Power Scheduling Problem Research Articles

Energy management method for battery swapping station combining reinforcement learning and mathematical optimization

Abstract The rapid proliferation of electric vehicles has spurred the expansion of scalable Battery Swapping Station (BSS) to cater to the demand for swift charging. However, the current energy management faces challenges in coping with the fluctuation of charging batteries in scalable BSS, the unpredictability of electricity prices and battery demand, as well as the intricacy of demand response. So, this paper presents a two-layer optimization framework for energy management in scalable BSS. The framework decomposes the power scheduling problem in BSS into two subproblems and solves them with deep reinforcement learning and mathematical optimization. The upper layer uses deep reinforcement learning to schedule the BSS’s total power, while the lower layer uses mathematical optimization to allocate the power to each charging pile. The two layers cooperate to achieve an efficient solution. The experiments demonstrate that the proposed method can reduce the operating cost of the BSS, satisfy the safety and user’s demand, and facilitate grid demand response, in BSSs of different sizes. The method is an effective solution for power scheduling of scalable BSS.

Deep contextual reinforcement learning algorithm for scalable power scheduling

This article introduces a deep contextual reinforcement learning (DCRL) optimization algorithm to tackle the NP-hard power scheduling problem. The algorithm is based on a multi-agent simulation environment that decomposes the power scheduling problem into sequential Markov decision processes (MDPs). The simulation environment inherently corrects incorrect decisions and adjusts supply capacities so that the MDPs adhere to the optimization constraints. A deep reinforcement learning (DRL) model is trained on these MDPs to provide optimal solutions. Demonstrating its applicability and effectiveness, the proposed method is evaluated on various test systems with different unit numbers, constraints, and production cost functions. The experimental results show that the proposed method has better performance relative to alternative methods, such as binary alternative moth-flame optimization (BAMFO), binary particle swarm optimization (BPSO), teaching learning-based optimization (TLBO), new binary particle swarm optimization (NBPSO), binary learning particle swarm optimization (BLPSO), quasi-oppositional teaching learning-based algorithm (QOTLBO), binary-real-coded genetic algorithm (BRCGA), hybrid genetic-imperialist competitive algorithm (HGICA), three-stage priority list (TSPL), and hybridized evolutionary algorithm and sequential quadratic programming (HEPSQP). The novelties of the proposed method lie in its adaptability to longer planning horizons and linear dimensionality complexity, rendering it suitable for large-scale power systems.

Reinforcement learning-based optimization for power scheduling in a renewable energy connected grid

Power scheduling is an NP-hard optimization problem that demands a delicate equilibrium between economic costs and environmental emissions. In response to the growing concern for climate change, global environmental policies prioritize decarbonizing the electricity sector by integrating renewable energies (REs) into power grids. While this integration brings economic and environmental benefits, the intermittency of REs amplifies the uncertainty and complexity of power scheduling. Existing optimization approaches often grapple with a limited number of units, overlook critical parameters, and disregard the intermittency of REs. To address these limitations, this article introduces a robust and scalable optimization algorithm for renewable integrated power scheduling based on reinforcement learning (RL). In this proposed methodology, the power scheduling problem is decomposed into Markov decision processes (MDPs) within a multi-agent simulation environment. The simulated MDPs are used to train a deep reinforcement learning (DRL) model for solving the optimization. The validity and effectiveness of the proposed method are validated across various test systems, encompassing single-to tri-objective problems with 10–100 generating units. The findings consistently demonstrate the superior performance of the proposed DRL algorithm compared to existing methods, such as multi-agent immune system-based evolutionary priority list (MAI-EPL), binary real-coded genetic algorithm (BRCGA), teaching learning-based optimization (TLBO), quasi-oppositional teaching learning-based algorithm (QOTLBO), hybrid genetic-imperialist competitive algorithm (HGICA), three-stage priority list (TSPL), real-coded grey wolf optimization (RCGWO), multi-objective evolutionary algorithm based on decomposition (MOEAD), and non-dominated sorting algorithms (NSGA-II and NSGA-III). Regarding the experimental results, it is important to highlight the importance of integrating RESs into larger power systems. In a 10-unit system with 2.81 % RE penetration, reductions of 3.42 %, 4.03 %, and 3.10 % were observed in costs, CO2 emissions, and SO2 emissions, respectively. Similarly, in a 100-unit system with a RE penetration rate of only 0.28 %, reductions of 3.75 % in cost, 4.42 % in CO2, and 3.34 % in SO2 were observed. These findings emphasize the effectiveness of RES integration, even at lower penetration rates, in larger-scale power systems.

