Between green hills and green bills: Unveiling the green shades of sustainability and burden shifting through multi-objective optimization in Swiss energy system planning.

The Paris Agreement is the first-ever universally accepted and legally binding agreement on global climate change. It is a bridge between today's and climate-neutrality policies and strategies before the end of the century. Critical to this endeavor is energy system modeling, which, while adept at devising cost-effective carbon-neutral strategies, often overlooks the broader environmental and social implications. This study introduces an innovative methodology that integrates life-cycle impact assessment indicators into energy system modeling, enabling a comprehensive assessment of both economic and environmental outcomes. Focusing on Switzerland's energy system as a case study, the model reveals that optimizing key environomic indicators can lead to significant economic advantages, with system costs potentially decreasing by 15% to 47% by minimizing potential impacts from the current system still operating with fossil technologies to an alternative only relying on renewable and where the impact are mainly related to the construction of the infrastructure. However, a system optimized solely for economic efficiency, despite achieving 63% reduction in carbon footprint compared to 2020, shows a potential risk of burden shift to other environmental issues. The adoption of multi-objective optimization in this approach nuances the exploration of the complex interplay between environomic objectives and technological choices. The results illuminate pathways towards more holistically optimized energy systems, effectively addressing trade-offs across environmental problems and enhancing societal acceptance of the solutions to this century's defining challenge.

A Multi-Layer Techno-Economic-Environmental Energy Management Optimization in Cooperative Multi-Microgrids with Demand Response Program and Uncertainties Consideration.

This paper presents a multi-layer, multi-objective (MLMO) optimization model for techno-economic-environmental energy management in cooperative multi-Microgrids (MMGs) that incorporates a Demand Response Program (DRP). The proposed MLMO approach simultaneously optimizes operating costs, MMG operator benefits, environmental emissions, and MMG dependency. This paper proposed a new hybrid ε-lexicography-weighted-sum that eliminates the need to normalize or scalarize objectives. The first layer of the model schedules MMG resources with DRP to minimize operating costs (local generation and power transactions with the utility grid) and maximize MMG profit. The second layer achieves the environmental operation of the MMG, while the third layer maximizes MMG reliability. This paper also proposed a new application of a recently developed enhanced equilibrium optimizer (EEO) for solving the three-layer EM problem. In addition, the uncertainties of solar power generation, wind power generation, load demand, and energy prices are considered based on the probabilistic 2m + 1 Point estimation method (PEM) approach. Three case studies are presented to verify the proposed MLMO approach on an MMG test system. In Case I, a deterministic EM is solved to simulate the MMG as a single layer to minimize costs and maximize benefits through DRP, while Case II solves the MLMO optimization problem. Simulation results show that the proposed MLMO technique reduces environmental emissions by 2.45% and 3.5% in its optimization layer and at the final layer, respectively. The independence index is also enhanced by 2.49% and 4.8% in its layer only and as a total increase, respectively. Case III is for the probabilistic EM simulation; due to the uncertain variables effect, the mean value in this case is increased by about 2.6% over Case I.

Bi-level expansion planning of power system considering wind farms based on economic and technical objectives of transmission system operator.

Planning for the expansion of generation and transmission infrastructure, with a focus on integrating wind farms is presented in this study according to the goals of economic efficiency, operational performance, security, and reliability of the transmission system operator. The approach incorporates a bi-level optimization framework, with the upper level outlining the formulation of power system expansion planning to reduce construction and operational costs while adhering to the investment budget limits. In the lower-level model, which economic reliable-secure functioning is formulated for the transmission network. The objective function of the problem aims to minimize operational costs, energy losses, and anticipated energy not supplied, and the voltage security index. The constraints of this problem include AC optimal power flow model, security, and reliability limits. Scheme extracts a convex-linear model for the formulation using the conventional linearization technique. Pareto optimization driven by the aggregation of weighted functions results in a single-objective framework for the lower-level problem, and the Karush-Kuhn-Tucker technique presents a single-level model for the scheme. The approach utilizes stochastic optimization has been adopted to model load, wind farms, and network equipment availability uncertainties. Finally, the study cases yielded numerical findings that showcase the efficacy of the proposed scheme in achieving the desired economic, operational, security, and reliability status within the transmission network. This is particularly true in situations where there is appropriate generation and transmission expansion.

