Wen-Sheng Zhao | MSc in Electronics and Technology

Multiobjective Deep Reinforcement Learning Driven Collaborative Optimization of TSV-Based Microchannel and PDN for 3-D ICs

Sun, 01 Feb 2026 00:00:00 +0000

This study introduces a multiobjective deep reinforcement learning (MODRL) framework for the concurrent thermal-hydraulic optimization of the through-silicon-via (TSV) microchannel heat sink (MCHS) embedded in 3-D integrated circuits (3-D ICs) power delivery network (PDN). By exploiting the inherent structural synergy between TSVs and pin-fin MCHS, the proposed method enhances thermal management in high-density 3-D ICs. The framework integrates deep reinforcement learning (RL) with multiobjective optimization and computational fluid dynamics (CFD) simulations, enabling an efficient exploration of the high-dimensional design space to resolve tradeoffs between thermal efficacy and fluidic resistance. Relative to baseline, the optimized design achieves a reduction in maximum chip temperature of up to 3.3% while concurrently lowering the overall pressure drop by 17.2%. Impedance analysis further validates the design’s superiority, showing that the optimized TSV geometry effectively suppresses high-frequency peak impedance. Compared with standard deep reinforcement learning (SDRL) and genetic algorithm (GA), MODRL converges faster by 57.1% and 62.5%, respectively, showing stronger convergence. These results highlight the advantages of the MODRL intelligent optimization framework in design speed and its great potential in driving the development of next-generation 3-D integrated circuits, especially in applications requiring high power density and high reliability.

Hybrid neural network based multi-objective optimal design of hybrid pin-fin microchannel heatsink for integrated microsystems

Wed, 01 Jan 2025 00:00:00 +0000

With the rapid advancement of 2.5D/3D heterogeneous integrated microsystems, the performance and fast intelligent design for thermal management are unprecedentedly required to address the electrical and mechanical reliability issues caused by thermal runaway. In this work, a hybrid neural network, featuring a small dataset requirement, is developed to accelerate the design of the hybrid pin-fin microchannel heatsink. Assisted by the trained machine learning surrogate model and the non-dominated sorting genetic algorithm, a powerful heatsink characterizing power-adaptive cooling capacity is designed. In this study, firstly, a hybrid pin-fin microchannel heatsink is modeled. Then the grid test and simulation validity are carried out. The critical structural parameters correlated with the heat transfer and hydraulic performance are analyzed and identified through numerical simulation. A hybrid neural network serving as a surrogate model, is then developed to map the relationship between key structural parameters and the targeted performance indexes. The hybrid neural network achieves a prediction accuracy of at least 94.33% and outperforms traditional networks, including DNN and CNN, in RMSE, MAE, and RE. It improves by 93.4%, 89.5%, and 87.8% over DNN, and by 91.7%, 93.0%, and 91.9% over CNN. The non-dominated sorting genetic algorithm is performed to explore the Pareto front where the intelligent design of power-adaptive pin-fin layout under uneven thermal profile is achieved. The performance indexes of the optimized heatsink are validated with that from the computational fluid dynamics. Compared with the original structure, it is found that enhancements of 5.58%, 10.76% and 45.73% are achieved in the maximum temperature of high-power heat source, low-power heat source and the pressure drop of microchannel.

Smart cooling: Hydrogel-enhanced adaptive jet impingement utilizing through silicon via for integrated microsystems

Wed, 01 Jan 2025 00:00:00 +0000

In three-dimensional integrated circuits, disparities in power usage across various areas result in inconsistent temperature distributions, potentially jeopardizing system stability and dependability. Although microchannels etched on the back of the chip are frequently employed for cooling, standard designs typically offer a fixed cooling capacity, often failing to effectively target specific hotspots. Furthermore, straight microchannels extending throughout the entire setup can lead to excessive cooling in low-power zones and inadequate cooling in areas of high power consumption. This research introduces an innovative adaptive jet impingement cooling structure that merges hydrogel, jet impingement heat sink (JIHS), and through silicon via (TSV) technologies. The structure incorporates vertical channels and leverages the thermally responsive deformation of hydrogel to facilitate adaptive cooling. This configuration enables the cooler to be strategically positioned at hotspots, dynamically modulating microfluidic injection in reaction to temperature variations. Consequently, it alleviates overcooling in low-power zones while ensuring adequate cooling in hotspots, thereby enhancing thermal uniformity. In comparison to conventional jet impingement sinks, the proposed adaptive model enhances temperature uniformity by 12.21%, decreases thermal spreading resistance by 13%, and only slightly raises the maximum total thermal resistance by 3.08%. The maximum pressure drop experiences a minor increase of just 1.28 kPa.