Enhancing optimal transmission or subtransmission planning by using decision trees

Abstract

Due to the large size of electric power systems, there is a very high computational burden when obtaining the optimum network by using classical optimization techniques. Several authors have used heuristics and/or sensitivities in order to guide the search of optimal network investments. This paper proposes an Automatic Learning approach in order to decide whether a network change will improve the overall costs or not. More specifically, Decision Trees methods are used to identify a set of simple and reliable rules which combine criteria based on both heuristics and sensitivities. These decision trees are integrated in a subtransmission planning tool, improving dramatically both the "optimality" of the resultant network and the computational time.

Offshore wind farm electrical design using a hybrid of ordinal optimization and mixed-integer programming

“…This is a linear problem that can be solved relatively quickly. Select the top samples to form the selected subset.The selected subset is formed from the solutions that have the lowest cost. In this case, the top 1% performers in terms of total cost are selected (that is, the top 5 samples out of 500). Analyze common features in the selected subset.Similar to the measures used by Peco et al . to guide a heuristic solution, the mechanism that looks for common features studies decision variables (the variables describing cables, transformers and converter stations that define a generated sample) and aggregations of variables (this will be referred to as descriptive variables ).…”

“…Similar to the measures used by Peco et al . to guide a heuristic solution, the mechanism that looks for common features studies decision variables (the variables describing cables, transformers and converter stations that define a generated sample) and aggregations of variables (this will be referred to as descriptive variables ).…”