An Enhanced Deep Reinforcement Learning Algorithm for Decoupling Capacitor Selection in Power Distribution Network Design

Zhang, Ling; Huang, Wen‐Chang; Juang, Jack; Lin, Hank; Tseng, Bin-Chyi; Hwang, Chulsoon

doi:10.1109/emcsi38923.2020.9191512

Cited by 18 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to physical understanding, decap locations closer to the IC are more effective as they provide current return paths with smaller loop inductances. Therefore, the method proposed in [12], [16] is used to quantitatively evaluate the priority of each decap location.…”

Section: A Port Prioritization Based On Physical Inductancementioning

confidence: 99%

“…To solve this problem, a concept of sub-priority for each decap type is proposed. Namely, for each decap type, the subpriorities of the locations that allow this decap type are calculated using the approach proposed in [12]. When all the decap types are allowed at each location, the sub-priority lists for different decap types will be identical to the global priority without considering package size constraints.…”

Section: B Initial Solution Determinationmentioning

confidence: 99%

“…Metaheuristic searching algorithms such as genetic algorithm (GA) [4], [5], [6], [7], [8], [9] and particle swarm optimization (PSO) [10] have been proposed for decap optimization and demonstrate good performance in finding solutions with the minimum number of decaps. Recently, with the popularization of artificial intelligence, machine learning (ML)-based methods, such as reinforcement learning (RL) [11], [12], [13], [14], have been broadly adopted in PI optimization problems. Besides, some algorithms based on human experience and knowledge have also been proposed to quickly determine the decap distribution, such as the Newton-Hessian minimization method [15] and several other approaches [16], [17], [18], [19], [20] with different empirical knowledge and decision-making rules.…”

Section: Introductionmentioning

confidence: 99%

“…Our code is open-source and available at https://github.com/SoFoolish250/ Physics-Assisted-Genetic-Algorithm-PAGA-for-Decap-Optimization. [11], [12], [13], [14] require a significant amount of time for data generation and model training, and the robustness and generalization performance of the RL models are difficult to ensure. The human-knowledge-inspired methods [15], [16], [17], [18], [19], [20] can find feasible decap solutions, but the solution quality cannot be guaranteed for large-scale scenarios.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Novel Physics-Assisted Genetic Algorithm for Decoupling Capacitor Optimization

Jiang,

Zhang,

Tan

et al. 2024

IEEE Trans. Microwave Theory Techn.

View full text Add to dashboard Cite

This article proposes a new physics-assisted genetic algorithm (PAGA) for decoupling capacitor (decap) optimization in power distribution networks (PDNs), which is, by far, the most powerful approach to efficiently minimizing the number of decaps within an enormous search space. In the proposed PAGA method, the priority of the decap ports is first determined based on their physical loop inductances. Then, an initial solution is quickly obtained by placing decaps sequentially on the port with the highest priority. Subsequently, a GA with prior physical knowledge is developed to find better decap solutions progressively. A port removal scheme that eliminates the lowpriority ports and a modified mutation operation that better guides the mutation direction is proposed to accelerate the convergence of the GA. The initial solution and the proposed auxiliary schemes can significantly narrow the search space and incorporate physical knowledge into the GA, thus greatly accelerating the convergence process. Several representative stateof-the-art algorithms and commercial tools are thoroughly compared with the proposed PAGA in different application scenarios. The proposed PAGA shows remarkably better performance in efficiently finding high-quality decap solutions and exhibits strong robustness to handle real-world and largescale problems, which brings decap optimization algorithms to a new benchmark.

show abstract

Section: A Port Prioritization Based On Physical Inductancementioning

confidence: 99%

Section: B Initial Solution Determinationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Physics-Assisted Genetic Algorithm for Decoupling Capacitor Optimization

Jiang,

Zhang,

Tan

et al. 2024

IEEE Trans. Microwave Theory Techn.

View full text Add to dashboard Cite

show abstract

“…Deep Reinforcement Learning-based Methods. Several DRL methods to solve DPP were proposed since the work of [20] using Q-learning and several approaches with convolutional neural network (CNN)-based Q approximator were proposed by [21,22] later. However, their methods were sample inefficient and their trained policies were non-reusable; if the DPP task changes, they must be re-trained.…”

Section: Related Workmentioning

confidence: 99%

Collaborative Distillation Meta Learning for Simulation Intensive Hardware Design

Kim¹,

Kim²,

Kim³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper proposes a novel collaborative distillation meta learning (CDML) framework for simulation intensive hardware design problems. Deep reinforcement learning (DRL) has shown promising performance in various hardware design problems. However, previous works on DRL-based hardware design only dealt with problems with simplified objectives, which are not practical. In fact, the objective evaluation of real-world electrical performance through simulation is costly in terms of both time and computation, making DRL scheme involving extensive reward calculations not suitable. In this paper, we apply the CDML framework to decoupling capacitor placement problem (DPP), one of the significant simulation intensive hardware design problems. The CDML framework consists of a context-based meta learner and collaborative distillation scheme to produce a reusable solver. The context-based meta learner captures the location of probing port (i.e., target circuit block) and improves generalization capability. The collaborative distillation scheme with equivariant label transformation imposes the action-permutation (AP)-equivariant nature of placement problems, which not only improves sample efficiency but also improves generalization capability. Extensive experimental results verified that our CDML outperforms both neural baselines and iterative conventional design methods in terms of real-world objective, power integrity, with zero-shot transfer-ability.Preprint. Under review.

show abstract

Resonance frequency of Vertical SIW based on the artificial neural network

Feng

Xiao

2022

2022 Asia-Pacific International Symposium on Electromagnetic Compatibility (APEMC)

View full text Add to dashboard Cite

An Enhanced Deep Reinforcement Learning Algorithm for Decoupling Capacitor Selection in Power Distribution Network Design

Cited by 18 publications

References 14 publications

A Novel Physics-Assisted Genetic Algorithm for Decoupling Capacitor Optimization

A Novel Physics-Assisted Genetic Algorithm for Decoupling Capacitor Optimization

Collaborative Distillation Meta Learning for Simulation Intensive Hardware Design

Resonance frequency of Vertical SIW based on the artificial neural network

Contact Info

Product

Resources

About