Search results

Times Series Building Energy Systems data Imputation

Completeness of data is vital for the decision making and forecasting on Building Management Systems (BMS) as missing data can result in biased decision making down the line. This study creates a guideline for imputing the gaps in BMS datasets by comparing four methods: K Nearest Neighbour algorithm (KNN), Recurrent Neural Network (RNN), Hot Deck (HD) and Last Observation Carried Forward (LOCF). The guideline contains the best method per gap size and scales of measurement. The four selected methods are from various backgrounds and are tested on a real BMS and meteorological dataset. The focus of this paper is not to impute every cell as accurately as possible but to impute trends back into the missing data. The performance is characterised by a set of criteria in order to allow the user to choose the imputation method best suited for its needs. The criteria are: Variance Error (VE) and Root Mean Squared Error (RMSE). VE has been given more weight as its ability to evaluate the imputed trend is better than RMSE. From preliminary results, it was concluded that the best K‐values for KNN are 5 for the smallest gap and 100 for the larger gaps. Using a genetic algorithm the best RNN architecture for the purpose of this paper was determined to be Gated Recurrent Units (GRU). The comparison was performed using a different training dataset than the imputation dataset. The results show no consistent link between the difference in Kurtosis or Skewness and imputation performance. The results of the experiment concluded that RNN is best for interval data and HD is best for both nominal and ratio data. There was no single method that was best for all gap sizes as it was dependent on the data to be imputed.

Diversity scale

No More Surprises: Stand Assignment Algorithm with Likelihood of Turnaround Time Deviation

Airport management is frequently faced with a problem of assigning flights to available stands and parking positions in the most economical way that would comply with airline policies and suffer minimum changes due to any operational disruptions. This work presents a novel approach to the most common airport problem – efficient stand assignment. The described algorithm combines benefits of data-mining and metaheuristic approaches and generates qualitative solutions, aware of delay trends and airport performance perturbations. The presented work provides promising solutions from the starting moments of computation, in addition, it delivers to the airport stakeholders delay-aware stand assignment, and facilitates the estimation of risk and consequences of any operational disruptions on the slot adherence.

Location and distribution management of relief centers : a genetic algorythm approach

Humanitarian logistics is regarded as a key area for improved disaster management efficiency and effectiveness. In this study, a multi-objective integrated logistic model is proposed to locate disaster relief centers while taking into account network costs and responsiveness. Because this location problem is NP-hard, we present a genetic approach to solve the proposed model.

Enhancing a simulation-based Allocator Software with machine learning and genetic algorithms for improving the gate assignment problem

Assigning gates to flights considering physical, operational, and temporal constraints is known as the Gate Assignment Problem. This article proposes the novelty of coupling a commercial stand and gate allocation software with an off-the-grid optimization algorithm. The software provides the assignment costs, verifies constraints and restrictions of an airport, and provides an initial allocation solution. The gate assignment problem was solved using a genetic algorithm. To improve the robustness of the allocation results, delays and early arrivals are predicted using a random forest regressor, a machine learning technique and in turn they are considered by the optimization algorithm. Weather data and schedules were obtained from Zurich International Airport. Results showed that the combination of the techniques result in more efficient and robust solutions with higher degree of applicability than the one possible with the sole use of them independently.

Flight Trajectory Optimization Through Genetic Algorithms for Lateral and Vertical Integrated Navigation

For long flights, the cruise is the longest phase and where the largest amount of fuel is consumed. An in-cruise optimization method has been implemented to calculate the optimal trajectory that reduces the flight cost. A three-dimensional grid has been created, coupling lateral navigation and vertical navigation profiles. With a dynamic analysis of the wind, the aircraft can perform a horizontal deviation or change altitudes via step climbs to reduce fuel consumption. As the number of waypoints and possible step climbs is increased, the number of flight trajectories increases exponentially; thus, a genetic algorithm has been implemented to reduce the total number of calculated trajectories compared to an exhaustive search. The aircraft’s model has been obtained from a performance database, which is currently used in the commercial flight management system studied in this paper. A 5% average flight cost reduction has been obtained.