Optimal energy management via day-ahead scheduling considering renewable energy and demand response in smart grids.

The energy optimization in smart power grids (SPGs) is crucial for ensuring efficient, sustainable, and cost-effective energy management. However, the uncertainty and stochastic nature of distributed generations (DGs) and loads pose significant challenges to optimization models. In this study, we propose a novel optimization model that addresses these challenges by employing a probabilistic method to model the uncertain behavior of DGs and loads. Our model utilizes the multi-objective wind-driven optimization (MOWDO) technique with fuzzy mechanism to simultaneously address economic, environmental, and comfort concerns in SPGs. Unlike existing models, our approach incorporates a hybrid demand response (HDR), combining price-based and incentive-based DR to mitigate rebound peaks and ensure stable and efficient energy usage. The model also introduces battery energy storage systems (BESS) as environmentally friendly backup sources, reducing reliance on fossil fuels and promoting sustainability. We assess the developed model across various distinct configurations: optimizing operational costs and pollution emissions independently with/without DR, optimizing both operational costs and pollution emissions concurrently with/without DR, and optimizing operational costs, user comfort, and pollution emissions simultaneously with/without DR. The experimental findings reveal that the developed model performs better than the multi-objective bird swarm optimization (MOBSO) algorithm across metrics, including operational cost, user comfort, and pollution emissions.

Optimal Design of a Sensor Network for Guided Wave-Based Structural Health Monitoring Using Acoustically Coupled Optical Fibers.

Guided waves (GW) allow fast inspection of a large area and hence have received great interest from the structural health monitoring (SHM) community. Fiber Bragg grating (FBG) sensors offer several advantages but their use has been limited for the GW sensing due to its limited sensitivity. FBG sensors in the edge-filtering configuration have overcome this issue with sensitivity and there is a renewed interest in their use. Unfortunately, the FBG sensors and the equipment needed for interrogation is quite expensive, and hence their number is restricted. In the previous work by the authors, the number and location of the actuators was optimized for developing a SHM system with a single sensor and multiple actuators. But through the use of the phenomenon of acoustic coupling, multiple locations on the structure may be interrogated with a single FBG sensor. As a result, a sensor network with multiple sensing locations and a few actuators is feasible and cost effective. This paper develops a two-step methodology for the optimization of an actuator-sensor network harnessing the acoustic coupling ability of FBG sensors. In the first stage, the actuator-sensor network is optimized based on the application demands (coverage with at least three actuator-sensor pairs) and the cost of the instrumentation. In the second stage, an acoustic coupler network is designed to ensure high-fidelity measurements with minimal interference from other bond locations (overlap of measurements) as well as interference from features in the acoustically coupled circuit (fiber end, coupler, etc.). The non-sorting genetic algorithm (NSGA-II) is implemented for finding the optimal solution for both problems. The analytical implementation of the cost function is validated experimentally. The results show that the optimization does indeed have the potential to improve the quality of SHM while reducing the instrumentation costs significantly.

GRNMOPT: Inference of gene regulatory networks based on a multi-objective optimization approach.

