Search

In this paper, a decentralized energy management system is presented for intelligent microgrids with the presence of distributed resources using reinforcement learning. Due to the unpredictable nature of renewable energy resources, the variability of load consumption, and the nonlinear model of batteries, the design of a microgrid energy management system is associated with many challenges. In addition, centralized control structures in large-scale systems increase computational volume and complexity in control algorithms. In this paper, a fully decentralized multi-agent structure for a microgrid energy management system is proposed and the Markov decision process is used to model the stochastic behavior of agents in the microgrid. Electrical and thermal distributed resources, batteries, and consumers are considered intelligent and independent agents. They have the learning ability to explore and exploit the environment in a fully decentralized manner and achieve their optimal policies. The proposed method for hourly microgrid management is model-independent and based on learning. The method maximizes the profits of all manufacturers, minimizes consumer costs, and reduces the dependence of the microgrid on the maingrid. Finally, using real data from renewable energy sources and consumers, the accuracy of the proposed method in the Iranian electricity market is simulated and verified. [ABSTRACT FROM AUTHOR]

Traditionally, photovoltaic power plants use Maximum Power Point Tracking (MPPT) algorithms to produce maximum electrical energy. However, with the increase of grid-installed photovoltaic power plants, power system operators have faced new challenges such as overload, overvoltage, and proper performance during grid voltage disturbances. As a result, network standards and codes have been updated in the direction of photovoltaic systems that are more controllable and compatible with the network. To provide various grid support functions, such as frequency response and voltage support, the Constant Power Generation (CPG) control algorithm is established by grid codes. For this purpose, MPPT algorithms have been replaced by flexible power point tracking (FPPT) algorithms. This paper proposes an algorithm to control photovoltaic systems based on a multi-level cascaded full-bridge (CHB) inverter to achieve constant power generation control by the FPPT method. The required power reference is distributed among the sub-modules of the CHB converter according to the available power of each sub-module in such a way that, as much as possible, each sub-module is loaded equally. Then, the FPPT algorithm with an adaptive voltage step is used to set the power of each submodule in its reference value. The voltage step is calculated adaptively based on the observed condition (transient or steady state) so that the tracking performance has fast dynamics. The effectiveness of the proposed algorithm is evaluated by simulating a 500-kW photovoltaic system directly connected to a 4.7 kV grid. [ABSTRACT FROM AUTHOR]