Optimizing grid connected PV-Battery system for residential energy management system using deep learning

As the world energy crisis continues to burden our natural resources, it is imperative that current technologies be employed to make energy usage more efficient. In this paper, an intelligent residential home energy management system is discussed. A Master Energy Controller was developed to forecast future power demand based on user's life style and environmental/social factors affecting power consumption; this controller uses a branch and bound scheduling algorithm for managing appliance runtime schedules. Further, time-of-use pricing is employed to close the loop between the residential customer and the utility company. The focus of this paper is on how the appliance network architecture and master controller can link to the outside world through the internet. A gateway architecture is used for this interface and details of the communication process and message configurations are presented. This architecture provides a simple, yet powerful approach in linking each intelligent residential energy management system to an energy grid with the goal of improving energy usage.

Multi-agent-based decentralized residential energy management using Deep Reinforcement Learning

The main purpose of this study is to develop a sustainable smart energy management system for the desert climate, which aims to reduce energy expenses, energy consumption, and greenhouse gas (GHG) emissions via finding optimum power output and smart scheduling while considering users' uncertain behaviors. Moreover, the effectiveness of five metaheuristic optimization algorithms is analyzed and reviewed for presented system, which is modeled as a multiobjective function and contains over 1000 variables. The case study is city of Kashan located at the desert area of Iran with hot and dry climate. Presented system is established based on smart residential energy hub and home energy management system. Residential loads for a modern household are appropriately categorized and modelled. Ten different uncertain scenarios for users' energy consumption are simulated within the algorithm with considering users' comfort level simultaneously. Both energy cost and users' comfort deviation for studied multi-energy system are formulated as a multiobjective function with two weighting factors. Our results present a comparison between different cases studied and the effects of uncertain power consumption on energy cost, comfort level, and computing time. Our findings indicate that the presented system with specified weighting factors is able to reduce energy expenses around 50% in different cases. Accordingly, due to a noticeable decrease in energy consumption, GHG emissions from fossil fuels are reduced remarkably considering the fact that only 1% of Iran's power supply is provided by clean energies. Results also illustrate that considering uncertainty has more effect on users' comfort level than energy cost.

The increasing power demand and the emergence of smart grids have given access to new opportunities for the energy management system of smart residential buildings that can reduce energy usage. Demand Response (DR) program is one of the most important strategies for implementing the residential building energy management system. The consumer load gets modified depending upon the electricity price provided by the utility so that the consumer electricity bill decreases. This strategy decreases the peak demand by scheduling the schedulable loads from the period when the electricity prices are high for the period when the prices are low with minimal effect on consumer comfort. It reduces the demand and increases the effective utilization of the energy of a residential building. This paper proposes an Effective Energy Management System (E-EMS) for residential buildings that models the problem by considering the uninterruptable and interruptible residential load appliances which can be controlled and their shifting windows constraints. It also manages the battery bank operation for maximum utilization of energy stored so that the wastage of power through dump load is minimum depending upon the Power Export Limit (PEL) defined by the utility. Further, the optimal sizing of renewable energy resources is also carried out for choosing the size of renewable energy resources and battery banks for effective utilization. The results of the proposed system are simulated by using MATLAB software to verify the effectiveness of the proposed strategy to control household appliances and their energy consumption by using BPSO.

Introduction. The significance of machine learning under the conditions of digital transformation of industry, and methods of implementing deep learning to provide the performance of trust management systems are considered. The necessity of using convolutional artificial neural networks for deep machine learning is determined. Various technologies and architectures for the implementation of artificial neural networks are briefly considered; a comparative analysis of their performance is carried out. The work objective is to study the need to develop new approaches to the architecture of computing machines for solving problems of deep machine learning in the trust management system implementation.Materials and Methods. In the context of digital transformation, the use of artificial intelligence reaches a new level. The technical implementation of artificial neural systems with deep machine learning is based on the use of one of three basic technologies: high performance computing (HPC) with parallel data processing, neuromorphic computing (NC), and quantum computing (QC).Results. Implementation models for deep machine learning, basic technologies and architecture of computing machines, as well as requirements for trust assurance in control systems using deep machine learning are analyzed. The problem of shortage of computation power for solving such problems is identified. None of the currently existing technologies can solve the full range of learning and impedance problems. The current level of technology does not provide information security and reliability of neural networks. The practical implementation of trust management systems with deep machine learning based on existing technologies for a significant part of the tasks does not provide a sufficient level of performance.Discussion and Conclusions. The study made it possible to identify the challenge of the computation power shortage for solving problems of deep machine learning. Through the analysis of the requirements for trust management systems, the external challenges of their implementation on the basis of existing technologies, and the need to develop new approaches to the computer architecture are determined.

