Multi-objective Decision Approach Research Articles

Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning

Infectious disease outbreaks can have a disruptive impact on public health and societal processes. As decision-making in the context of epidemic mitigation is multi-dimensional hence complex, reinforcement learning in combination with complex epidemic models provides a methodology to design refined prevention strategies. Current research focuses on optimizing policies with respect to a single objective, such as the pathogen’s attack rate. However, as the mitigation of epidemics involves distinct, and possibly conflicting, criteria (i.a., mortality, morbidity, economic cost, well-being), a multi-objective decision approach is warranted to obtain balanced policies. To enhance future decision-making, we propose a deep multi-objective reinforcement learning approach by building upon a state-of-the-art algorithm called Pareto Conditioned Networks (PCN) to obtain a set of solutions for distinct outcomes of the decision problem. We consider different deconfinement strategies after the first Belgian lockdown within the COVID-19 pandemic and aim to minimize both COVID-19 cases (i.e., infections and hospitalizations) and the societal burden induced by the mitigation measures. As such, we connected a multi-objective Markov decision process with a stochastic compartment model designed to approximate the Belgian COVID-19 waves and explore reactive strategies. As these social mitigation measures are implemented in a continuous action space that modulates the contact matrix of the age-structured epidemic model, we extend PCN to this setting. We evaluate the solution set that PCN returns, and observe that it explored the whole range of possible social restrictions, leading to high-quality trade-offs, as it captured the problem dynamics. In this work, we demonstrate that multi-objective reinforcement learning adds value to epidemiological modeling and provides essential insights to balance mitigation policies.

Active and Reactive Power loss Minimization Along with Voltage profile Improvement for Distribution Reconfiguration

Optimal distribution network reconfiguration (DNR), distributed generations location and sizing (DGs-LS), tap changer adjustment (TCA), and capacitors bank location and sizing (CAs-SL) are different methodologies used to reduce loss and enhance the voltage profile of distribution systems. DNR is the process of changing the network topography by changing both sectionalized and tie switch states. The optimal location looks to find the optimal setting of the DG and CA within the distribution network. Optimal size seeks to find the optimal output generation of both DG and CA. The TCA looks to find the optimal position for TC. These methods are challenging optimization problems and resort to meta-heuristic techniques to find a globally optimal solution. This paper presents a new methodology with which to simultaneously solve the problem of DNR, DGs-LS, TCA, and CAs-SL in distribution networks. This work aims to minimize active and reactive power losses, including voltage profile improvement using a multi-objective decision approach. The firefly algorithm (FA) and analytic hierarchy process (AHP) are used to optimize the fitness function and determine the function weight factors through the use of MATLAB software. Several scenarios were considered on the IEEE 69-bus network. In terms of active power and reactive losses, reductions in the test system of 96.16% and 92.7%, respectively, were achieved, evidencing the positive impact of the proposed methodology on distribution networks.

Multiobjective optimization of frozen and freeze-dried Lactobacillus delbrueckii subsp. bulgaricus CFL1 production via the modification of fermentation conditions.

This study investigates the individual and combined effects of fermentation parameters for improving cell biomass productivity and the resistance to freezing, freeze-drying, and freeze-dried storage of Lactobacillus delbrueckii subsp. bulgaricus CFL1. Cells were cultivated at different temperatures (42°C and 37°C) and pH values (5.8 and 4.8) and harvested at various growth phases (mid-exponential, deceleration, and stationary growth phases). Specific acidifying activity was determined after fermentation, freezing, freeze-drying, and freeze-dried storage. Multiple regression analyses were performed to identify the effects of fermentation parameters on the specific acidifying activity losses and to generate the corresponding 3D response surfaces. A multiobjective decision approach was applied to optimize biomass productivity and specific acidifying activity. The temperature positively influenced biomass productivity, whereas low pH during growth reduced the loss of specific acidifying activity after freezing and freeze-drying. Furthermore, freeze-drying resistance was favored by increased harvest time. Productivity, and freezing and freeze-drying resistances of L. delbrueckii subsp. bulgaricus CFL1 were differentially affected by the fermentation parameters studied. There was no single fermentation condition that improved both productivity and resistance to freezing and freeze-drying. Thus, Pareto fronts were helpful to optimize productivity and resistance, when cells were grown at 42°C, pH 4.8, and harvested at the deceleration phase.

Multi-Objective Decision Approach Integrated with Loadability and Weight Factor Analysis for Reconfiguration with DG Sizing and Allocation Including Tap Changer

Multi-Objective Decision Approach Integrated with Loadability and Weight Factor Analysis for Reconfiguration with DG Sizing and Allocation Including Tap Changer

Optimal allocation of CO2 emission quotas at the city level in Bohai Rim Economic Circle based on multi-objective decision approach.

