Energy Load Research Articles

Cluster-based multicast optimized routing in VANETs using elite knowledge-based genetic algorithm

The advancement of autonomous and driver-assistance technology has greatly improved the experience of driving. With the growing use of vehicles, there is a greater need for effective communication among them to ensure both applications in Vehicular Ad-hoc Networks (VANETs) for safety and non-safety. VANETs commonly prioritize multicast communication to efficiently use computational resources and achieve a desirable Quality of Service (QoS). However, the dynamic nature of VANETs, marked by high mobility and frequent topology changes, presents significant challenges in establishing and sustaining multicast communication. To ensure that sensing data from all target points is reliably sent to the base station, it is crucial to address the important factors of energy balancing, load balancing, connectivity, and coverage. These factors play a vital role in achieving a balanced and efficient transmission system. In this research paper, clustering-based multicast routing is proposed that utilizes an enhanced Genetic Algorithm Elite Knowledge Sharing Genetic Algorithm (EKSGA) to choose cluster heads. The EKSGA identifies the top 5 % performers with the highest fitness score and generates a new population by exchanging genetic information, aiming to establish a population with the greatest potential for optimal fitness. The performance assessment of the suggested protocol demonstrates significant enhancements in network lifetime and throughput compared to various existing protocols, including LEACH, DEEC, p-WOA, DDEEE, ECBLTR, and GA with improvements ranging from 2.4 % to 22 % in network lifetime and from 3.2 % to 23.2 % in throughput for a system consisting of 500 nodes with energy level set at 0.1 J for rounds 300. Additionally, the proposed approach utilizes the existing population to generate a more fit population, thereby reducing the need for excessive iterations and computational overhead.

A cloud-edge collaborative task scheduling method based on model segmentation

With the continuous development and combined application of cloud computing and artificial intelligence, some new methods have emerged to reduce task execution time for training neural network models in a cloud-edge collaborative environment. The most attractive method is neural network model segmentation. However, many factors affect the segmentation point, such as resource allocation, system energy consumption, load balancing, and network Bandwidth allocation. Some segmentation methods consider the shortest task execution time, which ignores the utilization of resources at the edge and can result in resource waste. Additionally, these factors are difficult to measure, which presents a challenge in calculating the best segmentation point to achieve the goal of maximum resource utilization and minimum task execution time. To solve this problem, this paper proposes a cloud-edge collaborative task scheduling method based on model segmentation (CECMS). This method first analyzes the factors affecting the segmentation point of the model and then obtains accurate factors that affect the segmentation point calculation through the pre-execution method. Furthermore, a multi-objective solution algorithm is improved to calculate the optimal model segmentation point. And tasks are separately offloaded to the edge and cloud based on the optimal model segmentation point. Finally, the experiments are conducted to verify the effectiveness of this method. Finally, the effectiveness of the CECMS method was verified through simulation experiments. Compared with the Dynamic Adaptive DNN Surgery (DADS) method and an adaptive DNN inference acceleration framework algorithm with end–edge–cloud collaborative computing algorithm (ADC), CECMS achieves the same effectiveness as DADS and ADC in optimizing task execution time by comprehensively considering the utilization of edge resources and minimizing task execution time, while also effectively ensuring resource utilization.

Integration of RES and AI for Grid Distribution Network Energy Management

In an era where sustainability and efficient resource utilization are paramount, optimizing energy management in grid distribution networks is a top priority. This research introduces a cutting-edge approach that harnesses the power of Renewable Energy Sources (RES), Artificial Intelligence (AI), Long Short-Term Memory (LSTM) networks, Quadratic Regression, and Demand Response mechanisms for Grid Distribution Network Energy Management. By fuzing these state-of-the-art technologies, we unlock the potential to revolutionize energy load forecasting with unprecedented precision and foresight. LSTM models, enriched with historical load data, weather conditions, and demand-response patterns, empower us to anticipate grid requirements with exceptional accuracy. Our approach consistently achieves an average Mean Absolute Percentage Error (MAPE) below 5% and a Root Mean Square Error (RMSE) under 2% for load predictions with an overall grid distribution efficiency is 98%, surpassing conventional forecasting methodologies. Furthermore, the integration of demand response strategies results in a remarkable 20% peak shaving ratio, contributing to a 15% reduction in energy demand during high-demand periods. This research not only enhances smart grid technologies but also ushers in a more resilient, adaptive, and eco-friendly energy infrastructure for the future.

