Artificial intelligence-enabled probabilistic load demand scheduling with dynamic pricing involving renewable resource

In the context of the global green and low-carbon transformation, microgrids containing renewable energy have been widely developed. At present, renewable energy generation has the disadvantages of instability and low energy density. In addition, the high proportion of electric vehicles (EVs) connected to the state grid will cause different degrees of disturbance to its safe operation. Therefore, a coordinated operation strategy of EV and photovoltaic (PV)-energy-storage charging stations induced by dynamic electricity price considering carbon reduction benefit is proposed. On the power generation side, a dual-axis PV tracking control method with "fixed frequency + variable frequency" control is proposed. One day is used as a period to divide the time segments, and the same time segment uses the fixed frequency tracking method, while different time segments use the variable frequency tracking method to improve the power generation efficiency. On the electricity consumption side, a dynamic electricity price strategy is adopted, using the minimum carbon reduction cost as the reward function, optimizing the dynamic electricity price under the minimum carbon reduction cost using the deep deterministic policy gradient (DDPG) algorithm to promote the shifting of EV charging load to the effective hours of PV generation. In conclusion, the simulation analysis is carried out in Zibo City, and the generation capacity of the proposed tracking method on the power generation side is improved by about 32% compared with the fixed PV generation capacity. Compared with the time-of-use electricity price, the optimized dynamic electricity price under the minimum carbon reduction cost can better promote the load transfer and photoelectric consumption of EVs and reduce the carbon reduction cost.

Load management based on dynamic pricing has been advocated as a key approach for demand-side management in smart grids. By appropriately pricing energy, economic incentives are given to consumers to shift their usage away from peak hours, thereby limiting the amount of energy that needs to be produced. However, traditional pricing-based load management methods usually rely on the assumption that the statistics of the system dynamics (e.g. the time-varying electricity price, the arrival distribution of consumers' load demands) are known a priori, which is not true in practice. In this paper, we propose a novel price-dependent load scheduling algorithm which, unlike previous works, can operate optimally in systems where such statistical knowledge is unknown. We consider a power grid system where each consumer is equipped with an energy storage device that has the capability of storing electrical energy during peak hours. Specifically, we allow each consumer to proactively determine the amount of energy to purchase from the utility companies (or energy producers) while taking into consideration that its load demand and the electricity price dynamically vary over time in an a priori unknown manner. We first assume that all the dynamics are known and formulate the real-time load scheduling as a Markov decision process and systematically unravel the structural properties exhibited by the resulting optimal load scheduling policy. By utilizing these structural properties, we then prove that our proposed load scheduling algorithm can learn the system dynamics in an online manner and converge to the optimal solution. A distinctive feature of our algorithm is that it actively exploits partial information about the system dynamics so that less information needs to be learned than when using conventional reinforcement learning methods, which significantly improves the adaptation speed and the runtime performance. Our simulation results demonstrate that the proposed load scheduling algorithm achieves efficiency by more than 30% compared to existing state-of-the-art online learning algorithms.

In power systems, electrical consumers can become a significant source of flexibility, by adjusting their consumption according to grid’s needs while respecting their operational constraints. Consumers’ flexibility potential can be exploited through the submission of dynamic electricity prices. Such prices are able to describe the variable condition of the power system and are broadcast to the consumers in order to obtain a certain change in consumption. The formulation of effective dynamic prices requires the development of proper models that describe the price responsiveness of electrical consumers. In this paper, we propose a nonlinear prediction model for the dynamic electricity prices in demand response (DR) programs. Specifically, the nonlinear auto-regressive with exogenous input (NARX) model structure is used to learn from available data to predict appropriate electricity price signals. For the validation of the model (in an aggregate manner) in predicting consumers’ price-response, the data from 10 Danish households is utilised, which has provided by the Danish Transmission Service Operator (TSO) Energinet.

A novel method for harmonizing the advantages of dynamic retail electricity pricing with the protections of approved, regulated electricity tariffs is discussed and demonstrated. The method socializes and protects customers from long-term locational price variability that is unfair to those customers who are, by no fault of their own, served at congested locations on a distribution system. However, the method preserves short-term (e.g., diurnal) price variability that might induce helpful, mitigative responses from retail electricity customers. Because the method causes actual price recovery to track a customer class's approved, regulated price recovery, the method may remove regulators' objections to dynamic electricity pricing and thereby hasten adoption of market-based retail electricity pricing and transactive energy systems.

The load scheduling is a paramount concern in the cloud-based computing due to the involvement of conflicting parameters and fluctuating demands of users. Though the problem of load scheduling comes in the category of NP-hard problem, it is utmost essential to design a load scheduling approach to tackle the challenges in cloud computing. These challenges could be elevated by using metaheuristic approaches that offer an optimal solution to an NP-hard problem. In this research, authors propose a binary self-adaptive JAYA-based load scheduling algorithm to solve the dynamically independent load scheduling problem in cloud-based computing. The proposed algorithm is compared with the lately invented metaheuristic-based task scheduling algorithms such as bird swarm optimization (BSO), modified particle swarm optimization (MPSO), and the standard JAYA. The proposed algorithm is evaluated using a real-world dataset for the various QoS scheduling parameters to advocate the effectiveness of the algorithm. The simulated results show notable improvements over other compared algorithms for makespan, average resource utilization, and load-balancing.

