Efficient Design Optimization of High-Performance MEMS Based on a Surrogate-Assisted Self-Adaptive Differential Evolution

Akinsolu, Mobayode O.; Liu, Bo; Lazaridis, Pavlos I.; Mistry, Keyur K.; Mognaschi, Maria Evelina; Barba, Paolo Di; Zaharis, Zaharias D.

doi:10.1109/access.2020.2990455

Cited by 11 publications

(6 citation statements)

References 53 publications

(86 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, the algorithm with the DNN surrogate model is applied to solve the OEM problem. The Differential Evolution (DE) algorithm which is guaranteed as one of the best tools of metaheuristic algorithms, is employed to solve many problems according to [40]- [43]. To verify the performance of the DDPG, the OEM result using the DDPG is compared with the DE.…”

Section: Dnn Surrogate-assisted Ddpg Verificationmentioning

confidence: 99%

See 1 more Smart Citation

Electric Distribution Network With Multi-Microgrids Management Using Surrogate-Assisted Deep Reinforcement Learning Optimization

2022

View full text Add to dashboard Cite

Increasing of electric vehicle demand and uncertain electricity generation from solar photovoltaics lead to poor reliability in the Distribution Network (DN). MicroGrids (MG) connecting to the DN with suitable energy trading is an effective way to solve this issue. However, suitable energy trading considering grid constraints with a low computational burden is a challenge for solving Optimal Energy Management (OEM). Therefore, this paper proposes an OEM using a surrogate which is modeled based on a Deep Neural Network to assist the Deep Reinforcement Learning Optimization for reducing the computational burden. The proposed method is applied to a bi-level OEM for multi-MGs connected in the DN with real-time pricing consideration, represented as the proposed strategy. The surrogate is modeled to predict the power system parameters of the MG based on probabilistic power flow, whereas a deterministic power flow is applied to evaluate the parameters of DN. To validate and demonstrate the proposed method and strategy, the modified IEEE-33 test feeder and a residential distribution system which are defined as the DN and MG, respectively are used to test. Simulation results show that the proposed method can reduce computational burden by 89.23% compared with the Differential Evolution algorithm. Moreover, the proposed strategy provides the optimal purchased energy price of DN offering to each MG which can reduce the cost of energy purchased from the main grid resulting in lower operating cost of DN.

show abstract

Section: Dnn Surrogate-assisted Ddpg Verificationmentioning

confidence: 99%

“…This method can reduce the computational burden for the OEM process. Also, the performance of the proposed method is compared with one of the best tools of metaheuristic algorithms named Differential Evolution which was employed to solve many problems in the past [40]- [43].…”

Section: Introductionmentioning

confidence: 99%

Electric Distribution Network With Multi-Microgrids Management Using Surrogate-Assisted Deep Reinforcement Learning Optimization

2022

View full text Add to dashboard Cite

show abstract

“…The mutated part is obtained by the difference of two randomly selected individuals from the parent population, except for the aforementioned parent individual. The individual obtained by the mutation operation is the mutation vector [31]. In addition, Price, Storn, and other studies have proposed various strategies, including DE/best/1 and DE/rand-to-best/1 [29,32].…”

Section: Mutation Operationmentioning

confidence: 99%

“…The DE optimization algorithm has the problems [31] of search stagnation and premature convergence in the application. The main reasons for this are that [33] (1) strict constraints may create an extremely narrow region in which the optimal objective function value exists, and that (2) it is of great significance to have a high searchability to leave out the local optimum when searching for the best results.…”

Section: Improved Differential Evolution Algorithmmentioning

confidence: 99%

Structural Design and Optimization of a Resonant Micro-Accelerometer Based on Electrostatic Stiffness by an Improved Differential Evolution Algorithm

