Traditional Machine Learning Models for Building Energy Performance Prediction: A Comparative Research
Issue:
Volume 8, Issue 1, June 2023
Pages:
1-8
Received:
29 April 2023
Accepted:
18 May 2023
Published:
29 May 2023
Abstract: A large proportion of total energy consumption is caused by buildings. Accurately predicting the heating and cooling demand of a building is crucial in the initial design phase in order to determine the most efficient solution from various designs. In this paper, in order to explore the effectiveness of basic machine learning algorithms to solve this problem, different machine learning models were used to estimate the heating and cooling loads of buildings, utilising data on the energy efficiency of buildings. Notably, this paper also discusses the performance of deep neural network prediction models and concludes that among traditional machine learning algorithms, GradientBoostingRegressor achieves better predictions, with Heating prediction reaching 0.998553 and Cooling prediction Compared with our machine learning algorithm HB-Regressor, the prediction accuracy of HB-Regressor is higher, reaching 0.998672 and 0.995153 respectively, but the fitting speed is not as fast as the GradientBoostingRegressor algorithm.
Abstract: A large proportion of total energy consumption is caused by buildings. Accurately predicting the heating and cooling demand of a building is crucial in the initial design phase in order to determine the most efficient solution from various designs. In this paper, in order to explore the effectiveness of basic machine learning algorithms to solve th...
Show More
Research Article
Hybridizing Slime Mould Algorithm with Simulated Annealing for Solving Metric Dimension Problem
Basma Mohamed,
Mohamed Amin
Issue:
Volume 8, Issue 1, June 2023
Pages:
9-16
Received:
13 September 2023
Accepted:
8 October 2023
Published:
28 October 2023
Abstract: In this paper, we consider the NP-hard problem of finding the metric dimension of graphs. A set of vertices B of a connected graph G = (V, E) resolves G if every vertex of G is uniquely identified by its vector of distances to the vertices in B. The cardinality of the smallest resolving set of G is the metric dimension of G. The metric dimension problem arises in several different fields, such as robot navigation, telecommunication, and geographical routing protocol. The slime mould algorithm (SMA) is an efficient population-based optimizer based on the oscillation mode of slime mould in nature. The SMA has a specific mathematical model and very competitive results, along with fast convergence for many problems, particularly in real-world cases. SMA has good exploration and exploitation abilities for solving optimization problems. However, complex and high-dimensional SMA may fall into local optimal regions. SA is a very preferable technique among the other heuristic approaches as it provides practical randomness in the search to avoid the local extreme points. However, SA involves a trade-off between computing time and solution sensitivity. The SA is used to enhance the fitness of the best agent if it falls in a suboptimal region, which will lead to the enhancement of all individuals. We solve the problem as integer linear programming and introduce the hybrid algorithm SMA-SA, which combines simulated annealing SA and SMA for determining the metric dimension of graphs. Comparisons were performed on the graphs: k-home chain graph, tadpole graph, alternate triangular snake graph, and mirror graph. Finally, computational results and comparisons with pure SA, SMA, and PSO algorithms confirm the effectiveness of the proposed SMA-SA for solving metric dimension problem.
Abstract: In this paper, we consider the NP-hard problem of finding the metric dimension of graphs. A set of vertices B of a connected graph G = (V, E) resolves G if every vertex of G is uniquely identified by its vector of distances to the vertices in B. The cardinality of the smallest resolving set of G is the metric dimension of G. The metric dimension pr...
Show More