As the most developed city circle in northern China, allocating CO2 emission quotas at the Bohai Rim Economic Circle (BREC) city level is essential for developing specific abatement policies. Thus, with reflecting multi-principles (fairness, efficiency, sustainability, and feasibility), this paper formulates the CO2 emission quota allocation among cities in BREC in 2030 based on the multi-objective decision approach. We first propose three allocation schemes based on the principles of fairness, efficiency, and sustainability, which are conducted by entropy method, zero-sum gains data envelopment (ZSG-DEA) model, and CO2 sequestration share method, respectively. Then, the CO2 allocation satisfaction is defined and used to measure the feasibility principle which is integrated as the objective function of the multi-objective decision model together with three allocation schemes to obtain the optimal allocation results. The results show that Beijing, Tianjin, Dalian, Shijiazhuang, Yantai, Weifang, and Linyi enjoy the largest CO2 emission quotas, having 1179.94 Mt in total and accounting for 31%. Beijing has the highest quotas, and Laiwu has the lowest emission quotas. Cities with large energy consumption and less CO2 sequestration capacity, such as Tianjin, Handan, and Tangshan, experience a decrease in the emission quota shares from 2017 to 2030, indicating that these cities would undertake large emission reduction obligations. Sensitivity analysis shows that Beijing, Zibo, and Jinan are more sensitive to minimum satisfaction changes, and the total satisfaction experiences an increase first and declines thereafter. Based on the results above, cities with large pressure to reduce CO2 emissions should not only promote economic development but also improve the capacity of CO2 sequestration by enhancing environmental protection to realize emission reduction targets.

Milling of Ti–6Al–4V under hybrid Al2O3-MWCNT nanofluids considering energy consumption, surface quality, and tool wear: a sustainable machining

Sustainable manufacturing philosophy strives for energy-efficient, high quality, and productivity as critical characteristics of a milling process. Hence, an attempt was made to limit the energy consumption, and tool wear in the face milling of hard-to-cut titanium alloy without compromising product quality and productivity. For that, a strong influence of hybrid alumina and multiwalled carbon nanotube (Al2O3-MWCNT) nanoadditive-based minimum quantity lubrication (MQL) was investigated on key machining characteristics. The simultaneous influence of control factors on machining characteristics was evaluated through mathematical modeling and the most straightforward multi-objective optimization. Based on the multi-objective decision approach, the energy consumption of Ec = 829.78 W, surface roughness Ra = 0.549 μm, and material removal rate MRR = 303.9 mm3/min were attained at cutting speed N = 3800 rpm, feed f = 0.012 mm/tooth, depth of cut ap = 0.40 mm, and width of cut ae = 3.6 mm respectively. Despite the trade-off among energy consumption, surface roughness, and material removal rate, the desirability function tried to strike a balanced operating level to achieve less energy consumption, better surface quality, and higher materials removal rate. Additionally, tool wear, chip analysis, and surface topography as key characteristics of the milling process were considered to analyze the wear behavior, chip sliding, and machined surface characteristics under hybrid nanoadditive-based MQL machining. The novelty of this experimental work lies in considering important milling characteristics of hard-to-cut Ti–6Al–4V alloy under hybrid nanofluid-assisted MQL machining. Regarding sustainable green cutting technology, clean cutting of titanium alloy was implemented by nanoadditive-assisted MQL technique.

A novel hybrid approach based on fuzzy multi-criteria decision-making tools for assessing sustainable alternatives of power generation in San Andrés Island

This paper presents a novel approach based on fuzzy multi-criteria decision-making tools for assessing sustainable alternatives of power generation in San Andrés Island, Colombia. In the first stage, the energy system was established. A fuzzy multi-objective decision approach based on a mixed-integer linear model was implemented to obtain a set of alternatives, including solar photovoltaic, wind turbines, and the diesel plants currently used. Subsequently, the total cost and the CO2 emissions of the energy system were minimized all while considering design, operational, and efficiency constraints. The CO2 emissions and the total present value of the alternatives of energy, together with social, technological, economic, and environmental factors assessed through expert opinions were used as input in the fuzzy multi-criteria decision phase, where a novel fuzzy logic model was employed for selecting the most sustainable alternative. The results indicate that the current diesel capacity in San Andrés Island prevails; with a maximum participation of 3% and 4% of solar and wind systems, respectively.