BACKGROUND AND OBJECTIVE: The reconstruction of gene regulatory networks (GRNs) stands as a vital approach in deciphering complex biological processes. The application of nonlinear ordinary differential equations (ODEs) models has demonstrated considerable efficacy in predicting GRNs. Notably, the decay rate and time delay are pivotal in authentic gene regulation, yet their systematic determination in ODEs models remains underexplored. The development of a comprehensive optimization framework for the effective estimation of these key parameters is essential for accurate GRN inference. METHOD: This study introduces GRNMOPT, an innovative methodology for inferring GRNs from time-series and steady-state data. GRNMOPT employs a combined use of decay rate and time delay in constructing ODEs models to authentically represent gene regulatory processes. It incorporates a multi-objective optimization approach, optimizing decay rate and time delay concurrently to derive Pareto optimal sets for these factors, thereby maximizing accuracy metrics such as AUROC (Area Under the Receiver Operating Characteristic curve) and AUPR (Area Under the Precision-Recall curve). Additionally, the use of XGBoost for calculating feature importance aids in identifying potential regulatory gene links. RESULTS: Comprehensive experimental evaluations on two simulated datasets from DREAM4 and three real gene expression datasets (Yeast, In vivo Reverse-engineering and Modeling Assessment [IRMA], and Escherichia coli [E. coli]) reveal that GRNMOPT performs commendably across varying network scales. Furthermore, cross-validation experiments substantiate the robustness of GRNMOPT. CONCLUSION: We propose a novel approach called GRNMOPT to infer GRNs based on a multi-objective optimization framework, which effectively improves inference accuracy and provides a powerful tool for GRNs inference.

An extended goal programming approach with piecewise penalty functions for uncertain supplier-material selection problem in cardboard box manufacturing systems.

In this study a real case multi-objective material and supplier selection problem in cardboard box production industries is studied. This problem for the first time optimizes the objective functions such as total wastage amounts remained from all raw sheets, total costs of the system including purchasing cost and transportation cost (including fixed and variable costs) of the raw sheets, and total overplus of produced cardboard boxes. To be closer to the real situations, as a novelty, the problem is formulated in belief-degree-based uncertain environment with normal distribution where this type of uncertainty applies the ideas of experts. A solution approach including two steps is proposed to solve the problem. In the first step, the proposed uncertain formulation is converted to a crisp form using a typical chance constrained programming scheme. In the second step, a new goal programming approach containing a piecewise penalty function is developed in order to solve the obtained multi-objective crisp formulation. In this approach, based on the ideas of experts, multiple goals are considered with different penalty values. A case study from cardboard box industries is considered to evaluate the proposed formulations and solution approach. According to the obtained results, the proposed solution approach is compared to similar approaches of the literature and its efficiency is studied.

Optimizing irrigation and nitrogen application strategies to improve sunflower yield and resource use efficiency in a cold and arid oasis region of Northwest China.

In arid regions, water scarcity, land degradation and groundwater pollution caused by excessive fertilization are the main constraints to sustainable agricultural production. Optimizing irrigation and fertilizer management regime is an effective means of improving crop water and fertilizer productivity as well as reducing negative impacts on the ecosystem. In order to investigate the effects of different irrigation and nitrogen (N) fertilizer rates on sunflower growth, yield, and water and N use efficiency, and to determine the optimal water and N management strategy, a two-year (2021 and 2022) field experiment with under-mulched drip irrigation was conducted in the Hexi Oasis area of Northwest China. The experiment design comprised three irrigation levels (W1, 55%-65% FC, where FC represents field water capacity; W2, 65%-75% FC; W3, 75%-85% FC) and three N application levels (N1, 120 kg ha-1; N2, 180 kg ha-1; N3, 240 kg ha-1), resulting in a total of nine treatments. The findings indicated that increasing irrigation and N application rates led to improvements in leaf area index (15.39%-66.14%), dry matter accumulation (11.43%-53.15%), water consumption (ET, 1.63%-42.90%) and sunflower yield (6.85%-36.42%), in comparison to the moderate water deficit and low N application (W1N1) treatment. However, excess water and N inputs did not produce greater yield gains and significantly decreased both water use efficiency (WUE) and nitrogen partial factor productivity (NPFP). Additionally, a multiple regression model was developed with ET and N application as explanatory variables and yield, WUE and NPFP as response variables. The results based on the regression model combined with spatial analysis showed that an ET range of 334.3-348.7 mm and N application rate of 160.9-175.3 kg ha-1 achieved an optimal balance between the multiple production objectives: yield, WUE and NPFP. Among the different irrigation and N management strategies we evaluated, we found that W2N2 (65%-75% FC and 180 kg N ha-1) was the most fruitful considering yield, resource use efficiency, etc. This result can serve as a theoretical reference for developing appropriate irrigation and N fertilization regimes for sunflower cultivation in the oasis agricultural area of northwest China.