Maximum Completion Time Optimization in Uplink Multi-Subcarrier NOMA Systems

Maximum completion time is a key performance metric for future wireless applications that have stringent latency requirements. This letter studies its optimization in uplink multi-subcarrier non-orthogonal multiple access (NOMA) networks. The joint optimization problem of power allocation, user pairing and scheduling is analyzed and proved to be NP-hard. To tackle the problem, the power allocation subproblem for a single NOMA pair is first derived. Next, for the joint user pairing and scheduling subproblem, an optimal algorithm for a special case is constructed and a suboptimal algorithm for the general case is designed. Our proposed scheme is applicable to data aggregation in wireless federated learning networks, and simulation results validate its superior performance.

A multi‐agent privacy‐preserving energy management framework for renewable networked microgrids

AbstractThis paper proposes a fully distributed scheme to solve the day‐ahead optimal power scheduling of networked microgrids in the presence of different renewable energy resources, such as photovoltaics and wind turbines, considering energy storage systems. The proposed method enables the optimization of the power scheduling problem through local computation of agents in the system and private communication between existing agents, without any centralized scheduling unit. In this paper, a cloud‐fog‐based framework is also introduced as a fast and economical infrastructure for the proposed distributed method. The suggested optimized energy framework proposes an area to regulate and update policies, detect misbehaving elements, and execute punishments centrally, while the general power scheduling problem is optimized in a distributed manner using the proposed method. The suggested cloud‐fog‐based method eliminates the need to invest in local databases and computing systems. The proposed scheme is examined on a small‐scale microgrid and also a larger test networked microgrid, including 4 microgrids and 15 areas in a 24‐h time period, to illustrate the scalability, convergence, and accuracy of the framework. The simulation results substantiate the fast and precise performance of the proposed framework for networked microgrids compared with other existing centralized and distributed methods.

Energy-Efficient Optimal Sensor Scheduling for State Estimation Over Multihop Sensor Networks.

In this article, we consider the power scheduling problem of the multihop transmission with limited power resources. For a discrete-time linear time-invariant process, we consider a more practical scenario where the forward-error-correcting (FEC) coding scheme is utilized. An approximate communication model is introduced to formulate the nonanalytical relationship between the consumption of power and the successful-decoding-probability. For the single-hop transmission, we propose an analytical method to figure out the optimal offline scheduling for the finite-time case and the optimal periodic schedule for the infinite-time case. We consider the process and terminal errors simultaneously, and explicitly discuss how different values of parameters affect the optimality. Moreover, we extend our conclusions to the multihop case. In order to deal with the difficulty and complexity brought by the multihop scenario, a novel method based on the equivalent-scheduling matrix (ESM) is proposed to describe the accumulated effects through the multihop transmission. Meanwhile, explicit solutions of the multihop case are provided for finite- and infinite-time cases, respectively. Numerical examples are provided to demonstrate the effectiveness of the proposed methods.

Design of topic priority based on industrial publish-subscribe system

As the size of the industrial systems increases, more and more topic messages need to be published and subscribed to in industrial scenarios such as microgrids and manufacturing industries. A priority scheduling algorithm based on the hotness of message topics is proposed to address the problem of efficient distribution of messages with different topics in microgrids. It is an algorithm that gives different priority permissions according to the number of topics, so that in the face of a large number of different topic messages, the data messages with a higher number or urgency can be transmitted first, solving the problem of port blocking when the server distributes the messages. At the same time, to prevent low priority data from sending timeout or waiting for a long time, a time period is set up, a low priority transmission mechanism is set up within a specific time period to ensure that the system can send data to customers in a timely and accurate manner. The results show that the priority design in this paper can well solve the power scheduling problem of multi-target data transmission and ensure the transmission efficiency of messages in the microgrid system.