Optimizing electricity peak shaving through stochastic programming and probabilistic time series forecasting

This paper proposes a predict-then-optimize framework to optimally schedule the charging and discharging activities of battery energy storage systems (BESS). BESS are used to eliminate peak electricity consumption loads, which pose a significant risk of microgrid system failure and increase electricity costs to end users. A major challenge in BESS lies in determining the battery usage schedule, which must be determined before actual energy consumption materializes. To address this challenge, we propose a two-phase approach. In the first phase, we develop a deep-learning-based probabilistic time-series forecasting model to predict future electricity consumption. In the second phase, the output of the prediction model is used to generate future load scenarios, which are incorporated into a two-stage stochastic programming model that determines the optimal battery usage schedule. Extensive computational experiments on real-world datasets demonstrate the effectiveness of the proposed framework in shaving peak loads and minimizing energy costs. Specifically, our proposed framework reduces daily energy peaks by up to 26%, with the potential for greater improvement as the forecast of future energy loads improves. To the best of our knowledge, this work is the first to investigate the integration of probabilistic forecasting and stochastic optimization to enhance the effectiveness of BESS in managing peak energy loads, leading to more energy-efficient buildings.

Optimizing Energy Consumption in Agricultural Greenhouses: A Smart Energy Management Approach

Efficient energy management is crucial for optimizing greenhouse (GH) operations and promoting sustainability. This paper presents a novel multi-objective optimization approach tailored for GH energy management, aiming to minimize grid energy consumption while maximizing battery state of charge (SOC) within a specified time frame. The optimization problem integrates decision variables such as network power, battery power, and battery energy, subject to constraints based on battery capacity and initial energy, along with minimum and maximum energy from the battery storage system. Through the comparison of a smart energy management system (EMS) with traditional optimization algorithms, the study evaluates its efficiency. Key hyperparameters essential for the optimization problem, including plateau time, prediction time, and optimization time, are determined using the ellipse optimization method. Treating the GH as a microgrid, the analysis encompasses energy management indicators and loads. A simulation conducted via Simulink in MATLAB software (R2021b) demonstrates a significant enhancement, with the smart EMS achieving a more than 50% reduction in the objective function compared to conventional EMS. Moreover, the EMS exhibits robust performance across variations in the load power and irradiation profile. Under partial shading conditions, the EMS maintains adaptability, with a maximum objective function increase of 0.35553%. Aligning the output power of photovoltaic (PV) systems with real-world conditions further validates the EMS’s effectiveness in practical scenarios. The findings underscore the efficiency of the smart EMS in optimizing energy consumption within GH environments, offering promising avenues for sustainable energy management practices. This research contributes to advancing energy optimization strategies in agricultural settings, thereby fostering resource efficiency and environmental stewardship.

Large Signal Stability Analysis of Hybrid AC/DC Microgrids When a Single-Phase-to-Ground Fault Occurs

Islanded hybrid AC/DC microgrids lack support for a large grid, and the negative incremental impedance of constant power loads (CPLs) aggravates the poor anti-disturbance capability of the system. When a single-phase ground fault (SPGF) occurs, the amount of fault impulse power that islanded AC/DC hybrid microgrids can stably withstand and when the protection equipment can work are both unknown. In this paper, the method of symmetrical components is utilized, and high-signal stability criteria for islanded hybrid AC/DC microgrids when a SPGF occurs are derived based on the mixed potential theory. The proposed criteria place quantitative constraints on the power of the PV unit, DC/AC converter current inner-loop proportional parameters, inductors, and inductor equivalent resistance, as well as energy storage unit power, CPL power, capacitors, DC bus voltage, line equivalent resistance, line equivalent inductance, equivalent inductance in the faulty branch, equivalent resistance in the faulty branch, positive-sequence equivalent impulse power of the SPGF, and zero-sequence equivalent impulse power. Furthermore, the maximum impulse power of a SPGF that islanded hybrid AC/DC microgrids could stably withstand is also presented, providing guidelines for protection equipment to decide when to work. In addition, the allowable maximum CPL power that islanded hybrid AC/DC microgrids could steadily support as a SPGF occurs is deduced, and the power is usually adopted to determine the states of an energy storage unit and load shedding in advance. Simulation and experimental validations prove the correctness of the derived high-signal stability criteria.