Process Parameters Optimization and Numerical Simulation of AlCoCrFeNi High-Entropy Alloy Coating via Laser Cladding.

The use of laser cladding technology to prepare coatings of AlCoCrFeNi high-entropy alloy holds enormous potential for application. However, the cladding quality will have a considerable effect on the properties of the coatings. In this study, considering the complex coupling relationship between cladding quality and the process parameters, an orthogonal experimental design was employed, with laser power, scanning speed, and powder feed rate as correlation factor variables, and microhardness, dilution rate, and aspect ratio as characteristic variables. The experimental data underwent gray correlation analysis to determine the effect of various process parameters on the quality of cladding. Then, the NSGA-II algorithm was used to establish a multi-objective optimization model of process parameters. Finally, the ANSYS Workbench simulation model was employed to conduct numerical simulations on a group of optimized process parameters and analyze the change rule of the temperature field. The results demonstrate that the laser cladding coating of AlCoCrFeNi high-entropy alloy with the single pass is of high quality within the determined orthogonal experimental parameters. The powder feed rate exerts the most significant influence on microhardness, while laser power has the greatest impact on dilution rate, and scanning speed predominantly affects aspect ratio. The designed third-order polynomial nonlinear regression model exhibits a high fitting accuracy, and the NSGA-II algorithm can be used for multi-objective optimization to obtain the Pareto front solution set. The numerical simulation results demonstrate that the temperature field of AlCoCrFeNi high-entropy alloy laser cladding exhibits a "comet tail" phenomenon, where the highest temperature of the molten pool is close to 3000 °C. The temperature variations in the molten pool align with the features of laser cladding technology. This study lays the groundwork for the widespread application of laser cladding AlCoCrFeNi high-entropy alloy in surface engineering, additive manufacturing, and remanufacturing. Researchers and engineering practitioners can utilize the findings from this research to judiciously manage processing parameters based on the results of gray correlation analysis. Furthermore, the outcomes of multi-objective optimization can assist in the selection of appropriate process parameters aligned with specific application requirements. Additionally, the methodological approach adopted in this study offers valuable insights applicable to the exploration of various materials and diverse additive manufacturing techniques.

Numerical study on the forward and inverse problems of the mobile pump truck frame.

Aiming at the requirements of strong mobility and high flexibility of rescue and relief mobile pump trucks, this paper designs a new type of mobile pump truck frame based on existing mobile vehicle frame models. The materials used for the frame are 40Cr and Q235, and the finite element method is utilized to carry out static mechanical analysis and dynamic characteristic analysis. Simultaneously utilizing topology optimization and multi-objective genetic algorithm to optimize the design of the frame structure. The results show that the optimized pump truck frame can meet the strength design requirements of four typical working conditions: full load bending, full load torsion, emergency turning and emergency braking, while avoiding resonance phenomena caused by road surface and diesel engine vibration. Compared with the original frame model, the weight of the optimized frame is reduced by 87.88 kg, with a weight reduction rate of 10.89%, realizing the lightweight design requirements.

Finite element analysis and surrogate-optimized design of a nature-inspired auxetic stent.

