Power Generation Expansion Planning Using an Interior Point with Cutting Plane （IP/CP） Method

The generation expansion planning is one of complex mixed-integer optimization problems, which involves a large number of continuous or discrete decision variables and constraints. In this paper, an interior point with cutting plane （IP/CP） method is proposed to solve the mixed-integer optimization problem of the electrical power generation expansion planning. The IP/CP method could improve the overall efficiency of the solution and reduce the computational time. Proposed method is combined with the Bender＇s decomposition technique in order to decompose the generation expansion problem into a master investment problem and a slave operational problem. The numerical example is presented to compare with the effectiveness of the proposed algorithm.

An entropy based central cutting plane algorithm for convex min-max semi-infinite programming problems

In this paper,we present a central cutting plane algorithm for solving convex min-max semi-infinite programming problems.Because the objective function here is non-differentiable,we apply a smoothing technique to the considered problem and develop an algorithm based on the entropy function.It is shown that the global convergence of the proposed algorithm can be obtained under weaker conditions.Some numerical results are presented to show the potential of the proposed algorithm.

Mini-batch cutting plane method for regularized risk minimization

Although concern has been recently expressed with regard to the solution to the non-convex problem, convex optimization is still important in machine learning, especially when the situation requires an interpretable model. Solution to the convex problem is a global minimum, and the final model can be explained mathematically. Typically, the convex problem is re-casted as a regularized risk minimization problem to prevent overfitting. The cutting plane method (CPM) is one of the best solvers for the convex problem, irrespective of whether the objective function is differentiable or not. However, CPM and its variants fail to adequately address large-scale data-intensive cases because these algorithms access the entire dataset in each iteration, which substantially increases the computational burden and memory cost. To alleviate this problem, we propose a novel algorithm named the mini-batch cutting plane method (MBCPM), which iterates with estimated cutting planes calculated on a small batch of sampled data and is capable of handling large-scale problems. Furthermore, the proposed MBCPM adopts a "sink" operation that detects and adjusts noisy estimations to guarantee convergence. Numerical experiments on extensive real-world datasets demonstrate the effectiveness of MBCPM, which is superior to the bundle methods for regularized risk minimization as well as popular stochastic gradient descent methods in terms of convergence speed.

An efficient algorithm for multi-dimensional nonlinear knapsack problems

Multi-dimensional nonlinear knapsack problem is a bounded nonlinear integer programming problem that maximizes a separable nondecreasing function subject to multiple separable nondecreasing constraints. This problem is often encountered in resource allocation, industrial planning and computer network. In this paper, a new convergent Lagrangian dual method was proposed for solving this problem. Cutting plane method was used to solve the dual problem and to compute the Lagrangian bounds of the primal problem. In order to eliminate the duality gap and thus to guarantee the convergence of the algorithm, domain cut technique was employed to remove certain integer boxes and partition the revised domain to a union of integer boxes. Extensive computational results show that the proposed method is efficient for solving large-scale multi-dimensional nonlinear knapsack problems. Our numerical results also indicate that the cutting plane method significantly outperforms the subgradient method as a dual search procedure.

A new heuristic algorithm for general integer linear programming problems

A new heuristic algorithm is proposed for solving general integer linear programming problems. In the algorithm, the objective function hyperplane is used as a cutting plane, and then by introducing a special set of assistant sets, an efficient heuristic search for the solution to the integer linear program is carried out in the sets on the objective function hyperplane. A simple numerical example shows that the algorithm is efficient for some problems, and therefore, of practical interest.

Gomory’s Method Based on the Objective Equivalent Face Technique

This paper discusses a re-examinatlon of dual methods based on Gomory＇s cutting plane for the solution of the integer programming problem, in which the increment of objection function is allowed as a pivot variable to decide the search direction and stepsize. Meanwhile, we adopt the current equivalent face technique so that lattices are found in the discrete integral face and stronger valid inequalities are acquired easily.

Enhancing cut selection through reinforcement learning

With the rapid development of artificial intelligence in recent years,applying various learning techniques to solve mixed-integer linear programming(MILP)problems has emerged as a burgeoning research domain.Apart from constructing end-to-end models directly,integrating learning approaches with some modules in the traditional methods for solving MILPs is also a promising direction.The cutting plane method is one of the fundamental algorithms used in modern MILP solvers,and the selection of appropriate cuts from the candidate cuts subset is crucial for enhancing efficiency.Due to the reliance on expert knowledge and problem-specific heuristics,classical cut selection methods are not always transferable and often limit the scalability and generalizability of the cutting plane method.To provide a more efficient and generalizable strategy,we propose a reinforcement learning(RL)framework to enhance cut selection in the solving process of MILPs.Firstly,we design feature vectors to incorporate the inherent properties of MILP and computational information from the solver and represent MILP instances as bipartite graphs.Secondly,we choose the weighted metrics to approximate the proximity of feasible solutions to the convex hull and utilize the learning method to determine the weights assigned to each metric.Thirdly,a graph convolutional neural network is adopted with a self-attention mechanism to predict the value of weighting factors.Finally,we transform the cut selection process into a Markov decision process and utilize RL method to train the model.Extensive experiments are conducted based on a leading open-source MILP solver SCIP.Results on both general and specific datasets validate the effectiveness and efficiency of our proposed approach.

A Novel MILP Model for N-vehicle Exploration Problem

The N-vehicle exploration problem(NVEP)is a nonlinear discrete scheduling problem,and the complexity status remains open.To our knowledge,there is no literature until now employing mixed integer linear programming(MILP)technology to solve this problem except for Wang(J Oper Res Soc China 3(4):489–498,2015).However,they did not give numerical experiments since their model existed strictly inequalities and the number of constraints was up to O(n3),which was inefficient to solve practical problems.This paper establishes a more concise MILP model,where the number of constraints is just O(n2).Therefore,the existing efficient MILP algorithms can be used to solve NVEP.Secondly,we provide some properties of N-vehicle problem and give three methods for cutting plane construction,which can increase the solving speed significantly.Finally,a numerical experiment is provided to verify the effectiveness and robustness for different instances and scales of acceleration techniques.