Cost-effective and comfort-aware residential energy management under different pricing schemes and weather conditions

In this paper, we apply adaptive dynamic programming to the residential energy system control and management, with an emphasis on home battery use connected to power grids. The proposed scheme is built upon a self-learning architecture with only a single critic module instead of the action-critic dual module architecture. The novelty of the present scheme is its ability to improve the performance as it learns and gains more experience in real-time operations under uncertain changes of the environment. Simulation results demonstrate that the proposed scheme can achieve the minimum electricity cost for residential customers.

Computational tools for design, analysis, and management of residential energy systems

An adaptive fuzzy logic system for residential energy management in smart grid environments

Deep learning networks were employed to predict the maximum differential deflection of stiffened and waffle rafts due to reactive soil movements, Δmax. Four deep learning networks were used to predict Δmax, these are (1) stiffened rafts on shrinking soil, (2) stiffened rafts on swelling soil, (3) waffle rafts on shrinking soil, and (4) waffle rafts on swelling soil. The deep learning models were used to create design lines, which showed that both soil and structural features strongly influence the stiffened rafts. In contrast, waffle rafts showed a strong dependence on soil features in shrinking soils and beam depth in swelling soils. This demonstrates that the finite element-based deep learning networks captured the effect of the embedment of the beams. The results of the deep learning models led to non-linear design curves, which are disparate from the suggested standard Australian design. These results suggest that increasing the value of beam depth can have a positive or negative impact on the global residential slab depending on the type of substructure and whether the founding reactive soil is shrinking or swelling. Global sensitivity analyses of the deep learning models showed that for stiffened rafts on shrinking soil, the slab length, slab width and active depth zone of reactive soil had the most significant influence on Δmax, whilst for stiffened rafts on swelling soil, the primary drivers are ground movement, beam depth, and slab width. The prediction of Δmax for waffle rafts on shrinking soil was driven by the surface characteristic and mound movements, and the active depth zone, whilst waffle rafts on swelling soil was driven by the beam depth. Overall, the finite element-based deep learning showed the capacity to estimate Δmax in both shrinking and swelling design scenarios for different types of residential footing systems to further understand the characteristic behaviour of shallow residential slab foundations on reactive soils leading to improved designs.

Increasing incorporation of intermittent Renewable Energy Sources (RES) in grid systems has engendered the need for intelligent control of power flow. The variation of load demand, number of controllable units and intermittent nature of the RES makes power management in grid-tied RES-based microgrids a challenging task. With the recent advances in Deep Learning (DL) architecture, Deep Neural Network (DNN) based Deep Reinforcement Learning (DRL) algorithms have become effective at solving the power management problem in Grid-Tied Microgrids (GT-MGs). This paper proposes such an intelligent RL control approach to tackle the intermittent and stochastic nature of the RES and load demand to produce optimal power management in GT-MGs. We consider a residential Solar-Energy Storage System (ESS) MG, which can buy and sell power to the grid. We propose a Deep Long-Short Term Memory (DeepLSTM) network to approximate the Q-function in RL and compare its performance with Deep Q-Network (DQN) based RL approach. The goal in both approaches is to reduce the overall cost of operation for the GT-MG. Results show that the designed reward scheme produces better performance in the proposed DeepLSTM approach while meeting all operational constraints.

Optimal sizing of residential battery energy storage systems for long-term operational planning

Residential community with PV and batteries: Reserve provision under grid constraints

An AI based energy management system (EMS) for microgrids is proposed. It is composed of three modules: a strategy based module, a deep learning (DL) and a reinforcement learning module (RL). This framework determines heuristically the optimal actions for the microgrid system under different time-dependent environmental conditions. In essence, a main innovation is applied to the EMS. Our deep learning algorithm uses recurrent neural networks (RNNs) instead of the habitual State Action Reward (SAR) approach (whether classical or deep). Learning is hence guided by successful actions rather than by blind exploration. A large improvement in learning rates is hence observed when compared to classical Q-learning on real datasets that present a large diversity in energy consumption profiles, acquired in French premises over a long period. It leads to question about the best appropriate reinforcement policies to adopt when solving large state environments.

In Australia, the penetration of rooftop photovoltaic (PV) systems with storage is expected to increase in the future because of rising electricity costs, decreasing capital costs and growing concerns about climate change. Residential energy users can seize the full financial benefits of these systems by using an automated energy management system (EMS) to schedule and coordinate their energy use. An important aspect of an effective EMS is to control the battery state of charge, taking into consideration of the intermittent nature of PV generation and variability of electrical demand over a decision horizon of several days. However, this is difficult because of the computational burden associated with the currently proposed solution techniques. Given these existing shortcomings, this paper evaluates a two-stage stochastic optimisation framework for energy management of residential PV-storage systems to identify the benefits of having a longer decision horizon. That is: a simplified longer-horizon solver that uses stochastic mixed-integer linear programming (MILP) and a more detail shorter horizon solver using dynamic programming. In doing so, this paper discusses the general benefits of residential PV-storage systems coupled with an EMS.