Prior studies have revealed that the structural design of stents is critical to reducing some of the alarming post-operative complications associated with stent-related intervention. However, the technical search for stents that guarantee robustness against stent-induced post-intervention complications remains an open problem. Along this objective, this study investigates a re-entrant auxetic stent's structural response and performance optimizations. In pursuit of the goal, a nonlinear finite element analysis (FEA) is employed to uncover metrics characterizing the auxetic stent's mechanical behavior. Subsequently, the non-dominated sorting genetic algorithm (NSGA-II) is implemented to simultaneously minimize the stent's von Mises stress and the elastic radial recoil (ERR). Results from the FEA revealed a tight connection between the stent's response and the features of the base auxetic building block (the rib length, strut width, and the re-entrant angle). It is observed that the auxetic stent exhibits a much lower ERR. Besides, larger values of its rib length and re-entrant angle are noticed to favor smaller von Mises stress. The Pareto-optimal front from the NSGA-II-based optimization scheme revealed a sharp trade-off in the simultaneous minimization of the von Mises stress and the ERR. Moreover, an optimal combination of the auxetic unit cell's geometric parameters is found to yield a much lower maximum von Mises stress of ≈403 MPa and ERR of ≈0.4%.

Multi-Objective Optimization and Mechanical Properties Analysis of Steel-PVA Hybrid Fiber-Reinforced Cementitious Composites.

When steel fiber and PVA fiber produced in China and PVA fiber made in Japan are prepared according to the appropriate proportions, the mechanical properties of hybrid fiber-reinforced cementitious composites (HFRCC) are better, which is beneficial to cost control and has wide application prospects. The effects of the volume content of steel fibers and the volume substitution rate of PVA fibers on the tensile strength, compressive strength, and flexural strength of HFRCC were analyzed using the factor optimization method and principal component analysis (PCA). Through the principal component analysis of HFRCC, a mathematical model for comprehensive performance evaluation was established, and a multi-objective optimization was carried out. The results show that compared with the matrix, the tensile strength, compressive strength, and flexural strength of concrete increase significantly when the volume content of steel fibers is 0.2-0.4% and the volume substitution rate of domestically produced PVA fibers in China or PVA fibers produced in Japan is 50-100%. The maximum cost reduction is 88.25%, and the strength index of HFRCC can reach the optimum; the weights of each factor on the performance of HFRCC were obtained through mathematical statistics. Combined with a variable correlation analysis, these indicators should be noted when optimizing the performance of HFRCC. The research results can provide a basis for the preparation of HFRCC.

Optimization Design of Submerged-Entry-Nozzle Structure Using NSGA-II Genetic Algorithm in Ultra-Large Beam-Blank Continuous-Casting Molds.

To achieve uniform cooling and effective homogenization control in ultra-large beam-blank molds necessitates the optimization of submerged-entry-nozzle (SEN) structures. This study employed computational fluid dynamic (CFD) modeling to investigate the impact of two-port and three-port SEN configurations on fluid flow characteristics, free-surface velocities, temperature fields, and solidification behaviors. Subsequently, integrating numerical simulations with the non-dominated sorting genetic algorithm II (NSGA-II) and metallurgical quality-control expertise facilitated the multi-objective optimization of a three-port SEN structure suitable for beam-blank molds. The optimized parameters enabled the three-port SEN to deliver molten steel to the meniscus at an appropriate velocity while mitigating harmful effects such as SEN port backflow, excessive surface temperature differences, and shell thickness reduction due to fluid flow. The results indicated that the three-port SEN enhanced the molten-steel flow pattern and mitigated localized shell thinning compared with the two-port SEN. Additionally, the optimized design (op2) of the three-port SEN exhibited reduced boundary layer separation and superior fluid dynamics performance over the initial three-port SEN configuration.

Performance-constrained multi-objective optimization of antennas for miniaturization design.