A novel intelligent modeling and prediction of heat energy consumption in smart buildings

The rising cost and demand for energy have prompted several organizations to devise innovative methods for monitoring, managing, and conserving energy. Heat energy load prediction in smart buildings is critical for saving energy as well as for meeting energy demands. As the cost of energy and demand is increasing, people must find some way to control it and save energy. To overcome these issues, an intelligent energy management system needs to be developed to help individuals by predicting heat energy demand ahead of time and analyzing energy use patterns. This paper introduces a data-driven short-term heat energy consumption prediction for smart buildings by developing a hybrid deep learning model considering the capabilities of Convolutional and Recurrent Neural Networks. The proposed model extracts hidden patterns from actual data collected through sensors and also uses hand-crafted features to predict the heat energy demand accurately. The efficiency of the proposed model has been evaluated on real smart heat metering data, a case study in Denmark, having three kinds of buildings: single-family, apartment, and terraced houses. The extensive experimental results have been reported with real-world data by considering various evaluation metrics such as MAE, RMSE, MAPE and R2. The results are promising and outperformed other state-of-the-art methods.

Integrating Compressed CO2 Energy Storage in an Integrated Energy System

The integration of an energy storage system into an integrated energy system (IES) enhances renewable energy penetration while catering to diverse energy loads. In previous studies, the adoption of a battery energy storage (BES) system posed challenges related to installation capacity and capacity loss, impacting the technical and economic performance of the IES. To overcome these challenges, this study introduces a novel design incorporating a compressed CO2 energy storage (CCES) system into an IES. This integration mitigates the capacity loss issues associated with BES systems and offers advantages for configuring large-scale IESs. A mixed integer linear programming problem was formulated to optimize the configuration and operation of the IES. With an energy storage capacity of 267 MWh, the IES integrated with a CCES (IES–CCES) system incurred an investment cost of MUSD 161.9, slightly higher by MUSD 0.5 compared to the IES integrated with a BES (IES–BES) system. When not considering the capacity loss of the BES system, the annual operation cost of the IES–BES system was 0.5 MUSD lower than that of the IES–CCES system, amounting to MUSD 766.6. However, considering the capacity loss of the BES system, this study reveals that the operation cost of the IES–BES system surpassed that of the IES–CCES system beyond the sixth year. Over the 30-year lifespan of the IES, the total cost of the IES–CCES system was MUSD 4.4 lower than the minimum total cost of the IES–BES system.

Unmanned sailboat with self-balancing rotating sail based on elastic rope: Modeling, optimization, and sea trials

Unmanned sailboats use wind energy to assist in propulsion during navigation and are featured by the advantages of clean energy and long endurance, making a hotspot of research on maritime unmanned vehicles. Sails are a core component of unmanned sailboats, and most existing studies on rotating sail have the shortcomings of high energy consumption and load. Therefore, this article proposes a novel method to achieve self-balancing sail rotation based on elastic rope and reduce the energy consumption and load of unmanned sailboats, and establishes a model for the self-balancing rotating sail. We introduced the sum of angular thrust of spherical surface SL as a performance evaluation index for unmanned sailboats, which considers both thrust and navigable range. Based on this index, the mechanical and positional parameters of the model are optimized to obtain the optimal solutions. The performance is increased by 24% after the optimization, and by 76% compared with the sailboat with the fixed sail angle when the same initial sail angle of 38° is adopted. Following the optimal solutions, we develop a prototype of the unmanned sailboat with self-balancing rotating sail. Subsequently, wind turbine experiments are conducted to preliminarily verify the correctness of the model for self-balancing rotating sail and the optimization results. Finally, sea trials are conducted to further verify the performance and seaworthiness of the unmanned sailboat under realistic sea conditions, successfully achieving a 15-day voyage under harsh sea conditions of levels 2 to 4. This study to some extent compensates for the shortcomings of existing studies on rotating sail and provides guidance for subsequent theoretical and engineering research in the field of unmanned sailboats.

