my analytical skills and learn about research on emerging trends in the CS field. I am a computer scientist who loves to study agent coordination problems, prediction methods, new market designs/platforms, and novel autonomous bidding/trading strategies. My passion is to work on applications/algorithms that can directly impact making human lives better.

Resume (PDF)» CV (PDF)»

---

News

Jun'20 Joined NMSU as a postdoc.
May'20 Completed my Ph.D.
Jul'18 Gave a talk at IJCAI'18.
Jul'18 Presented my poster at AAMAS'18.
Feb'16 Presented my poster at AAAI'16.
Sep'15 Presented my research at Graduate Research Expo at UTEP.

Back to top »

---

Research Projects

The smart energy grid promises to provide a more intelligent energy infrastructure than the current traditional energy grid by incorporating more advanced sensing capabilities and artificial intelligence for better decision making. It has the potential to improve many problems with our current energy infrastructure. A key feature of the smart grid is to replace humans with autonomous agents that are capable of making decisions in homes, businesses and production facilities to control power delivery, consumption and trading. To achieve this vision and as the grid becomes more decentralized, automated, and capable of providing much greater volumes of sensor data; we need to develop the economic structures and decision-making algorithms to ensure reliable and efficient energy delivery. The question I ask: "What are stronger strategies for artificially intelligent agents (i.e. Brokers) to trade energy in several markets in a profitable way to support dynamically changing smart grid operations?"

Wholesale Bidding Strategy

In a Periodic Double Auction (PDA), there are multiple discrete trading periods for a single type of good. PDAs are commonly used in real-world energy markets to trade energy in specific time slots to balance demand on the power grid. Strategically, bidding in a PDA is complicated because the bidder must predict and plan for future auctions that may influence the bidding strategy for the current auction. We present a general bidding strategy for PDAs based on forecasting clearing prices and using Monte Carlo Tree Search (MCTS) to plan a bidding strategy across multiple time periods. In addition, we present a fast heuristic strategy that can be used either as a standalone method or as an initial set of bids to seed the MCTS policy. We evaluate our bidding strategies using a PDA simulator based on the wholesale market implemented in the Power Trading Agent Competition (PowerTAC) competition. We demonstrate that our strategies outperform state-of-the-art bidding strategies designed for that competition. [Work published in AAAI, AAMAS & IJCAI.]

Retail Market Strategy

Learning stronger retail trading strategies in a dynamic environment using tabular reinforcement learning has been infeasible due to high dimensional continuous state and action spaces. We use deep reinforcement learning (DQN) and empirical game-theoretic analysis (EGTA) to learn stronger strategies from a pool of candidate strategies in an abstract controlled retail market simulation and want our newly learned strategy to perform better than the pool of candidate strategies. The question we ask here is, "How can we learn new stronger strategies using EGTA and Deep RL in the simple isolated simulator from a pool of candidate strategies?" [Currently working on this project.]

Back to top »

---

Publications

h-index: 4   Citations : 40  

Conferences

SPIE'21 "Empirical game-theoretic methods to minimize regret against specific opponents.",Moinul Morshed Porag Chowdhury, Jose Perez, Christopher Kiekintveld, Son Cao Tran, William Yeoh, Enrico Pontelli, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III, International Society for Optics and Photonics (SPIE), April, 2021
IJCAI'18 "Bidding in Periodic Double Auctions Using Heuristics and Dynamic Monte Carlo Tree Search.",Moinul Morshed Porag Chowdhury, Christopher Kiekintveld, Tran Cao Son and William Yeoh., Proceedings of the 27th International Joint Conference on Artificial Intelligence , IJCAI, Stockholm, Sweden — July 13 - 19, 2018
AAMAS'18 "Bidding Strategy for Periodic Double Auctions Using Monte Carlo Tree Search.",Moinul Morshed Porag Chowdhury, Christopher Kiekintveld, Tran Cao Son and William Yeoh., Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS, Stockholm, Sweden, 2018.
AAAI'16 "Predicting Prices in the Power TAC Wholesale Energy Market.",Moinul Morshed Porag Chowdhury. Proceedings of the 30th AAAI Conference on Artificial Intelligence, AAAI, Phoniex, Arizona 2016.

