A Monte-Carlo-based interval De Novo programming method for optimal system design under uncertainty. (June 2018)

• Record Type: Journal Article
• Authors: Gao, P.P.; Li, Y.P.; Sun, J.; Huang, G.H.
• Is Part Of: Engineering applications of artificial intelligence. Volume 72(2018)
• Page Start: 30
• Page End: 42
• Publication Date: 2018-06
• Subjects: Decision making -- De Novo programming -- Monte Carlo -- Multiobjective -- System design -- Uncertainty; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2018.03.010
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: In this study, a Monte-Carlo-based interval De Novo programming (MC-IDP) method is developed for designing optimal electricity-allocation system under uncertainty. MC-IDP incorporates Monte Carlo simulation (MCS), interval-parameter programming (IPP), and De Novo programming (DNP) within a general framework. MC-IDP has advantages in (i) constructing optimal system design through introducing the flexibility in the right-hand sides of constraints, (ii) handling uncertainty presented as interval numbers, and (iii) mitigating the influence of decision makers' subjectivity in optimum-path ratio. MC-IDP is then applied to a case study of planning electricity-allocation system involving multiple conflicting objectives, where various scenarios associated with different optimum-path ratios are examined. Results reveal that different scenarios would lead to varied electricity-allocation patterns, pollutant/ greenhouse gas (GHG) emissions, as well as system benefits. Compared to the traditional interval multiobjective programming (IMOP), MC-IDP can achieve higher system benefits and reduce electricity loss; moreover, the maximum benefit for each objective under MC-IDP can be realized at the same time. Findings are useful to decision makers for evaluating alternatives of system designs as well as for identifying which of these designs can most efficiently achieve the desired system objectives in a more sustainable development manner. Highlights: A Monte-Carlo-based interval De Novo programming (MC-IDP) method is developed. MC-IDP can address system design issues involving multiple conflicting objectives. MC-IDP can tackle uncertainty expressed as discrete intervals. MC-IDP can overcome the decision makers' subjectivity and simplicity. The obtained results could provide feasible solutions for decision makers.