Harmonic suppression control strategy of distribution networks based on the distributed power flow controller

New energy and multiple loads, such as distributed wind–solar storage and charging, are connected to the distribution network through power electronic converters, which increases the harmonic content in the distribution network and causes operational safety risks. In this paper, the mathematical model of harmonic current and harmonic power content in a distribution network is constructed by an equivalent circuit and vector diagram. The distributed power flow controller is proposed for harmonic control of the distribution network. The mathematical expressions of the harmonic current and harmonic power based on a distributed power flow controller are constructed, and the control strategy of the distributed power flow controller for harmonic control is proposed. The simulation results show that the proposed method can effectively suppress the fifth and seventh harmonics of the distribution network.

Achieving Energy Self-Sufficiency in a Dormitory Building: An Experimental Analysis of a PV–AWHP-ERV Integrated System

In this study, we investigated the performance of air-to-water heat pump (AWHP) and energy recovery ventilator (ERV) systems combined with photovoltaics (PV) to achieve the energy independence of a dormitory building and conducted an analysis of the energy independence rate and economic feasibility by using energy storage devices. Our data were collected for 5 months from July to November, and the building energy load, energy consumption, and system performance were derived by measuring the PV power generation, purchase, sales volume, AWHP inlet and outlet water temperature, and ERV outdoor, supply, and exhaust temperature. When analyzing representative days, the PV–AWHP integrated system achieved an energy efficiency ratio (EER) of 4.49 and a coefficient of performance (COP) of 2.27. Even when the generated electrical energy exceeds 100% of the electricity consumption, the energy self-sufficiency rate remains at 24% due to the imbalance between energy consumption and production. The monthly average energy self-sufficiency rate changed significantly during the measurement period, from 20.27% in November to 57.95% in September, highlighting the importance of energy storage for self-reliance. When using a 4 kWp solar power system and 4 kWh and 8 kWh batteries, the annual energy self-sufficiency rate would increase to 67.43% and 86.98%, respectively, and our economic analysis showed it would take 16.5 years and more than 20 years, respectively, to become profitable compared to the operation of an AWHP system alone.

Decentralized utilization of distributed energy storage resources for simultaneous frequency regulation in a microgrid

A microgrid has emerged for the transformation from centralized into localized electricity generation, which increases the opportunity for renewable-based distributed generators (DGs) applications such as photovoltaic (PV) and wind as well as small-scale conventional generation units. PV and wind integration provides environmental, technical, and economic benefits. However, the low inertia of the PV system and decoupling due to the presence of the power electronics converter in the wind generation system led to a significant declination in the microgrid's inertia, which causes an excessive frequency nadir and a high rate of change of frequency (ROCOF) in the presence of disturbances. The microgrid's inertia can be enhanced by storing or releasing energy within the microgrid. The wind generation system has intrinsic kinetic energy stored in the rotating parts, while the PV system's sorted energy is improved by introducing an external supercapacitor on the DC link. The aforementioned energy storage elements provide limited energy resources, which should be employed in a proper manner. This article proposes a control scheme to boost the cooperation of wind and PV generation systems for the enhancement of inertia and frequency support. Therefore, the proposed scheme prevents excessive stress on individual generators and improves the utilization of available energy resources. For example, at load increase by 0.5 MW, with frequency support using PV only or wind only, the frequency deviation is enhanced by 44.4 % and 29.5 %, respectively. While for both PV and wind support the frequency simultaneously, the frequency deviation is enhanced by 53.3 %. In addition, with the cooperation of PV and wind, the required energy from PV and wind is reduced by 29.5 % and 13.7 % respectively and the rate of change of frequency is enhanced by 61.9 %. The energy share among PV and wind generation systems is investigated and verified by simulations; tuning formulas are also developed to attain predefined energy support with equal energy sharing among different resources. For instance, with a non-equal energy share strategy and load increases by 0.5 MW, the wind delivers almost 1.6 times the energy delivered from the PV. Hence, more stress occurs on the wind generation compared to PV. While, using equal energy share strategy, the required energy from wind is about 1.03 times the energy delivered from the PV. The proposed control scheme is applied to an AC microgrid that comprises a thermal generation plant, a PV generation system, and a doubly-feed induction generator-based wind generation system. To verify the effectiveness of the proposed scheme, different simulation cases considering load change, wind speed variation, irradiance variations, and weak grid integration are implemented. When compared to individual frequency support, the proposed scheme provides a superior response.

