Stochastic multiobjective generation maintenance scheduling using augmented normalized normal constraint method and stochastic decision maker

Abstract

Summary This paper presents a stochastic multiobjective model for generation maintenance scheduling (GMS) problem and a solution method to solve it. The proposed model properly considers both competing objectives and uncertainty sources of GMS problem. Three competing objective functions including total cost, risk measure, and total emission are simultaneously minimized in the proposed model. Moreover, forced outages of generating units throughout the GMS horizon are characterized by externally generated scenarios. Stochastic programming as an efficient approach to model uncertainty sources has been used in the proposed stochastic multiobjective GMS. Augmented normalized normal constraint (A‐NNC) method is developed as an efficient multiobjective mathematical programming approach to obtain Pareto optimal solutions for the proposed model. Further, a stochastic decision maker based on out‐of‐sample analysis is suggested to find the most preferred solution for GMS problem. The IEEE 118‐bus test system is used to investigate the effectiveness of the proposed model and solution method.

VPP Self-Scheduling Strategy Using Multi-Horizon IGDT, Enhanced Normalized Normal Constraint, and Bi-Directional Decision-Making Approach

“…However, the 11 comparative models can only adopt risk seeker/neutral/averse decision making with a fixed over the scheduling horizon. In Table III, the proposed ENNC is compared with other MOMP methods including weighted sum (WS) [29], normal boundary intersection (NBI) [30], NNC [16], modified augmented -constraint (MA C) [31], and ANNC [17]. To fairly compare the MOMP methods of Table III, the same ex-ante performance evaluation and FBDP have been used for all of these methods.…”

“…Despite the NNC capability to cover various parts of the objective space, it suffers from generating inefficient or dominated solutions. To remedy this problem, ANNC has been presented in [17], which augments the Pareto solution production mechanism of NNC using slack variables. ANNC can essentially generate solely non-dominated or efficient Pareto solutions.…”

“…At the same time, ANNC saves the advantages of NNC to search objective space systematically and to generate distributed Pareto solutions uniformly. Details of ANNC can be found in [17].…”

“…In addition to optimizing the payoff matrix, using the proposed lexicographic orders and lexicographic optimizations, the anchor points of the ANNC [17] are also optimized within the proposed ENNC. In other words, each anchor point coordinate in the objective space (which is one objective function in the MH-IGDT problem) is successively optimized considering the results obtained for the previous coordinates.…”

Adaptive‐robust multi‐resolution generation maintenance scheduling with probabilistic reliability constraint

“…A recursive sampling method has been introduced in [15] to dynamically update scenarios based on the maintenance scheduling and SCUC solutions. Bagheri and Amjady [16] propose a stochastic multiobjective GMS model considering the uncertainty of unit forced outages. A stochastic condition-based multi-resolution model for GMS problem considering unexpected unit failures has been proposed in [12].…”