An integrated neural network for the dynamic domestic energy management of a solar house

Drir, N.; Chekired, Fathia; Rekioua, Djamila

doi:10.1002/2050-7038.13227

Cited by 7 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to meet the energy requirements of residential users and improve the performance of electrical networks, ref. [23] develops an enhanced control system using artificial neural network (ANN) ideas. The Levenberg-Marquardt algorithm provides connectivity in this method's multi-level feedback network (MLFN), which allows data and calculations to flow from input to output in a predetermined manner.…”

Section: Literature Reviewmentioning

confidence: 99%

An Artificial Neural Network-Based Approach for Real-Time Hybrid Wind–Solar Resource Assessment and Power Estimation

et al. 2023

View full text Add to dashboard Cite

The precise prediction of power estimates of wind–solar renewable energy sources becomes challenging due to their intermittent nature and difference in intensity between day and night. Machine-learning algorithms are non-linear mapping functions to approximate any given function from known input–output pairs and can be used for this purpose. This paper presents an artificial neural network (ANN)-based method to predict hybrid wind–solar resources and estimate power generation by correlating wind speed and solar radiation for real-time data. The proposed ANN allows optimization of the hybrid system’s operation by efficient wind and solar energy production estimation for a given set of weather conditions. The proposed model uses temperature, humidity, air pressure, solar radiation, optimum angle, and target values of known wind speeds, solar radiation, and optimum angle. A normalization function to narrow the error distribution and an iterative method with the Levenberg–Marquardt training function is used to reduce error. The experimental results show the effectiveness of the proposed approach against the existing wind, solar, or wind–solar estimation methods. It is envisaged that such an intelligent yet simplified method for predicting wind speed, solar radiation, and optimum angle, and designing wind–solar hybrid systems can improve the accuracy and efficiency of renewable energy generation.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

An Artificial Neural Network-Based Approach for Real-Time Hybrid Wind–Solar Resource Assessment and Power Estimation

et al. 2023

View full text Add to dashboard Cite

show abstract

“…For t � 1: 24 (7) Each agent senses the states of the environment (8) Te demand is predicted by the exponential random distribution (9) Te outputs of wind and PV are determined. (10) Each agent takes random actions with the probability 1and selects the best action with the probability based on Q i 0 (11) MO clears the market (12) Each agent observes its immediate reward (13) Te Q L,i 1 -function for each agent is updated according to equation (6) ( 14) End (15) End //end exploration period (16)…”

Section: Numerical Studymentioning

confidence: 99%

“…In [7], a dynamic EMS has been developed using the adaptive dynamic programming approach, in which the critical loads were supplied at all times. A home EMS based on Levenberg-Marquardt algorithm has been presented to optimize the customers' performance in presence of a grid-connected photovoltaic system with a battery energy storage system in [8]. An energy management structure based on the Nash Qlearning algorithm has been used in [9] to manage all the DERs.…”

Section: Introductionmentioning

confidence: 99%

Decentralized Reinforcement Learning Approach for Microgrid Energy Management in Stochastic Environment

Darshi

Shamaghdari

Jalali

et al. 2023

International Transactions on Electrical Energy Systems

View full text Add to dashboard Cite

Microgrids are considered to be smart power grids that can integrate Distributed Energy Resources (DERs) in the main grid cleanly and reliably. Due to the random and unpredictable nature of Renewable Energy Sources (RESs) and electricity demand, designing a control system for microgrid energy management is a complex task. In addition, the policies of microgrid agents are changing over time to improve their expected profits. Therefore, the problem is stochastic and the policies of the agents are not stationary and deterministic. This paper proposes a fully decentralized multiagent Energy Management System (EMS) for microgrids using the reinforcement learning and stochastic game. The microgrid agents, comprising customers, and DERs are considered as intelligent and autonomous decision makers. The proposed method solves a distributed optimization problem for each self-interested decision maker. Interactions between the decision makers and the environment during the learning phase lead the system to converge to the optimal equilibrium point in which the benefits of all the agents are maximized. Simulation studies using a real dataset demonstrate the effectiveness of the proposed method for the hourly energy management of microgrids.

show abstract

“…For given data of the produced energy and the consumed energy, as well as the State of Charge of the battery at time t, the system supplies appliances according to their priority of use [15]. These load groups are active and available according to the modes established during the energy flow management as shown in Table 3.…”

Section: Groups By Priority Appliancesmentioning

confidence: 99%

“…In order to improve HEM systems, several algorithms have been developed [12][13][14]. Some of them are based on demand response (DR), in which the priority of use of diverse loads is taken into consideration [15]. Other algorithms are based on optimization methods in the management of domestic loads in order to decrease the consumer's electricity bill by minimizing consumption and ensuring user comfort [11].…”

Section: Introductionmentioning

confidence: 99%

Near-Zero-Energy Building Management Based on Arduino Microcontroller—On-Site Lighting Management Application

et al. 2022

Self Cite

View full text Add to dashboard Cite

Near-Zero-Energy Buildings are a challenge in terms of energy production, storage, consumption and management, but these technological solutions remain financially difficult to access in developing countries. To this end, a complete low-cost and reliable home energy-management prototype was first developed and implemented on a scale model. A PWM charge controller drove the flow of energy produced and consumed in order to ensure the optimization of both the consumption of energy and energy savings. Battery storage was also managed by the home automation module using a set of sensors. The prototype of the scale model incorporated complete energy management of all electrical devices with group priorities through a graphical interface in a real-time mode. After testing this system, the lighting management part was implemented in a large-scale smart solar home. A smart lighting system via a complete algorithm integrated on an Arduino Mega board was then realized and implemented in the life-size house. This first step focuses, above all, on the users’ comfort and, in particular, on the lighting management. The results show that this smart device thus makes it possible to achieve additional energy savings on an essential and yet already energy-efficient device: lighting.

show abstract

An integrated neural network for the dynamic domestic energy management of a solar house

Cited by 7 publications

References 26 publications

An Artificial Neural Network-Based Approach for Real-Time Hybrid Wind–Solar Resource Assessment and Power Estimation

An Artificial Neural Network-Based Approach for Real-Time Hybrid Wind–Solar Resource Assessment and Power Estimation

Decentralized Reinforcement Learning Approach for Microgrid Energy Management in Stochastic Environment

Near-Zero-Energy Building Management Based on Arduino Microcontroller—On-Site Lighting Management Application

Contact Info

Product

Resources

About