Multiobjective Decision-Making Model for Power Scheduling Problem in Smart Homes

The aim of this study was to solve power scheduling issues in smart homes to enable demand response in smart grids. The objective of demand response is to match demand with supply by reflecting supply expectations through consumer price signals, and especially to avoid peak demand during times of high prices and when supply is limited. Three objectives were considered: first, economic rationing by minimizing the total costs for consumers with the given hourly prices; second, to achieve better efficiency in terms of supply and greater stability in a power system by reducing peaks in usage or load, which is defined by minimizing the percentage of power rate; third, related to consumer comfort levels, by reducing variance in the schedule of appliances to actual usage periods requested. This multiobjective power scheduling problem for smart homes (PHPSH) was explored using a nondominated sorting genetic algorithm, called NSGA-II. The results showed that the Pareto-optimal solutions from NSGA-II are compatible with the weighted-sum-based model from the literature, and viable alternatives are available for end users with different weighted objectives.

Online computation offloading with double reinforcement learning algorithm in mobile edge computing

Smart mobile devices have recently emerged as a promising computing platform for computation tasks. However, the task performance is restricted by the computing power and battery capacity of mobile devices. Mobile edge computing, an extension of cloud computing, solves this problem well by providing computational support to mobile devices. In this paper, we discuss a mobile edge computing system with a server and multiple mobile devices that need to perform computation tasks with priorities. The limited resources of the mobile edge computing server and mobile device make it challenging to develop an offloading strategy to minimize both delay and energy consumption in the long term. To this end, an online algorithm is proposed, namely, the double reinforcement learning computation offloading (DRLCO) algorithm, which jointly decides the offloading decision, the CPU frequency, and transmit power for computation offloading. Concretely, we first formulate the power scheduling problem for mobile users to minimize energy consumption. Inspired by reinforcement learning, we solve the problem by presenting a power scheduling algorithm based on the deep deterministic policy gradient (DDPG). Then, we model the task offloading problem to minimize the delay of tasks and propose a double Deep Q-networks (DQN) based algorithm. In the decision-making process, we fully consider the influence of task queue information, channel state information, and task information. Moreover, we propose an adaptive prioritized experience replay algorithm to improve the model training efficiency. We conduct extensive simulations to verify the effectiveness of the scheme, and the simulation results show that compared with the conventional schemes, our method reduces the delay by 48% and the energy consumption by 53%.

Power Allocation for Remote Estimation Over Known and Unknown Gilbert-Elliott Channels

In this paper, we consider the problem of power scheduling of a sensor that transmits over a (possibly) unknown Gilbert-Elliott (GE) channel for remote state estimation. The sensor supports two power modes, namely low power, and high power. The scheduling policy determines when to use low power or high power for data transmission over a fading channel with temporal correlation while satisfying the energy constraints. Although error-free acknowledgement/negative-acknowledgement (ACK/NACK) signals are provided by the remote estimator, they only provide meaningful information about the underlying channel state when low power is utilized. This leads to a partially observable Markov decision process (POMDP) problem and we derive conditions that preserve the optimality of a stationary schedule derived for its fully observable counterpart. However, implementing this schedule requires knowledge of the parameters of the GE model which are not available in practice. To address this, we adopt a Bayesian framework to learn these parameters online and propose an algorithm that is shown to satisfy the energy constraint while achieving near-optimal performance via simulation.