This paper deals with a regional demand response method based on dynamic electricity pricing in a multi-period energy market. In the proposed method, first, the power demand and supply in each area are determined considering power flow using the retail and wholesale electricity prices in a day-ahead market. Next, to adjust for power deviations caused by errors in power generation, our proposed method solves the problem of optimal allocation between power demand reduction by consumers and increased power supply from balancing generators in a real-time market. This paper also shows a distributed algorithm for obtaining the optimal values of each market player in both the day-ahead and real-time markets, and finally, numerical simulation results demonstrate the effectiveness of the proposed method.

We consider joint energy storage management and load scheduling at a\nresidential site with integrated renewable generation. Assuming unknown\narbitrary dynamics of renewable source, loads, and electricity price, we aim at\noptimizing the load scheduling and energy storage control simultaneously in\norder to minimize the overall system cost within a finite time period. Besides\nincorporating battery operational constraints and costs, we model each\nindividual load task by its requested power intensity and service durations, as\nwell as the maximum and average delay requirements. To tackle this finite time\nhorizon stochastic problem, we propose a real-time scheduling and storage\ncontrol solution by applying a sequence of modification and transformation to\nemploy Lyapunov optimization that otherwise is not directly applicable. With\nour proposed algorithm, we show that the joint load scheduling and energy\nstorage control can in fact be separated and sequentially determined.\nFurthermore, both scheduling and energy control decisions have closed-form\nsolutions for simple implementation. Through analysis, we show that our\nproposed real-time algorithm has a bounded performance guarantee from the\noptimal T-slot look-ahead solution and is asymptotically equivalent to it as\nthe battery capacity and time period goes to infinity. The effectiveness of\njoint load scheduling and energy storage control by our proposed algorithm is\ndemonstrated through simulation as compared with alternative algorithms.\n

Due to the rapid development of the building stock in Norway, the energy use in this segment is drastically increasing. Therefore, improving the energy performance of buildings becoming an urgent problem. Among technical systems in buildings, domestic hot water (DHW) systems have still significant untapped potential for energy saving. Storage tanks enable us to change DHW demand in buildings in a more energy-efficient and cost-effective way. However, to achieve this effect, the proper sizing and operation of the storage tanks are required. The aim of this study was to define a method for the DHW tank size optimization considering dynamic electricity prices and to assess how different electricity pricing methods would influence the DHW tank size. A dynamic discretized model of the DHW tank was used as a DHW tank model. Dynamic optimization was implemented as the optimization method to find the optimal tank charging rate based on the different pricing methods. Two pricing methods were considered in this study: 1) the current method with the fixed grid fee and 2) the power extraction method with the pricing of the maximum power extraction. The results showed that the electricity pricing pattern had significant impact on the DHW charging heating rate. In the case of the extraction fee pricing method, the charging rate was more stable over the day than in the case of the fixed grid fee. This stable charging rate gave stable DHW tank temperature over the day and the highest decrease in the total cost. A general conclusion was that the extraction grid fee pricing method would promote for stable charging over the day.

Aggregating the Demand Flexibility Related to Electric Hot Water Heating Under Endogenous Day-Ahead Prices

Scheduling model of electric vehicles charging considering inconvenience and dynamic electricity prices

A charge-discharge optimization strategy considering the spatiotemporal distribution of electric vehicles and the operational safety of the power distribution network in the power-transportation coupling network

In the context of electricity and carbon markets, with the in-depth research of virtual power plants and to realize the mutual assistance of electric energy in different regions within the same distribution network, a scheduling strategy of virtual power plant alliance based on dynamic electricity and carbon pricing using the Master–Slave game is proposed. Firstly, an interactive framework of virtual power plant alliance is designed in which the alliance operator formulates the electricity and carbon prices, and each user entity formulates the operation plan according to the prices. Secondly, the information gap decision theory is adopted to handle the uncertainties on the source–load side. Based on the Master–Slave game and source–load interaction, an economic optimal dispatching model for the virtual power plant alliance is established. Finally, the particle swarm optimization algorithm nested with the CPLEX solver is used to solve the model, and the rationality and effectiveness of the proposed strategy are demonstrated through case analysis. The simulation results show that, after considering the electricity energy interaction and dynamic electricity–carbon pricing, the daily operation cost of the virtual power plant alliance was reduced by 47.7%, carbon emissions decreased by 24.6%, and comprehensive benefits increased by 77.2%.

Cloudy GSA for load scheduling in cloud computing

SGEESS: Smart green energy-efficient scheduling strategy with dynamic electricity price for data center

HVAC systems account for 50% of buildings’ energy use and could play a critical role in energy management in buildings both for energy-saving, and demand-side management to reduce peak energy use. According to contextual demands of occupants, efficient control of HVAC systems could result in peak energy saving and decreased energy costs in demand response programs. Accordingly, in this paper, we have introduced an agent-based model consisting of three agents: human agent, thermostat agent, and utility agent. In this model, the thermostat agent receives the real-time electricity price from the utility agent and aggregates thermal comfort profiles of the occupants from human agents. By considering these inputs, the thermostat agent employs a predictive model of a house and calculates the next set point of the HVAC system on energy cost and occupants’ comfort. Then, the thermostat agent signals the suggested set point to the thermostat of the building at each time step. For evaluating the proposed controller’s performance, the electricity price profile from ERCOT, which supplies the state of Texas, is used as a signal from the utility agent. Realistic thermal comfort data were used to simulate the thermal preference of occupants represented as human agents. The evaluation was carried out in a co-simulation using a Python and EnergyPlus model of a residential unit. Our results show that the proposed controller reduces the peak energy by 5.5% to 10% and increases occupants’ thermal satisfaction up to 12%. The main contribution of this paper is developing an agent-based model that humans, as the main stakeholders of the buildings, play a role in controlling HVAC systems for peak reduction and energy saving.