Book Chapter

AMEC "Investigation of Learning Strategies for the SPOT Broker in Power TAC.",Moinul Morshed Porag Chowdhury, Russell Y Folk, Ferdinando Fioretto, Christopher Kiekintveld and William Yeoh., In Agent-Mediated Electronic Commerce. Designing Trading Strategies and Mechanisms for Electronic Markets, 2017.

Workshops

AMEC/TADA'16 "Investigation of Learning Strategies for the SPOT Broker in Power TAC.",Moinul Morshed Porag Chowdhury, Russell Y Folk, Ferdinando Fioretto, Christopher Kiekintveld and William Yeoh., In the International Workshop on Agent Mediated Electronic Commerce and TradingAgents Design and Analysis (AMEC/TADA), 2016.
WES'13 "Proximity-aware ID assignment and routing in Wireless Sensor Network.",Moinul Morshed Porag Chowdhury, Dr. Reaz Ahmed., In the Workshop on Design and Implementation of Emerging Computing Systems (WECS'13), Dhaka, Bangladesh, September 2013

Symposiums

SETS'17 "A Green Auction Mechanism For Prioritizing Renewable Energy Sources In Energy Markets.",Moinul Morshed Porag Chowdhury, Paras Mandal and Christopher Kiekintveld., Southwest Emerging Technology Symposium (SETS), El Paso, USA, 2017.
SETS'16 "BIDDING IN WHOLESALE ENERGY MARKET",Moinul Morshed Porag Chowdhury, Jesus Juarez, Christopher Kiekintveld., Southwest Emerging Technology Symposium (SETS), El Paso, USA, 2016.

Back to top »

---

Experiences

Back to top »

---

Other Projects

Bows and Arrows

A 2D single player shooting game developed in C and C graphics where the player tries to score points by shooting arrows at balloons of various heights, colors, and speeds.

Mail Server

A Java project including a Server which distributes emails with a file attachment option to clients using multi-threading.

Savings Account Management System

A database project, developed in C# and Oracle featuring signing up accounts, storing data, and showing data in grid view from the database.

Graphics Project

Modeling the exterior of Soccer City Football Stadium using OpenGL and C++.

Back to top »

---

Other Links

• Augmented Reality (AR) Science Fair Judge 2021
• PC Member of the international joint conference on Autonomous agents and multiagent systems (AAMAS) 2021
• PC Member of the Association for the Advancement of Artificial Intelligence (AAAI) 2021
• Judge at Sun Country Regional Science and Engineering Fair 2020, 2021
• Reviewer of AICS'20, AAMAS'20, AAAI'19, ACM EC'18, PAAMS'18, AAAI'18, IJCAI'17, IJCAI'15, AMEC/TADA'15, ACM EC'15, AAAI'15
• DrawPraw: I like to draw cartoons and stuffs in my pastimes.
• Gardening is one of my favorite hobbies besides programming :-)
• PowerTAC: I am a contributor to this open source smart grid research platform.

Back to top »

---

Awards and Honors

• Finalist and Honorable Mentions for People’s Choice at UTEP 3 Minute Thesis (3MT) competition 2020.
• Dissertation completion fellowship award from the College of Engineering for the 2019-2020 academic year in UTEP.
• 3^rd place at 2017 and 4^th place at 2019, 2018, and 2016 PowerTAC Competition.
• 3^rd place at 2015 Graduate Student Research Expo in UTEP out of 50 graduate students.
• Tuition fellowship award from the College of Engineering for the 2014-2015 academic year in UTEP.
• Received University Scholarship at Bangladesh University of Engineering and Technology two times.
• Received Dean merit list award in level 1 at Bangladesh University of Engineering and Technology.
• Received Board Merit Scholarship by the Ministry of Education, Bangladesh for the results in Secondary School Certificate examination in Chittagong Board 2003-2005 academic year.
• Received Junior scholarship in high school in 2000, awarded by the Ministry of Education, Bangladesh.

Back to top »

---

Contact

---