Hybrid multi-verse optimizer with grey wolf optimizer for power scheduling problem in smart home using IoT

Hybrid multi-verse optimizer with grey wolf optimizer for power scheduling problem in smart home using IoT

A Modified Coronavirus Herd Immunity Optimizer for the Power Scheduling Problem

The Coronavirus herd immunity optimizer (CHIO) is a new human-based optimization algorithm that imitates the herd immunity strategy to eliminate of the COVID-19 disease. In this paper, the coronavirus herd immunity optimizer (CHIO) is modified to tackle a discrete power scheduling problem in a smart home (PSPSH). PSPSH is a combinatorial optimization problem with NP-hard features. It is a highly constrained discrete scheduling problem concerned with assigning the operation time for smart home appliances based on a dynamic pricing scheme(s) and several other constraints. The primary objective when solving PSPSH is to maintain the stability of the power system by reducing the ratio between average and highest power demand (peak-to-average ratio (PAR)) and reducing electricity bill (EB) with considering the comfort level of users (UC). This paper modifies and adapts the CHIO algorithm to deal with such discrete optimization problems, particularly PSPSH. The adaptation and modification include embedding PSPSH problem-specific operators to CHIO operations to meet the discrete search space requirements. PSPSH is modeled as a multi-objective problem considering all objectives, including PAR, EB, and UC. The proposed method is examined using a dataset that contains 36 home appliances and seven consumption scenarios. The main CHIO parameters are tuned to find their best values. These best values are used to evaluate the proposed method by comparing its results with comparative five metaheuristic algorithms. The proposed method shows encouraging results and almost obtains the best results in all consumption scenarios.

A Software Defined Networking Architecture for DDoS-Attack in the Storage of Multimicrogrids

Multi-microgrid systems can improve the resiliency and reliability of the power system network. Secure communication for multi-microgrid operation is a crucial issue that needs to be investigated. This paper proposes a multi-controller software defined networking (SDN) architecture based on fog servers in multi-microgrids to improve the electricity grid security, monitoring and controlling. The proposed architecture defines the support vector machine (SVM) to detect the distributed denial of service (DDoS) attack in the storage of microgrids. The information of local SDN controllers on fog servers is managed and supervised by the master controller placed in the application plane properly. Based on the results of attack detection, the power scheduling problem is solved and send a command to change the status of tie and sectionalize switches. The optimization application on the cloud server implements the modified imperialist competitive algorithm (MICA) to solve this stochastic mixed-integer nonlinear problem. The effective performance of the proposed approach using an SDN-based architecture is evaluated through applying it on a multi-microgrid based on IEEE 33-bus radial distribution system with three microgrids in simulation results.

Multi-objective real-time integrated solar-wind-thermal power dispatch by using meta-heuristic technique

<abstract> <p>The elevated demand for electrical power, expeditious expenditure of fossil fuels, and degradation of the environment because of power generation have renewed attentiveness to renewable energy resources (RER). The rapid augmentation of RER increases the convolutions in leveling the demand and generation of electrical power. In this paper, an elaborated $ \alpha $-constrained simplex method (ACSM) is recommended for multi-objective power dispatch problems. This methodology is devised after synthesizing the non-linear simplex method (SM) with the $ \alpha $-constrained method (ACM) and the evolutionary method (EM). ACSM can transfigure an optimization technique for the constrained problems by reinstating standard juxtapositions with $ \alpha $-level collations. The insertion of mutations and multi-simplexes can explore the periphery of the workable zone. It can also manage the fastness of convergence and therefore, the high precision solution can be obtained. A real-time multi-objective coordinated solar-wind-thermal power scheduling problem is framed. Two conflicting objectives (operating cost and emission) are satisfied. The case studies are carried out for Muppandal (Tamil Nadu), Jaisalmer (Rajasthan), and Okha (Gujarat), India. The annual solar and wind data are analyzed by using Normal Distribution and Weibull Distribution Density Factor, respectively. The presented technique is inspected on numerous archetype functions and systems. The results depict the prevalence of ACSM over particle swarm optimization (PSO), simplex method with mutations (SMM), SM, and EM.</p> </abstract>

A Hybrid White Shark Equilibrium Optimizer for Power Scheduling Problem Based IoT

A Hybrid White Shark Equilibrium Optimizer for Power Scheduling Problem Based IoT

Short-term Hydro-Thermal-Wind-Solar Power Scheduling: A Case Study of Kanyakumari Region of India

