Research Projects
These are selected research projects that I worked on in the last three years. Feel free to contact me to get more details about their methodology, findings, or impact.
Reinforcement Learning for Operational Decisions of Power Systems
The goal of this ongoing research is to design new reinforcement learning algorithms that learn approximately optimal strategies efficiently and robustly, while also being applicable to a variety of real-world problems. To this end, I expand on recent advancements in reinforcement learning algorithms and provide formal regret and probably approximately correct learning guarantees. The developed algorithms are tested on the dynamics demand response problem and are compared with task-specific optimal statistical estimators.
E-Cast: Electricity Demand Forecasting Platform
One of the most important requirements for utility companies is to have an accurate forecast of the demand for the next couple of days. In this project, I worked on a complete pipeline for time series prediction. This includes enhancing a time-series cleaning and imputation algorithms utilizing low-rank approximation by singular value decomposition, and developing and tuning a deep learning model capable of predicting three days-ahead of electricity demand. The algorithms are deployed in a real-time forecasting platform.
Non-Technical Losses Detection in Electrical Grids
Detecting anomalies in electricity consumption, especially from low-resolution signals, is an important and non-trivial task. I developed an anomalies detection algorithm suitable for operating on low-resolution consumption signals by employing a highly nonlinear gradient boosting model. To augment this detection model, I designed a novel synthetic control model that estimates anomalies' magnitude. The two developed models jointly outperform other existing methods.
Modulation Classification for Millimeter Wave over Fiber Channels
The automatic detection of modulation schemes is an essential task in the agile and intelligent communication systems. In this project, I designed autoencoder based modulation classification algorithm capable of operating under the distortions of millimeter-wave optical systems. The distortions considered include fibers nonlinearity, chromatic dispersion, and amplified spontaneous emission. The designed algorithm has been validated through both simulation and experimental work.
Publications
M. Alharbi, A. Alhuseini, A. Ragheb, M. Altamimi, T. Alshawi and S. Alshebeili
​
In this paper, we design an autoencoder-based classification algorithm capable of operating under the distortions of millimeter-wave optical systems. The autoencoder is used for automatic features extraction and classification, and is preceded by a pre-processing step applied to the samples of the input signal. The performance of the system under consideration has been thoroughly investigated by simulation and verified experimentally under different impairments, including fiber chromatic dispersion and amplified spontaneous emission noise. The results are presented in terms of the probability of correct classification for different values of optical signal-to-noise ratio and different lengths of fiber channels. The results from the simulation are a good match to those obtained experimentally.
Meshal Alharbi, Saud Alghumayjan, Mansour Alsaleh, Devavrat Shah, and Ahmad Alabdulkareem
​
This paper proposes a new cost-driven approach for detecting non-technical loss (NTL) of electricity in a resolution-constrained setting. Our proposed method optimizes for the expected economic return. It employs a synthetic control approach and ensemble boosting model that jointly outperform state-of-the-art support vector machine and random forest methods described in the literature. We also used a class-imbalance-agnostic precision-recall metric to validate our approach under various conditions. The whole analysis was conducted using a subset of a dataset of customer accounts from a large utility company that serves a population of over 30 million people. Our proposed method was tested by the utility company and initial results show 75% precision in detecting new NTL cases.
B. Alaskar, A. Alhadlaq, M. Alharbi, S. Alghumayjan, A. Alabdulkareem, M. Alsaleh, and D. Shah
​
In this paper, we propose multiple techniques to enhance day-ahead forecasting models by leveraging independent daily peak and valley (PaV) predictors to ensemble short-term electricity demand forecasters. These ensemble techniques are then incorporated into a novel ensemble recommendation system (ERS). The ERS suggests the most appropriate ensemble technique to enhance the day-ahead predictor's performance while minimizing the computation required for testing multiple ensemble algorithms relative to a single ensemble algorithm. This approach aims to improve the PaV forecasting and enhance the overall accuracy of the day-ahead forecaster, and it can be used with any combination of forecasting models.
In Preparation: Sample Efficient Reinforcement Learning in Continuous Spaces Through State Aggregation
Meshal Alharbi, Mardavij Roozbehani, and Munther Dahleh
In Preparation: Identifying Symbolic Communication in Simulated Environments by Bayesian Modeling
Abdulrahman Alabdulkareem, Meshal Alharbi, Noor Almazroa, Boris Katz, and Andrei Barbu
Class Projects
MIT 6.231: Distributional Reinforcement Learning
The majority of reinforcement learning (RL) literature focuses on modeling and learning the expected random return incurred by RL agents. Operating solely based on expectations has a solid footing in the decision and expected utility theories [Von Neumann and Morgenstern, 1947, Barbera et al., 1999]; Nonetheless, recent works argue in favor of modeling and learning the distribution of the random returns, which gave rise to a sub-field known as distributional reinforcement learning [Bellemareet al., 2017, Barth-Maron et al., 2018, Mavrin et al., 2019, Urpí et al., 2021]. This project aims to explore the theories and methods behind this field.
MIT 6.337: Numerical Methods For System Identification
In this project, we study some of the numerical methods of the identification of linear time-invariant (LTI) systems. LTI systems play an important role in many engineering disciplines as many systems are linear or can be approximated effectively by linear dynamics. The process of retrieving the structure of dynamical systems from observable data is known as system identification, and a popular algorithm for that is the eigensystem realization algorithm (ERA). We study a variant of ERA that uses randomized matrix decomposition approaches to improve numerical efficiency.
Engineering Projects
COVID-19 Agent-Based Simulation and Intervention Recommendation System
Models simulating the spread of infectious diseases are indispensable tools that support the decision-making processes in the event of an epidemic. As part of the KACST response to COVID-19, I developed an agent-based disease spread model capable of simulating novel infectious diseases. I built this disease transmission model in a parallel, vectorized, and computationally efficient implementation. Ongoing work aims to utilize the developed model in policy support and recommendations.
Building Synthetic Aperture Radar
The objective of this project is to design, fabricate, and test a laptop-based radar capable of forming Doppler, range, and synthetic aperture radar (SAR) images. The fabricated radar produces frequency-modulated chirps and operates in the ISM band with a frequency of 2450 MHz. An Arduino Zero is utilized for digital processing, and auxiliary MATLAB functions are implemented to filter and denoise received signals.
Rectangular Microstrip Patch Antenna Simulation
The objective of this project is to investigate the design process of the rectangular microstrip patch antenna (MSA) through computer simulation using MATLAB and CST Studio simulation platforms. The designed antenna operates at 3.8 GHz frequency, it achieved directivity of 8.1 dB, and its input resistance was in the desired range of 50 Ω at the resonance frequency.
