Solving MKP Applied to IoT in Smart Grid Using Meta-heuristics Algorithms: A Parallel Processing Perspective

TL;DR

This paper explores optimizing energy management in smart grids by applying meta-heuristic algorithms to solve the NP-hard Multiple Knapsack Problem, emphasizing parallel processing for scalability and efficiency.

Contribution

It introduces the application of meta-heuristic algorithms, specifically the iterative Discrete Flower Pollination Algorithm, for DSM optimization in smart grids, and discusses parallelization strategies for scalability.

Findings

Meta-heuristic algorithms can effectively optimize DSM in smart grids.

Parallel processing enhances scalability of the optimization algorithms.

The iterative Discrete Flower Pollination Algorithm shows promise for solving MKP in this context.

Abstract

Increasing electricity prices in South Africa and the imminent threat of load shedding due to the overloaded power grid has led to a need for Demand Side Management (DSM) devices like smart grids. For smart grids to perform to their peak, their energy management controller (EMC) systems need to be optimized. Current solutions for DSM and optimization of the Multiple Knapsack Problem (MKP) have been investigated in this paper to discover the current state of common DSM models. Solutions from other NP-Hard problems in the form of the iterative Discrete Flower Pollination Algorithm (iDFPA) as well as possible future scalability options in the form of optimization through parallelization have also been suggested.