Learning Agents for Storage Devices Management in the Smart Grid

Abstract

A notable feature in the smart grid is the widespread usage of energy storage devices. How to manage those storage devices is a key problem for the smart grid. In this paper, a novel adaptive agent learning ZIPEM algorithm is presented for management of the storage devices. A system with such algorithm allows multi-agent learning that leads to optimal energy storage strategy. The experimental results show that load factor during peak time reduced significantly, and it is possible to save up to 6 percent per consumer on electricity expenses with a storage device of 2 kWh. Moreover, emissions of carbon-dioxide from power generation processes can decrease by 6.3 percent.

The role of communication systems in smart grids: Architectures, technical solutions and research challenges

“…Among the various approaches that have been proposed so far to implement autonomic management capabilities in distributed environments, multi-agent systems (MAS in short) are the most popular in the smart grid research community [254,4,255,233]. This is also demonstrated by the large number of multi-agent systems that have been designed for a variety of smart grid applications, including power system restoration [256,257], fault diagnosis [258][259][260][261], management of distributed energy resources [262][263][264], demand-side management [265], management of energy storage systems [266,78], optimization of EV operations [267][268][269]53], substation automation [270], distribution control [271], network monitoring [272,261] and visualization [273], electricity market simulation [274,275], profiling of power generation and energy usage patterns [276], management of micro-grids and VPPs [277,262,62,278,279].…”

Distributed Recharging Rate Control for Energy Demand Management of Electric Vehicles

“…For example, Vytelingum et al [15] and Wei et al [16] attempt to present MAS based solution to manage micro storage devices including EVs. However, they do not consider the actual mechanism by which agents acquire energy and assume that agents can buy it at market price.…”

Designing a residential hybrid electrical energy storage system based on the energy buffering strategy

“…For example, Exarchakos et al study demand side management and profitability by optimizing the allocation of charge and discharge time of the EES system [9]. Wei et al use a multi-agent system to model the demand side management problem with EES systems, and solve this problem using an adaptive learning approach [10]. These research efforts assume the EES systems have a fixed round-trip efficiency (cycle efficiency).…”