Accurate monitoring of the depth of anesthesia (DoA) is essential for effective anesthesia management. Traditionally, anesthesiologists rely on clinical expertise and patient responses, which can vary widely and complicate timely and precise decision-making. This paper introduces a cost-effective and reliable method for assessing DoA using photoplethysmography (PPG) signals. PPG signals, obtained through a noninvasive and affordable method, measure blood volume changes in the microvascular bed of tissue via a simple optical sensor placed on the skin. We evaluated several machine learning models, including XGBoost, LightGBM, CatBoost, random forest, decision tree, SVM, and neural networks. To address the class imbalance in our dataset, we utilized the Synthetic Minority Over-sampling Technique (SMOTE) for balancing. Among these, the LightGBM classifier achieved the highest accuracy of 98.11%. Our study demonstrates that PPG signals provide a dependable and economically viable solution for DoA monitoring, making it particularly suitable for use in smaller healthcare facilities where cost and resource constraints are significant considerations.