The miniaturization of antennas is crucial as it improves the integration of wireless communication system. In order to achieve miniaturization of antennas, a performance-constrained multi-objective optimization method (PCMOM) considering the size and return loss is proposed. In the PCMOM method, an optimization strategy based on a multi-port network model is introduced, enabling the formation of antennas with various structures. Furthermore, we integrate the constraint of return loss performance into the non-dominated sorting genetic algorithm II (NSGA-II), eliminating solutions that do not meet performance requirements. Three pixel antennas are designed using the PCMOM method and two of them are fabricated. Experimental results demonstrate that the proposed PCMOM method can effectively address the complex trade-off issues in antenna miniaturization design.

Multi-objective optimization design of low-power-driven, large-flux, and fast-response three-stage valve.

Intrinsically safe solenoids drive solenoid valves in coal mining equipment. The low power consumption of these solenoids limits the response time of the solenoid valves. Additionally, the low viscosity and high susceptibility to dust contamination of the emulsion fluid often lead to leakage and sticking of hydraulic valves. This study proposes a low-power-driven, large-flux, fast-response three-stage valve structure with an internal displacement feedback device to address these issues. The critical parameters of the valve were optimized using a novel multi-objective optimization algorithm. A prototype was manufactured based on the obtained parameters and subjected to simulation and experimental verification. The results demonstrate that the valve has an opening time of 21 ms, a closing time of 12 ms, and a maximum flow rate of approximately 225 L/min. The driving power of this structure is less than 1.2 W. By utilizing this valve for hydraulic cylinder control, a positioning accuracy of ± 0.15 mm was achieved. The comparative test results show that the proposed structural control error fluctuation is smaller than that of the 3/4 proportional valve.

Efficient production of pullulan by Aureobasidium pullulans using a multi-objective optimization strategy with orthogonal experimental design coupling artificial neural network and genetic algorithm.

Efficient pullulan production has long been a central research focus. This study used maltodextrin as the carbon source for pullulan production by Aureobasidium pullulans fermentation. A hybrid optimization approach, integrating orthogonal experimental design (OED), backpropagation artificial neural network (BP-ANN), and elite strategy non-dominated sequential genetic algorithm-II (NSGA-II), was developed. Range analysis based on OED revealed that MgSO4·7H2O significantly affects production but less impacts molecular weight, while pH notably influences molecular weight with a lesser effect on production, underscoring the need for multi-objective optimization. The BP-ANN model showed strong predictive capabilities, with goodness-of-fit values of 0.984 and 0.980 for production and molecular weight, respectively. Using this model as the fitness function for the optimization algorithm enhanced efficiency. Taking cost factors into account, the BP-ANN-NSGA-II algorithm identified the optimal fermentation medium conditions, resulting in a 6.89 % increase in production, a 368.97 % increase in molecular weight, and a 42.49 % reduction in cost. The maximum comprehensive optimization efficiency is 63.73 %, and the multi-objective optimization is better than the single objective optimization. This method significantly guides the improvement of pullulan fermentation optimization efficiency.

Multi-objective resistance-capacitance optimization algorithm: An effective multi-objective algorithm for engineering design problems.

Focusing on practical engineering applications, this study introduces the Multi-Objective Resistance-Capacitance Optimization Algorithm (MORCOA), a new approach for multi-objective optimization problems. MORCOA uses the transient response behaviour of resistance-capacitance circuits to navigate complex optimization landscapes and identify global optima when faced with many competing objectives. The core approach of MORCOA combines a dynamic elimination-based crowding distance mechanism with non-dominated sorting to generate an ideal and evenly distributed Pareto front. The algorithm's effectiveness is evaluated through a structured, three-phase analysis. Initially, MORCOA is applied to five benchmark problems from the ZDT test suite, with performance assessed using various metrics and compared against state-of-the-art multi-objective optimization techniques. The study then expands to include seven problems from the DTLZ benchmark collection, further validating MORCOA's effectiveness. The final phase involves applying MORCOA to six real-world constrained engineering design problems. Notably, the optimization of a honeycomb heat sink, which is crucial in thermal management systems, is a significant part of this study. This phase uses a range of performance measures to assess MORCOA's practical application and efficiency in engineering design. The results highlight MORCOA's robustness and efficiency in both real-world engineering applications and benchmark problems, demonstrating its superior capabilities compared to existing algorithms. The effective use of MORCOA in real-world engineering design problems indicates its potential as an adaptable and powerful tool for complex multi-objective optimization tasks.

