arXiv subjects

Huy Truong Dinh

Publications and source records attributed to Huy Truong Dinh.

5 recordsLinked to original sources

arXiv2025

Link prediction Graph Neural Networks for structure recognition of Handwritten Mathematical Expressions

We propose a Graph Neural Network (GNN)-based approach for Handwritten Mathematical Expression (HME) recognition by modeling HMEs as graphs, where nodes represent symbols and edges capture spatial dependencies. A deep BLSTM network is used for symbol segmentation, recognition, and spatial relation classification, forming an initial primitive graph. A 2D-CFG parser then generates all possible spatial relations, while the GNN-based link prediction model refines the structure by removing unnecessary connections, ultimately forming the Symbol Label Graph. Experimental results demonstrate the effectiveness of our approach, showing promising performance in HME structure recognition.

cs.CV↗

arXiv2022

MILP-based optimal day-ahead scheduling for system-centric CEMS supporting different types of homes and energy trading

Optimal day-ahead scheduling for a system-centric community energy management system (CEMS) is proposed to provide economic benefits and user comfort of energy management at the community level. Our proposed community includes different types of homes and allows prosumers to trade energy locally using mid-market rate pricing. A mathematical model of the community is constructed and the optimization problem of this model is transformed into an MILP problem that can be solved in a short time. By solving this MILP problem, the optimization of the overall energy cost of the community and satisfaction of the thermal comfort at every home are achieved. For comparison, we also establish two different scenarios for the same community: a prosumer-centric CEMS and no CEMS. The simulation results demonstrate that the overall energy cost of the community with the system-centric CEMS is the smallest among the three scenarios and is only half that of the community with the prosumer-centric CEMS. Moreover, by using linear transformation, the computational time of the optimization problem of the proposed system-centric CEMS is only 118.2 s for a 500-home community, which is a short time for day-ahead scheduling of a community.

eess.SY↗

arXiv2021

A Supervised-Learning based Hour-Ahead Demand Response of a Behavior-based HEMS approximating MILP Optimization

The demand response (DR) program of a traditional HEMS usually intervenes appliances by controlling or scheduling them to achieve multiple objectives such as minimizing energy cost and maximizing user comfort. In this study, instead of intervening appliances and changing resident behavior, our proposed strategy for hour-ahead DR firstly learns appliance use behavior of residents and then silently controls ESS and RES to minimize daily energy cost based on its knowledge. To accomplish the goal, our proposed deep neural networks (DNNs) models approximate MILP optimization by using supervised learning. The datasets for training DNNs are created from optimal outputs of a MILP solver with historical data. After training, at each time slot, these DNNs are used to control ESS and RES with real-time data of the surrounding environment. For comparison, we develop two different strategies named multi-agent reinforcement learning-based strategy, a kind of hour-ahead strategy and forecast-based MILP strategy, a kind of day-ahead strategy. For evaluation and verification, our proposed strategies are applied at three different real-world homes with real-world real-time global horizontal irradiation and real-world real-time prices. Numerical results verify that the proposed MILP-based supervised learning strategy is effective in term of daily energy cost and is the best one among three proposed strategies

eess.SY↗

arXiv2021

An Optimal Energy-Saving Home Energy Management Supporting User Comfort and Electricity Selling with Different Prices

In this study, we investigate the operation of an optimal home energy management system (HEMS) with integrated renewable energy system (RES) and energy storage system (ESS) supporting electricity selling functions. A multi-objective mixed integer nonlinear programming model, including RES, ESS, home appliances and the main grid, is proposed to optimize different and conflicting objectives which are energy cost, user comfort and PAR. The effect of different selling prices on the objectives is also considered in detail. We further develop a formula for the lower bound of energy cost to help residents or engineers quickly choose best parameters of RES and ESS for their homes during the installation process. The performance of our system is verified through extensive simulations under three different scenarios of normal, economic, and smart with different selling prices using real data, and simulation results are compared in terms of daily energy cost, PAR, user's convenience and consecutive waiting time to use appliances. Numerical results clearly show that the economic scenario achieves 51.6% reduction of daily energy cost compared to the normal scenario while sacrificing the user's convenience, PAR, and consecutive waiting time by 49%, 132%, and 1 hour, respectively. On the other hand, the smart scenario shows only slight degradation of user's convenience and PAR by 2% and 18%, respectively while achieving 46.4% reduction of daily energy cost and the same level of consecutive waiting time. Furthermore, our simulation results show that a decrease of selling prices has tiny impacts on PAR and user comfort even though the daily energy cost increases.

eess.SY↗

arXiv2020

MILP-based Imitation Learning for HVAC control

To optimize the operation of a HVAC system with advanced techniques such as artificial neural network, previous studies usually need forecast information in their method. However, the forecast information inevitably contains errors all the time, which degrade the performance of the HVAC operation. Hence, in this study, we propose MILP-based imitation learning method to control a HVAC system without using the forecast information in order to reduce energy cost and maintain thermal comfort at a given level. Our proposed controller is a deep neural network (DNN) trained by using data labeled by a MILP solver with historical data. After training, our controller is used to control the HVAC system with real-time data. For comparison, we also develop a second method named forecast-based MILP which control the HVAC system using the forecast information. The performance of the two methods is verified by using real outdoor temperatures and real day-ahead prices in Detroit city, Michigan, United States. Numerical results clearly show that the performance of the MILP-based imitation learning is better than that of the forecast-based MILP method in terms of hourly power consumption, daily energy cost, and thermal comfort. Moreover, the difference between results of the MILP-based imitation learning method and optimal results is almost negligible. These optimal results are achieved only by using the MILP solver at the end of a day when we have full information on the weather and prices for the day.

cs.LG↗