A Dynamic pricing demand response algorithm for smart grid: Reinforcement learning approach

In this paper, we study a dynamic pricing and energy consumption scheduling problem in the microgrid where the service provider acts as a broker between the utility company and customers by purchasing electric energy from the utility company and selling it to the customers. For the service provider, even though dynamic pricing is an efficient tool to manage the microgrid, the implementation of dynamic pricing is highly challenging due to the lack of the customer-side information and the various types of uncertainties in the microgrid. Similarly, the customers also face challenges in scheduling their energy consumption due to the uncertainty of the retail electricity price. In order to overcome the challenges of implementing dynamic pricing and energy consumption scheduling, we develop reinforcement learning algorithms that allow each of the service provider and the customers to learn its strategy without a priori information about the microgrid. Through numerical results, we show that the proposed reinforcement learning-based dynamic pricing algorithm can effectively work without a priori information about the system dynamics and the proposed energy consumption scheduling algorithm further reduces the system cost thanks to the learning capability of each customer.

/pdf/dynamic-pricing-and-energy-consumption-scheduling-with-1hs8psulvy.pdf

Dynamic Pricing and Energy Consumption Scheduling With Reinforcement Learning

The residential sector is a major contributor to the global energy balance. So far, the residential users demand has been largely uncontrollable and inelastic with respect to the power grid conditions. Demand Side Management (DSM) is an important function in smart grid that allows consumers to make informed decision regarding energy consumption, and helps energy providers to reshape the load profile and to reduce peak load demand. DSM can be mathematically formulated either to maximize the system total peak demand or to maximize overall system load factor and utility׳s revenue and to minimize customer electricity bill. This paper reviews the various optimization techniques applied to DSM as contrasting characteristics like individual users versus cooperative users, deterministic versus stochastic and day-ahead versus real time DSM. This paper reviews a survey on residential DSM, which can help general readers to have an outlook of the topic which includes the architecture, formulation of optimization problems and its various approaches. The issues, existing solutions and approaches are presented. In addition, the future research directions are also discussed to enhance the work in this domain.

A survey on residential Demand Side Management architecture, approaches, optimization models and methods

This paper proposes a reward based demand response algorithm for residential customers to shave network peaks. Customer survey information is used to calculate various criteria indices reflecting their priority and flexibility. Criteria indices and sensitivity based house ranking is used for appropriate load selection in the feeder for demand response. Customer Rewards (CR) are paid based on load shift and voltage improvement due to load adjustment. The proposed algorithm can be deployed in residential distribution networks using a two-level hierarchical control scheme. Realistic residential load model consisting of non-controllable and controllable appliances is considered in this study. The effectiveness of the proposed demand response scheme on the annual load growth of the feeder is also investigated. Simulation results show that reduced peak demand, improved network voltage performance, and customer satisfaction can be achieved.

Demand Response for Residential Appliances via Customer Reward Scheme

This paper focuses on developing an interdisciplinary mechanism that combines machine learning, optimization, and data structure design to build a demand response and home energy management system that can meet the needs of real-life conditions. The loads of major home appliances are divided into three categories: 1) containing fixed loads; 2) regulate-able loads; and 3) deferrable loads, based on which a decoupled demand response mechanism is proposed for optimal energy management of the three categories of loads. A learning-based demand response strategy is developed for regulateable loads with a special focus on home heating, ventilation, and air conditioning (HVACs). This paper presents how a learning system should be designed to learn the energy consumption model of HVACs, how to integrate the learning mechanism with optimization techniques to generate optimal demand response policies, and how a data structure should be designed to store and capture current home appliance behaviors properly. This paper investigates how the integrative and learning-based home energy management system behaves in a demand response framework. Case studies are conducted through an integrative simulation approach that combines a home energy simulator and MATLAB together for demand response evaluation.

An Optimal and Learning-Based Demand Response and Home Energy Management System

Demand response is a key feature of the smart grid. The addition of bidirectional communication to today's power grid can provide real-time pricing (RTP) to customers via smart meters. A growing number of appliance companies have started to design and produce smart appliances which embed intelligent control modules to implement residential demand response based on RTP. However, most of the current residential load scheduling schemes are centralized and based on either day-ahead pricing (DAP) or predicted price, which can deviate significantly from the RTP. In this paper, we propose an opportunistic scheduling scheme based on the optimal stopping rule as a real-time distributed scheduling algorithm for smart appliances' automation control. It determines the best time for appliances' operation to balance electricity bill reduction and inconvenience resulting from the operation delay. It is shown that our scheme is a distributed threshold policy when no constraint is considered. When a total power constraint exists, the proposed scheduling algorithm can be implemented in either a centralized or distributed fashion. Our scheme has low complexity and can be easily implemented. Simulation results validate proposed scheduling scheme shifts the operation to off-peak times and consequently leads to significant electricity bill saving with reasonable waiting time.

Shufang Li

Papers

Real-Time Opportunistic Scheduling for Residential Demand Response