Optimization techniques in diesel engine system design

The potential of the effect of insulation and photovoltaic panel use in buildings on energy performance for Turkey and LCC analysis

“…The main effect analysis can determine the level of efficiency of a factor on the outcome value, the direction of its effect and the most efficient levels. [33][34][35][36] The steepness of the line in the main effect graphs expresses the level of importance of the factors on the outcome. 37 The effect of a factor was calculated using equation (1): 33…”

Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings

“…In this work, the Tree-structured Parzen Estimator (TPE) was chosen among Optuna sampling algorithms [75] to optimize a multi-objective function, since the DRL agent should minimize the electricity cost while reducing the indoor temperature violations compared to the RBC strategy in the source building. In this case an optimal Pareto-front solution set exists [76], so it was employed the criterion of the minimum Euclidean distance from the ideal point [77] (i.e., the non-real point whose coordinates have the lowest values when separately considering the objectives in the target function). During the automated hyperparameter optimization procedure, twenty agents trained for 30 episodes were considered, and a coordinate point [E cost , T viol ] indicating its performance was retrieved for each agent.…”

Optimal operation of multi-reservoir system for flood control and hydroelectric generation

“…In contrast to the aggregation approach, there is a set of trade-off solutions, generally known as Pareto optimal solutions (also known as non-dominated). Such solutions are optimal in the sense that no other solutions are better than them in the creative potential, or can dominate them when considering all the objectives [14].…”