The rapid advancement of artificial intelligence(AI)has significantly increased the computational load on data centers.AI-related computational activities consume considerable electricity and result in substantial car...The rapid advancement of artificial intelligence(AI)has significantly increased the computational load on data centers.AI-related computational activities consume considerable electricity and result in substantial carbon emissions.To mitigate these emissions,future data centers should be strategically planned and operated to fully utilize renewable energy resources while meeting growing computational demands.This paper aims to investigate how much carbon emission reduction can be achieved by using a carbonoriented demand response to guide the optimal planning and operation of data centers.A carbon-oriented data center planning model is proposed that considers the carbon-oriented demand response of the AI load.In the planning model,future operation simulations comprehensively coordinate the temporal‒spatial flexibility of computational loads and the quality of service(QoS).An empirical study based on the proposed models is conducted on real-world data from China.The results from the empirical analysis show that newly constructed data centers are recommended to be built in Gansu Province,Ningxia Hui Autonomous Region,Sichuan Province,Inner Mongolia Autonomous Region,and Qinghai Province,accounting for 57%of the total national increase in server capacity.33%of the computational load from Eastern China should be transferred to the West,which could reduce the overall load carbon emissions by 26%.展开更多
Optimization of long-term mine production scheduling in open pit mines deals with the management of cash flows, typically in the order of hundreds of millions of dollars. Conventional mine scheduling utilizes optimiza...Optimization of long-term mine production scheduling in open pit mines deals with the management of cash flows, typically in the order of hundreds of millions of dollars. Conventional mine scheduling utilizes optimization methods that are not capable of accounting for inherent technical uncertainties such as uncertainty in the expected ore/metal supply from the underground, acknowledged to be the most critical factor. To integrate ore/metal uncertainty into the optimization of mine production scheduling a stochastic integer programming(SIP) formulation is tested at a copper deposit. The stochastic solution maximizes the economic value of a project and minimizes deviations from production targets in the presence of ore/metal uncertainty. Unlike the conventional approach, the SIP model accounts and manages risk in ore supply, leading to a mine production schedule with a 29% higher net present value than the schedule obtained from the conventional, industry-standard optimization approach, thus contributing to improving the management and sustainable utilization of mineral resources.展开更多
Recycling of waste electrical and electronic equipment （WEEE） is crucially important since it handles hazardous waste according to ever tightening laws and regulations and it adds benefits to economy and sustainable...Recycling of waste electrical and electronic equipment （WEEE） is crucially important since it handles hazardous waste according to ever tightening laws and regulations and it adds benefits to economy and sustainable environment. Disassembly is one of the most important processes performed during the recovery of WEEE. The overall goal of disassembly is to maximize the retrieval of various metals and plastics contained in WEEE in order to reduce their negative effects on human health and environmental sustainability and to increase economic gains. This study aims to evaluate alternative layout configurations for WEEE disassembly systems （WDS）. In this context, various configurations were compared in terms of pre-defined performance criteria, such as the total number of disassembled WEEE and the total revenue from sales, using simulation models. The results of this study show that the perfomaance of a WDS was significantly affected by output transfer systems along with the specialization of operators on certain types of WEEE.展开更多
Objective To establish two models based on machine learning and dose calculation algorithm that can be used for the prediction of the total dwell time and rapid quality control of brachytherapy plans.Methods A total o...Objective To establish two models based on machine learning and dose calculation algorithm that can be used for the prediction of the total dwell time and rapid quality control of brachytherapy plans.Methods A total of 1042 cases of treated gynecologic oncology patients were selected,of which 512 were used as training data to establish the model and the rest were used as test data.Each treatment plan optimized by inverse planning simulated annealing with all three catheters of the Fletcher applicator.The source strength Sk,prescription dose D,source dwell time t,and tumor volume V were recorded for each case.RV was defined as Sk·t/D.In accordance with the prescription dosage calculation formula in the planning system and machine learning method,the following equations were established:RV=kV2/3 and RV=a+b · V+c·V2.The R2 correlation coefficient represents the accuracy of the results.Result The dose calculation algorithm-based model is RV=1272×V2/3,R2=0.959,whereas the machine learning-based model is RV=258.8× V-0.359× V2+5110,R2=0.961.The treatment time prediction of the two models,each having 13 and 15 cases,respectively,has an error rate of more than10%,and the dose calculation algorithm-based method is more accurate.Conclusion The treatment time can be quickly predicted according to the planning target volume,and the two prediction models can be used as a way of quality control.展开更多
Objective:To study the correlation between tumor size,radiation source intensity,prescription dose,and source dwell time in afterloading treatment plan,and to establish a rapid quality control method for afterloading ...Objective:To study the correlation between tumor size,radiation source intensity,prescription dose,and source dwell time in afterloading treatment plan,and to establish a rapid quality control method for afterloading treatment plan.Methods:A total of 181 patients with gynecological tumor were enrolled in our hospital.A total of 84 patients were installed with three tubes of Fletcher'applicator,58 patients with single uterine tube and 39 patients with vaginal applicator.Each patient was scanned with CT before treatment,and the target area and organs were delineated by doctors.The treatment plan was optimized by IPSA.The planned source intensity,prescription dose,source residence time and tumor volume of each case were recorded and the CI,RV,and k value were calculated,The CI distribution characteristics and the relationship with RV value were analyzed.In addition,46 cases of gynecological tumor patients'afterloading plan used this method for quality control verification.Results:The CI of the three kinds of applicators was normal distribution.The average Ci of Fletcher applicator was 0.720±0.067,k=1394,r=0.894,the average CI of Fletcher applicator was 0.697±0.076,k=1428,r=0.940,the average CI of vaginal applicator was 0.742±0.067,k=1362,r=0.909.Conclusion:Using this method,we could quickly evaluate the target volume,radiation source intensity,prescription dose and treatment time,to determine the cause of deviation according to the feedback results,ensuring that the afterloading treatment plan can be implemented efficiently quickly,and accurately in accordance with the clinical requirements.展开更多
基金supported by the Scientific&Technical Project of the State Grid(5700--202490228A--1--1-ZN).