In this paper, an advanced modus operandi named the -constrained simplex method (ACSM) is deployed to resolve a real-time hydro-thermal-wind-solar power scheduling problem. ACSM is an updated articulation of the Nonlinear Simplex Method (SM) of Nelder and Mead. It has been designed after interbreeding an ordinary SM with some other methods like-evolutionary method, α-constrained method, etc. To develop this technique three alterations in the SM are adopted (i) -level differentiation, (ii) mutations of the worst point, and (iii) the incorporation of multi-simplexes. A real-time multi-objective hydro-thermal-wind-solar power scheduling problem is established and optimized for the Kanyakumari (Tamil Nadu, India) for the 18th of September of 2020. Four contrary constraints are contemplated for this case study (i)fuel cost and employing cost of wind and solar power system, (ii) NOx emission, (iii) SO2 emission, and (iv) CO2 emission. The fidelity of the projected practice is trailed upon two test systems. The first test system is hinged upon twenty-four-hour power scheduling of a pure thermal power system. The values of total fuel cost,emission, emission, and emission are attained as 4707.19$/day, 59325.23 kg/day, 207672.70 kg/day, and 561369.20 kg/day, respectively. In the second test system, two thermal generators are reintegrated with renewable energy resources (RER) based power system (hydro, wind, and solar system) for the same power demands. The hydro, wind, and solar data are probed with the Glimn-Kirchmayer model, Weibull Distribution Density Factor, and Normal Distribution model, respectively. The outturns using ACSM are contrasted with the SM and evolutionary method(EM). For this real-time hydro-thermal-wind-solar power scheduling problem the values of fuel cost, emission, emission, and emission are shortened to 1626.41 $/day, 24262.24 kg/day, 71753.80 kg/day, and 196748.20 kg/day, respectively for the specified interval using ACSM and with SM, these values are calculated as 1626.57 $/day, 24264.67 kg/day, 71760.98 kg/day, 196767.68 kg/day, respectively. The results for the same are obtained as 1626.74 $/day, 24267.10 kg/day, 71768.15 kg/day, 196787.55 kg/day, respectively, by using EM. The values of the operating cost of the solar system, wind system, total system transmission losses, and computational time of test system-2 with ACSM, SM, and EM are evaluated as 8438.76 $/day, 19017.42 $/day, 476.69 MW/day & 15.6 seconds; 8439.61 $/day, 19019.33 $/day, 476.74 MW/day and 16.8 sec; and 8447.20 $/day, 19036.43 $/day, 477.17 MW/day and 17.3 sec, respectively. The solutions portray the sovereignty of ACSM over the other two methods in the entire process.

Short-term Hydro-Thermal-Wind-Solar Power Scheduling: A Case Study of Kanyakumari Region of India

In this paper, a multi-objective hydro-thermal-wind-solar power scheduling problem is established and optimized for the Kanyakumari (Tamil Nadu, India) for the 18th of September of 2020. Four contrary constraints are contemplated for this case study (i) fuel cost and employing cost of wind and solar power system, (ii) NOx emission, (iii) SO2 emission, and (iv) CO2 emission. An advanced hybrid simplex method named as-the -constrained simplex method (ACSM) is deployed to solve the offered problem. To formulate this technique three amendments in the usual simplex method (SM) are adopted (i) -level differentiation, (ii) mutations of the worst point, and (iii) the incorporation of multi-simplexes. The fidelity of the projected practice is trailed upon two test systems. The first test system is hinged upon twenty-four-hour power scheduling of a pure thermal power system. The values of total fuel cost and emissions (NOx, SO2, CO2) are attained as 346117.20 Rs, 59325.23 kg, 207672.70 kg, and 561369.20 kg, respectively. In the second test system, two thermal generators are reintegrated with renewable energy resources (RER) based power systems (hydro, wind, and solar system) for the same power demands. The hydro, wind, and solar data are probed with the Glimn-Kirchmayer model, Weibull Distribution Density Factor, and Normal Distribution model, respectively. For this real-time hydro-thermal-wind-solar power scheduling problem the values of fuel cost and emissions (Nox, SO2, CO2) are shortened to 119589.00 Rs, 24262.24 kg, 71753.80 kg, and 196748.20 kg, respectively for the specified interval. The outturns using ACSM are contrasted with the SM and evolutionary method (EM). The values of the operating cost of solar system, wind system, total system transmission losses, and computational time of test system-2 with ACSM, SM, and EM are evaluated as 620497.40 Rs, 1398340.00 Rs, 476.6948 MW & 15.6 seconds; 620559.45 Rs, 1398479.80 Rs, 476.7425 MW & 16.8 seconds; and 621117.68 Rs, 1399737.80 Rs, 477.1715 MW and 17.3 seconds, respectively. The solutions portray the sovereignty of ACSM over the other two methods in the entire process.

