Open Challenges and Issues: Artificial Intelligence for Transactive Management

TL;DR

This paper reviews the current state of AI and ML techniques, especially MultiAgent Systems, in transactive energy management, highlighting challenges and potential solutions for improving smart energy systems.

Contribution

It provides an overview of AI-based methods in transactive management, compares MAS and ML approaches, and discusses open challenges in the field.

Findings

MAS faces difficulties in goal setting for agents

ML techniques can aid in agent goal configuration

Open challenges remain in AI-driven transactive energy management

Abstract

The advancement of Artificial Intelligence (AI) has improved the automation of energy managements. In smart energy management or in a smart grid framework, all the devices and the distributed resources and renewable resources are embedded which leads to reduce cost. A smart energy management system, Transactive management (TM) is a concept to improve the efficiency and reliability of the power system. The aim of this article is to look for the current development of TM methods based on AI and Machine Learning (ML) technology. In AI paradigm, MultiAgent System (MAS) based method is an active research area and are still in evolution. Hence this article describes how MAS based method applied in TM. This paper also finds that MAS based method faces major difficulty to design or set up goal to various agents and describes how ML technique can contribute to that solution. A brief comparison analysis between MAS and ML techniques are also presented. At the end, this article summarizes the most relevant open challenges and issues on the AI based methods for transactive energy management.