文摘The rapid advancement of artificial intelligence(AI)has significantly increased the computational load on data centers.AI-related computational activities consume considerable electricity and result in substantial carbon emissions.To mitigate these emissions,future data centers should be strategically planned and operated to fully utilize renewable energy resources while meeting growing computational demands.This paper aims to investigate how much carbon emission reduction can be achieved by using a carbonoriented demand response to guide the optimal planning and operation of data centers.A carbon-oriented data center planning model is proposed that considers the carbon-oriented demand response of the AI load.In the planning model,future operation simulations comprehensively coordinate the temporal‒spatial flexibility of computational loads and the quality of service(QoS).An empirical study based on the proposed models is conducted on real-world data from China.The results from the empirical analysis show that newly constructed data centers are recommended to be built in Gansu Province,Ningxia Hui Autonomous Region,Sichuan Province,Inner Mongolia Autonomous Region,and Qinghai Province,accounting for 57%of the total national increase in server capacity.33%of the computational load from Eastern China should be transferred to the West,which could reduce the overall load carbon emissions by 26%.
基金funded from the National Science and Engineering Research Council of Canada,Collaborative R&D Grant CRDPJ 335696 with BHP Billiton and NSERC Discovery Grant 239019 to R. Dimitrakopoulos
文摘Optimization of long-term mine production scheduling in open pit mines deals with the management of cash flows, typically in the order of hundreds of millions of dollars. Conventional mine scheduling utilizes optimization methods that are not capable of accounting for inherent technical uncertainties such as uncertainty in the expected ore/metal supply from the underground, acknowledged to be the most critical factor. To integrate ore/metal uncertainty into the optimization of mine production scheduling a stochastic integer programming(SIP) formulation is tested at a copper deposit. The stochastic solution maximizes the economic value of a project and minimizes deviations from production targets in the presence of ore/metal uncertainty. Unlike the conventional approach, the SIP model accounts and manages risk in ore supply, leading to a mine production schedule with a 29% higher net present value than the schedule obtained from the conventional, industry-standard optimization approach, thus contributing to improving the management and sustainable utilization of mineral resources.
文摘Recycling of waste electrical and electronic equipment （WEEE） is crucially important since it handles hazardous waste according to ever tightening laws and regulations and it adds benefits to economy and sustainable environment. Disassembly is one of the most important processes performed during the recovery of WEEE. The overall goal of disassembly is to maximize the retrieval of various metals and plastics contained in WEEE in order to reduce their negative effects on human health and environmental sustainability and to increase economic gains. This study aims to evaluate alternative layout configurations for WEEE disassembly systems （WDS）. In this context, various configurations were compared in terms of pre-defined performance criteria, such as the total number of disassembled WEEE and the total revenue from sales, using simulation models. The results of this study show that the perfomaance of a WDS was significantly affected by output transfer systems along with the specialization of operators on certain types of WEEE.
文摘Objective To establish two models based on machine learning and dose calculation algorithm that can be used for the prediction of the total dwell time and rapid quality control of brachytherapy plans.Methods A total of 1042 cases of treated gynecologic oncology patients were selected,of which 512 were used as training data to establish the model and the rest were used as test data.Each treatment plan optimized by inverse planning simulated annealing with all three catheters of the Fletcher applicator.The source strength Sk,prescription dose D,source dwell time t,and tumor volume V were recorded for each case.RV was defined as Sk·t/D.In accordance with the prescription dosage calculation formula in the planning system and machine learning method,the following equations were established:RV=kV2/3 and RV=a+b · V+c·V2.The R2 correlation coefficient represents the accuracy of the results.Result The dose calculation algorithm-based model is RV=1272×V2/3,R2=0.959,whereas the machine learning-based model is RV=258.8× V-0.359× V2+5110,R2=0.961.The treatment time prediction of the two models,each having 13 and 15 cases,respectively,has an error rate of more than10%,and the dose calculation algorithm-based method is more accurate.Conclusion The treatment time can be quickly predicted according to the planning target volume,and the two prediction models can be used as a way of quality control.
文摘Objective:To study the correlation between tumor size,radiation source intensity,prescription dose,and source dwell time in afterloading treatment plan,and to establish a rapid quality control method for afterloading treatment plan.Methods:A total of 181 patients with gynecological tumor were enrolled in our hospital.A total of 84 patients were installed with three tubes of Fletcher'applicator,58 patients with single uterine tube and 39 patients with vaginal applicator.Each patient was scanned with CT before treatment,and the target area and organs were delineated by doctors.The treatment plan was optimized by IPSA.The planned source intensity,prescription dose,source residence time and tumor volume of each case were recorded and the CI,RV,and k value were calculated,The CI distribution characteristics and the relationship with RV value were analyzed.In addition,46 cases of gynecological tumor patients'afterloading plan used this method for quality control verification.Results:The CI of the three kinds of applicators was normal distribution.The average Ci of Fletcher applicator was 0.720±0.067,k=1394,r=0.894,the average CI of Fletcher applicator was 0.697±0.076,k=1428,r=0.940,the average CI of vaginal applicator was 0.742±0.067,k=1362,r=0.909.Conclusion:Using this method,we could quickly evaluate the target volume,radiation source intensity,prescription dose and treatment time,to determine the cause of deviation according to the feedback results,ensuring that the afterloading treatment plan can be implemented efficiently quickly,and accurately in accordance with the clinical requirements.