The wind power scheduling problem

The importance of renewable energy cannot be overstated. Several nations are coming together in promoting green energy. One of the promotional schemes of the Indian government is the exchange of power under the inter state transmission system. This study deals with a decision-making problem for a large paper manufacturing company in India that exchanges its windmill energy under this scheme. The problem is a challenging combinatorial optimization problem with a quadratic objective function and intricate relationships among decision variables. It is different from the usual decision making problems that are encountered in the literature. In this article, we present a solution methodology and show that the solutions obtained are $$\epsilon$$ -optimal. Several live instances of the problem are solved and the results are presented and discussed. Both the formulation and the solution approach are innovative.

Smart Home Battery for the Multi-Objective Power Scheduling Problem in a Smart Home Using Grey Wolf Optimizer

The power scheduling problem in a smart home (PSPSH) refers to the timely scheduling operations of smart home appliances under a set of restrictions and a dynamic pricing scheme(s) produced by a power supplier company (PSC). The primary objectives of PSPSH are: (I) minimizing the cost of the power consumed by home appliances, which refers to electricity bills, (II) balance the power consumed during a time horizon, particularly at peak periods, which is known as the peak-to-average ratio, and (III) maximizing the satisfaction level of users. Several approaches have been proposed to address PSPSH optimally, including optimization and non-optimization based approaches. However, the set of restrictions inhibit the approach used to obtain the optimal solutions. In this paper, a new formulation for smart home battery (SHB) is proposed for PSPSH that reduces the effect of restrictions in obtaining the optimal/near-optimal solutions. SHB can enhance the scheduling of smart home appliances by storing power at unsuitable periods and use the stored power at suitable periods for PSPSH objectives. PSPSH is formulated as a multi-objective optimization problem to achieve all objectives simultaneously. A robust swarm-based optimization algorithm inspired by the grey wolf lifestyle called grey wolf optimizer (GWO) is adapted to address PSPSH. GWO has powerful operations managed by its dynamic parameters that maintain exploration and exploitation behavior in search space. Seven scenarios of power consumption and dynamic pricing schemes are considered in the simulation results to evaluate the proposed multi-objective PSPSH using SHB (BMO-PSPSH) approach. The proposed BMO-PSPSH approach’s performance is compared with that of other 17 state-of-the-art algorithms using their recommended datasets and four algorithms using the proposed datasets. The proposed BMO-PSPSH approach exhibits and yields better performance than the other compared algorithms in almost all scenarios.

Artificial bee colony optimization algorithm for adaptive power scheduling in an isolated system

<p>The objective of this work is to solve the power scheduling problems for efficient energy management by assigning the optimal values. Artificial neural networks are used widely in the field of energy management and load scheduling. The backpropagation technique is used for the feed-forward neural network training and the levenberg-marquardt algorithm is used to minimize the errors. The slow speed of convergence and getting stuck in local minima are some negatives of backpropagation in complex computation. To overcome these drawbacks an innovative meta-heuristic search algorithm called modified artificial bee colony optimization algorithm is used. A hybrid neural network is introduced in this work. The simulation result shows that the efficiency of the system is improved when hybrid optimization is used. With this method, the system achieves an optimal accuracy of 99.23%.</p>