Multi-objective constraints for path planning in screw fixation of scaphoid fractures.

PURPOSE: Scaphoid fractures, a common type of clinical fracture, often require screw placement surgery to achieve optimal therapeutic outcomes. Path planning algorithms can avoid more risks and have vital potential for developing precise and automatic surgeries. Despite the success of surgical path planning algorithms, automatic path planning for scaphoid fractures remains challenging owing to the complex bone structure and individual variations. METHODS: Thus, we propose a Multi-objective constrained Path planning Algorithm (MPA) for fracture screw placement, which includes the identification of the center of the fracture surface. Further, three constraint conditions were introduced to eliminate infeasible paths, followed by adding three objectives to the remaining paths for more accurate planning. Finally, the Nondominated Sorting Genetic Algorithms (NSGA)-II algorithm was used to optimize the surgical paths. RESULTS: We defined the vertical compression distance (VCD), a common observation index in clinics. The experiments show that the average VCD of the MPA paths is measured at 23.88 mm, outperforming the clinical planning paths by 21.71 mm. Ablation experiments demonstrated that all three objectives (distance, length, and angle) effectively optimized the path planning. Additionally, we also used finite element analysis to compare and analyze the MPA path and clinical path. The experimental results showed that the MPA path always outperformed the clinical path in terms of scaphoid strain and screw stress. CONCLUSION: This study presents a solution for the path planning of scaphoid fractures. Our future research will attempt to enhance the model's performance and extend its application to a broader range of fracture types.

PyBrOpS: a Python package for breeding program simulation and optimization for multi-objective breeding.

Plant breeding is a complex endeavor that is almost always multi-objective in nature. In recent years, stochastic breeding simulations have been used by breeders to assess the merits of alternative breeding strategies and assist in decision-making. In addition to simulations, visualization of a Pareto frontier for multiple competing breeding objectives can assist breeders in decision-making. This paper introduces Python Breeding Optimizer and Simulator (PyBrOpS), a Python package capable of performing multi-objective optimization of breeding objectives and stochastic simulations of breeding pipelines. PyBrOpS is unique among other simulation platforms in that it can perform multi-objective optimizations and incorporate these results into breeding simulations. PyBrOpS is built to be highly modular and has a script-based philosophy, making it highly extensible and customizable. In this paper, we describe some of the main features of PyBrOpS and demonstrate its ability to map Pareto frontiers for breeding possibilities and perform multi-objective selection in a simulated breeding pipeline.

Multi-objective evolutionary optimization for hardware-aware neural network pruning.

Neural network pruning is a popular approach to reducing the computational complexity of deep neural networks. In recent years, as growing evidence shows that conventional network pruning methods employ inappropriate proxy metrics, and as new types of hardware become increasingly available, hardware-aware network pruning that incorporates hardware characteristics in the loop of network pruning has gained growing attention. Both network accuracy and hardware efficiency (latency, memory consumption, etc.) are critical objectives to the success of network pruning, but the conflict between the multiple objectives makes it impossible to find a single optimal solution. Previous studies mostly convert the hardware-aware network pruning to optimization problems with a single objective. In this paper, we propose to solve the hardware-aware network pruning problem with Multi-Objective Evolutionary Algorithms (MOEAs). Specifically, we formulate the problem as a multi-objective optimization problem, and propose a novel memetic MOEA, namely HAMP, that combines an efficient portfolio-based selection and a surrogate-assisted local search, to solve it. Empirical studies demonstrate the potential of MOEAs in providing simultaneously a set of alternative solutions and the superiority of HAMP compared to the state-of-the-art hardware-aware network pruning method.