Real Time Demand Response Modeling for Residential Consumers in Smart Grid Considering Renewable Energy With Deep Learning Approach

Abstract

Demand response modelling have paved an important role in smart grid at a greater perspective. DR analysis exhibits the analysis of scheduling of appliances for an optimal strategy at the user's side with an effective pricing scheme. In this proposed work, the entire model is done in three different steps. The first step develops strategy patterns for the users considering integration of renewable energy and effective demand response analysis is done. The second step in the process exhibits the learning process of the consumers using Robust Adversarial Reinforcement Learning for privacy process among the users. The third step develops optimal strategy plan for the users for maintaining privacy among the users. Considering the uncertainties of the user's behavioral patterns, typical pricing schemes are involved with integration of renewable energy at the user' side so that an optimal strategy is obtained. The optimal strategy for scheduling the appliances solving privacy issues and considering renewable energy at user' side is done using Robust Adversarial Reinforcement learning and Gradient Based Nikaido-Isoda Function which gives an optimal accuracy. The results of the proposed work exhibit optimal strategy plan for the users developing proper learning paradigm. The effectiveness of the proposed work with mathematical modelling are validated using real time data and shows the demand response strategy plan with proper learning access model. The results obtained among the set of strategy develops 80 % of the patterns created with the learning paradigm moves with optimal DR scheduling patterns. This work embarks the best learning DR pattern created for the future set of consumers following the strategy so privacy among the users can be maintained effectively.INDEX TERMS Demand response, best strategy, robust adversarial reinforcement learning, renewable energy. NOMENCLATURE n i S -Strategy for set of users In -Incentives announced () n  -cost function for the model and   -Best policy parameters for learning , tt hl -reward and incentive function in learning i   -Policy strategy ( , ) n v  -Optimization function for pricing and cost analysis RL-Reinforcement Learning ADP -Approximate Dynamic Programming RARL -Robust Adversarial Reinforcement learning GNI -Gradient Based Nikaido -Isoda Function

A novel information gap decision theory‐based demand response scheduling for a smart residential community considering deep uncertainties

“…In (29), T Ch∕Dis 1 and T Ch∕Dis 2 express the arrival time of EVs and the last hour they can be charged in only the charging and discharging programs, respectively. Since EVs cannot be charged and discharged simultaneously two binary variables, 𝛽 Ch cd ,t , 𝛽 Dis cd ,t , are defined to choose only one charging and discharging mode every hour, as shown in (30). EVs' charging and discharging powers are restricted by (31) and (32), respectively.…”

“…Most robust optimization methods consider fully risk attitudes in the uncertainty aspects of a stochastic model, and these methods are just for models with PDF. An optimal strategy for scheduling the appliances solving privacy issues, and considering integration of RESs at the user side is proposed using Robust Adversarial Reinforcement Learning and the Gradient‐based Nikaido‐Isoda function in [30]. This work considers the uncertainties of the user's behavioural patterns, and the authors claim that privacy among the users maintains effectively.…”

Combating Uncertainties in Wind and Distributed PV Energy Sources Using Integrated Reinforcement Learning and Time-Series Forecasting

“…The ultimate goal of the PA is to learn a policy to minimize the total electricity bill in Eq. (7), in the presence of PV generation and price uncertainties. For the PA, to deal with the uncertainty in future price, we observe the past 𝑁-step of the electricity price.…”

“…Additionally, to solve the energy management in smart grid, mathematical model-based programming approaches, such as mixed-integer linear programming (MILP), and dynamic and stochastic programming have been widely used [5,6]. Recently, model-free reinforcement learning (RL) techniques have attracted significant interests in dynamic energy management applications such as home energy management, EV charge controls, and battery optimization since they do not require an explicit model of the environment [7]. However, the problem of integrating RES uncertainty with dynamic energy management by RL, while integrating wholesale and retail market uncertainties that are highlighted in some works [8,9], is not fully explored yet.…”

Cost-Effective Design of IoT-Based Smart Household Distribution System

“…Worldwide energy demand has been significantly augmented over the last few years due to the increased population and rapid industrial advancement. As such, renewable energy sources have been widely employed at both industry and residential levels [1,2]. As a result, the traditional consumer market has been changed into prosumer-oriented market [3,4].…”