Allocating CO2 allowances to emitters in China: A multi-objective decision approach

China CO2 allowance (CHA) allocation for emitters is one of the pivotal issues to build the effective national carbon market. In this study, we propose a multi-objective decision approach, incorporating the principles of fairness, efficiency, and feasibility, to allocate the CHAs to emitters from the industry perspective. Taking Guangdong, China as an example, we employ the proposed approach for allocating the CHAs to six major industries of petrochemical, chemical, cement, steel, nonferrous metals, and electricity power by 2030. The empirical results show that there are significant conflicts between principles. The proposed approach can not only effectively eliminate the defects of single-object models to make the allocation results more reasonable and acceptable, but also achieve optimal allocation options under various decision preferences. The power industry has the highest CHA and petrochemical industry has the lowest one, and petrochemical, chemical, and steel industries have the greatest potential to reduce carbon intensity. Single-factor sensitivity analysis shows that the CHA/104 Yuan added value (TY) of the industry with lower emissions is more sensitive to the changes of physical capital stock but received fewer impacts from the changes of emissions cap for six industries.

Multi-objective approach for broker dominant supply-demand matching decision

Supply-demand matching is crucial to optimize resource utilization and form long-term partnership. This study will contribute to the current supply-demand matching research by (1)generalizing the broker dominant supply-demand matching problem (B-SDMP); (2) proposing the B-SDMP multi-objective decision approach including (a) the mathematical model considering the satisfaction of important suppliers and buyers determined by the broker; (b) a weighted linearization method to solve the model; and (3) application the B-SDMP in practice. The results are the optimum matching decision solutions which can help the buyers to find the appropriate suppliers on one commodity. It could promote the formulation of long-term partnership of the three parties (suppliers, buyers, and the broker) as a stable supply chain. To demonstrate the effectiveness of the approach on a practical level, a seaborne coal transaction project is used. The matching solutions obtained from B-SDMP analysis are practically feasible.

A multi-objective decision approach for optimal augmentation and expansion of transmission network

In this paper, the authors propose a new multi-objective decision making approach for optimal augmentation and expansion of transmission network. Fundamental elements of the proposed approach are value of reliability and electricity market. Investment Cost (IC), Total Congestion Cost (TCOC) and Social Welfare (SW) and also Average Load Interruption Cost (ALIC) are the four objectives considered in the optimization, while short-term and long-term constraints, are modeled as constraints. The proposed model is one of complicated non-convex optimization problem having a nonlinear, mixed-integer nature. Therefore, a new and robust hybrid Improved Harmony Search Algorithm (IHSA) and Quadratic Programming (QP) is used and followed by a Fuzzy Satisfying Method (FSM) to determine the final optimal solution. The feasibility and capabilities of the proposed approach are tested on the 6-machine 8-bus test system. The detailed results of the case studies are presented and thoroughly analyzed. The obtained results illustrate the sufficiency and profitableness of the newly developed method in augmentation and expansion of transmission network when, compared with other methods.

DECISION ON ENTERPRISE COMPUTING SOLUTIONS FOR AN INTERNATIONAL TOURISM

This study proposes a multi-objective decision approach for evaluating the enterprise computing solutions in international tourism. We first analyze one tour operator in Thailand as well as its specific requirements for enterprise computations. In the decision processes for enterprise computation, several experts are invited to evaluate the alternatives based on a multi-tier electronic business architecture. This study designs two models for evaluating the information systems investments in international tourism. The first model maximizes the overall utility for each criterion, and the other model maximizes the utility for every expert. Because each alternative for enterprise computation involves approximate costs and efforts, we represent the cost data with fuzzy sets and possibility distributions.

Indicators and framework for assessing sustainable infrastructure

Much of the focus on sustainable infrastructure has concentrated on buildings and construction processes. To advance this thinking for other civil infrastructure systems (CIS), this paper outlines a framework that uses a set of proposed indicators to measure the sustainability of chosen infrastructure options and help select the preferred alternative in a multiobjective decision approach. Physically implementing "sustainable infrastructure" involves three life stages for any project: preproject planning, project implementation, and ongoing operations. It is critical to evaluate the sustainability of chosen options in each of these life stages. This research develops two categories of indicators, mandatory screening indicators (MSI) and judgment indicators (JI), and a multilayer approach for incorporating these indicators. A normalization procedure has been adapted to work within the framework to help compare alternatives across a range of indicators and different orders of data magnitude. A hypothetical example using a transmission line corridor is presented to illustrate how the framework can be applied.Key words: indicators, infrastructure, sustainable, environment, decision making, alternatives.

Optimum Decision of Capacity and Location of Plants : Multi-Objective Decision Approach with Uncertain Demand Forecast

Optimum Decision of Capacity and Location of Plants : Multi-Objective Decision Approach with Uncertain Demand Forecast