A Mixed-Integer Linear Programming Framework for Optimal Design of a Hybrid Solar-Wind-Battery-Fuel Cell-Diesel Microgrid Considering Regulatory Penalties and Reliability Constraints

Amir-Mohammad Golmohammadi

The optimal planning of hybrid renewable energy systems has become increasingly important due to rising energy demand, environmental concerns, and the need for reliable electricity supply in remote and isolated regions. This study presents a comprehensive mixed-integer linear programming (MILP) framework for the optimal design of a hybrid solar–wind–battery–fuel cell–diesel microgrid. The proposed model simultaneously determines the optimal type, size, and operation of system components over the project lifetime while minimizing the equivalent annual cost. Unlike many existing optimization approaches, the framework integrates economic, environmental, and reliability considerations into a unified objective function by incorporating carbon emission penalties, load curtailment penalties, and renewable energy incentive policies. Furthermore, replacement costs and component lifetime degradation are reformulated into linear constraints, enabling the problem to be solved efficiently using exact optimization techniques. Hourly meteorological and load data are employed to accurately capture seasonal and daily variations in renewable energy generation and electricity demand. The optimization model is implemented in GAMS and solved using the CPLEX solver. Different system configurations and regulatory scenarios are evaluated to investigate the influence of diesel generators, battery storage, hydrogen technologies, and government support policies on system performance. The results demonstrate that an appropriately designed hybrid microgrid can substantially improve renewable energy penetration while maintaining system reliability and reducing the overall lifecycle cost. Moreover, regulatory incentive mechanisms significantly increase the economic viability of renewable energy resources and decrease dependence on fossil-fuel-based generation. The proposed MILP framework provides an effective decision-support tool for policymakers, system planners, and investors involved in the development of sustainable hybrid microgrids.

A Neuro-Symbolic Framework for Face Recognition with a SOAR-Based Cognitive Meta-Controller, Parameter-Efficient Transfer Learning (PEFT), and Test-Time Adaptation (TTA)

Azamossadat Nourbakhsh

Face recognition in real-world environments remains challenging due to domain shifts, limited labeled data, decision uncertainty, and constrained computational resources. This paper presents a novel neuro-symbolic framework that combines a SOAR-based cognitive meta-controller, cost-aware reinforcement learning, and domain adaptation to jointly improve recognition accuracy, computational efficiency, and inference latency. A face embedding network is first trained on the source domain and then adapted to the target domain using parameter-efficient fine-tuning (PEFT) and Domain-Adversarial Neural Networks (DANN). To enhance robustness under limited supervision and distribution shifts, the framework further incorporates few-shot learning and test-time adaptation (TTA). The proposed meta-controller is formulated as a Markov Decision Process (MDP), enabling dynamic allocation of computational resources based on image quality, uncertainty estimation, and recognition status. Symbolic knowledge encoded in the SOAR architecture guides the reinforcement learning policy through a neuro-symbolic gating mechanism, improving both interpretability and decision consistency. Experiments on the IJB-C and MegaFace benchmarks demonstrate significant improvements in face recognition and open-set recognition performance, while PEFT reduces trainable parameters by more than 95% without increasing inference latency. Overall, the proposed framework offers an accurate, adaptive, interpretable, and computationally efficient solution for real-world face recognition applications.

Iranian Journal of Operations Research

A Mixed-Integer Linear Programming Framework for Optimal Design of a Hybrid Solar-Wind-Battery-Fuel Cell-Diesel Microgrid Considering Regulatory Penalties and Reliability Constraints

A Neuro-Symbolic Framework for Face Recognition with a SOAR-Based Cognitive Meta-Controller, Parameter-Efficient Transfer Learning (PEFT), and Test-Time Adaptation (TTA)