Small Boxes Big Data: A Deep Learning Approach to Optimize Variable Sized Bin Packing

Abstract

Abstract-Bin Packing problems have been widely studied because of their broad applications in different domains. Known as a set of NP-hard problems, they have different variations and many heuristics have been proposed for obtaining approximate solutions. Specifically, for the 1D variable sized bin packing problem, the two key sets of optimization heuristics are the bin assignment and the bin allocation. Usually the performance of a single static optimization heuristic can not beat that of a dynamic one which is tailored for each bin packing instance. Building such an adaptive system requires modeling the relationship between bin features and packing perform profiles. The primary drawbacks of traditional AI machine learnings for this task are the natural limitations of feature engineering, such as the curse of dimensionality and feature selection quality. We introduce a deep learning approach to overcome the drawbacks by applying a large training data set, auto feature selection and fast, accurate labeling. We show in this paper how to build such a system by both theoretical formulation and engineering practices. Our prediction system achieves up to 89% training accuracy and 72% validation accuracy to select the best heuristic that can generate a better quality bin packing solution.

Applying Deep Learning Techniques for Big Data Analytics: A Systematic Literature Review

“…For instance, [FS5] used TF in their implementation process, and their entire framework was implemented using TF [33]. [FS19] used the TF deep learning model to build the packing algorithms for their experiments [34]. [FS15] used the TF * framework to build a network that was trained on a set of dataset that yields a good mapping result for the experiment [30].…”

Efficient Algorithm Based on Adaptive Window–Model Predictive Control for Automatic Stacking in Warehouse Center

“…, ( ) and , represent the lengths of the package ( ) and the cart alongside the Cartesian coordinate system axes. Equation (2) implies that the origin of the Cartesian coordinate system is placed on the back-left-bottom corner of the cart floor.…”

“…The algorithm learns the optimal solution with a lifelong manner which leads to poor solutions whenever the items distribution changes. In [2], a deep learning method has been proposed to solve the 1D variable sized BPP where the bins capacities are decision variables. It requires a large training data set which is computationally intensive.…”

Generative Neural Network based Spectrum Sharing using Linear Sum Assignment Problems

“…The variational type of the autoencoders could learn the low-dimensional embedding z of the cost matrx x by maximizing the lower-bound likelihood in (10) with respect to the group of deep network parameters θ.…”

“…Therefore, the first term in (10) can be reduced to a decoder network f (z; θ) with the L 2 loss function given in (9). Employing the L 2 norm as part of the loss function improves the network convergence and helps in avoiding over fitting.…”