Huang

Qin

et al. 2021

Micromachines

View full text Add to dashboard Cite

This study designed an in-plane resonant micro-accelerometer based on electrostatic stiffness. The accelerometer adopts a one-piece proof mass structure; two double-folded beam resonators are symmetrically distributed inside the proof mass, and only one displacement is introduced under the action of acceleration, which reduces the influence of processing errors on the performance of the accelerometer. The two resonators form a differential structure that can diminish the impact of common-mode errors. This accelerometer realizes the separation of the introduction of electrostatic stiffness and the detection of resonant frequency, which is conducive to the decoupling of accelerometer signals. An improved differential evolution algorithm was developed to optimize the scale factor of the accelerometer. Through the final elimination principle, excellent individuals are preserved, and the most suitable parameters are allocated to the surviving individuals to stimulate the offspring to find the globally optimal ability. The algorithm not only maintains the global optimality but also reduces the computational complexity of the algorithm and deterministically realizes the optimization of the accelerometer scale factor. The electrostatic stiffness resonant micro-accelerometer was fabricated by deep dry silicon-on-glass (DDSOG) technology. The unloaded resonant frequency of the accelerometer resonant beam was between 24 and 26 kHz, and the scale factor of the packaged accelerometer was between 54 and 59 Hz/g. The average error between the optimization result and the actual scale factor was 7.03%. The experimental results verified the rationality of the structural design.

show abstract

“…Therefore, more and more researchers have devoted themselves to the research of intelligent optimization algorithms for large-scale and complex problems. For example, meta-heuristic algorithms have good performance on many large-scale and real-world engineering optimization problems, e.g., electric vehicle field [15], electromechanical field [16], mobile robotic filed [17], multimodal optimization problem [18]. The meta-heuristic algorithms have also been proposed to solve the problem of resource allocation in wireless networks.…”

Section: Introduction 1motivationmentioning

confidence: 99%

DE based Resource Allocation for D2D assisted NOMA Systems

Jia

Tian

et al. 2023

Preprint

View full text Add to dashboard Cite

The explosion of wireless network services forces us to seek new technologies and resource allocation schemes. Three joint resource allocation frameworks for device-to-device (D2D) communication in non-orthogonal multiple access (NOMA) assisted multi-cell systems are proposed. D2D can reduce the access pressure of base station (BS) equipment, and NOMA can multiplex network spectrum resources, and the integration of them can further improve the performance of multi-cell networks. We investigate the joint user association, resource block (RB) assignment, and power allocation problem in multi-cell systems with the aim of maximizing the sum rate of D2Ds. To solve this mixed-integer non-linear programming (MINLP) problem, we propose three differential evolution (DE) algorithms. First, we invoke the coevolution DE-based resource allocation (CDRA) framework which encodes the RB assignment and power allocation into the same individual for evolution. Second, we invoke the iteration-combining DE-based resource allocation (IDRA) framework, which adopts two-steps DE algorithm to solve optimal power allocation and RB assignment scheme iteratively. Last, we invoke the power-repairing DE-based resource allocation (PDRA) framework, which combines a similar joint RB assignment and power allocation as CDRA, where power repair is added after each iteration. Simulation results demonstrate that: \romannumeral1) the integration of D2D and NOMA techniques is capable of enhancing the achievable sum rate of D2Ds; \romannumeral2) the proposed three proposed frameworks for multi-cell NOMA networks can effectively optimize the objective function. However, comparing with CDRA and IDRA, PDRA performs better in terms of convergence speed and maximum D2D rate.

show abstract

Efficient Design Optimization of High-Performance MEMS Based on a Surrogate-Assisted Self-Adaptive Differential Evolution

Cited by 11 publications

References 53 publications

Electric Distribution Network With Multi-Microgrids Management Using Surrogate-Assisted Deep Reinforcement Learning Optimization

Electric Distribution Network With Multi-Microgrids Management Using Surrogate-Assisted Deep Reinforcement Learning Optimization

Structural Design and Optimization of a Resonant Micro-Accelerometer Based on Electrostatic Stiffness by an Improved Differential Evolution Algorithm

DE based Resource Allocation for D2D assisted NOMA Systems

Contact Info

Product

Resources

About