Optimal sizing of hybrid renewable energy systems using quasi-optimal control

This paper addresses the critical challenge of sizing hybrid renewable energy systems over their lifespan while accounting for uncertainties in energy sources and load demands. By leveraging stochastic programming, we introduce a novel modeling technique that ensures robust optimization without compromising numerical tractability. Unlike conventional methods, which determine system parameters for the entire project duration upfront, our approach enables annual adjustments to the renewable components’ sizing. This dynamic strategy alleviates early-stage under-utilization, aligning system capacity with evolving demand patterns. Central to our approach is the reformulation of the two-stage stochastic program as a quasi-optimal control. This reduces the number of optimization variables significantly, simplifying the solution process. Moreover, thousands of constraints are replaced with a system of differential equations, enhancing computational efficiency. By minimizing capital costs and dynamic operating expenses, we achieve an optimal system size. Through a real-world application in a rural area of South Africa, we demonstrate the effectiveness of our approach. The results showed a remarkable improvement in problem-solving efficiency, reduced under-utilization, and heightened adaptability to unpredictable weather conditions. This innovative framework represents a substantial leap forward in hybrid renewable energy systems design, offering a more agile and efficient solution for sustainable energy generation.

Research on joint dispatch of wind, solar, hydro, and thermal power based on pumped storage power stations

In the context of energy conservation and emission reduction, the integration and consumption of large-scale wind and solar resources is an inevitable trend in future energy development. However, with the increase of wind and solar grid-connected capacity, the power system also requires more flexible resources to ensure safe operation. To enhance the economic efficiency of the complementary operation of wind, solar, hydro, and thermal sources, considering the peak regulation characteristics of different types of power sources, the study of the joint dispatch model of complementary utilization of various generation methods like wind, solar, hydro, thermal, and storage is of great significance for the economic dispatch of the power system. Existing studies mainly focus on traditional thermal power units or hydropower units, with few studies investigating the impact of pumped-storage power stations on the absorption of renewable energy. Firstly, this paper introduces the composition and function of each unit under the research framework and establishes a joint dispatch model for wind, solar, hydro, and thermal power. Secondly, the paper elaborates on the objective function within the model, mainly covering the operating costs of thermal power units, hydropower units, pumped storage, wind and solar units, the cost of discarding new energy, and the cost of load shedding. Subsequently, the paper presents the constraints of the system model, mainly the feasible boundaries for the operation of each unit within the system. Finally, The results of the calculations show that the proposed model reduces the total operating cost by 12% and the power abandonment rate by 82% compared to the conventional model. It is shown that the proposed model can not only significantly improve the economic efficiency of the system operation but also reduce the level of energy waste and load shedding, effectively enhancing the degree of energy utilization within the system.

Enhanced energy balancing and optimal load curtailment strategy for DC microgrid integration in hybrid AC/DC distribution networks

AbstractUnleashing the potential of distributed renewable energy sources (RESs), intelligent and autonomous microgrids are becoming pivotal in attaining net‐zero carbon emission goals. Hybrid AC/DC microgrids rise as cutting‐edge microgrid topologies, capitalising on the best of both AC and DC systems. However, the integration of intermittent renewables and uncertainties in loading poses stability challenges. Advanced bidirectional converter controls provide efficient power exchange, but in extreme contingencies, a resilient supervisory control framework (load management/load curtailment approach) is inevitable to withstand/avoid unplanned renewable disruptions/blackouts. Moreover, the operational paradigm shift towards achieving net‐zero emissions, isolated operation of RESs, and conventional load shedding methods are anticipated to encounter substantial challenges, necessitating the development of alternative strategies. In order to improve the stability of hybrid microgrid systems in islanding scenarios, this research presents an energy balancing and load curtailment strategy. The proposed method aims at optimising resource utilisation, prioritising essential loads, and executing an optimal load curtailment strategy (if required), thereby augmenting the stability of systems. Unlike a meta‐heuristic or exhaustive search, which depends on 2n − 1 possible combinations and become unworkable as load numbers increase, the suggested methodology is based on a mathematically modelled load restriction method. By including load criticality, this strategy effectively prevents blackouts even with an increasing number of loads, providing a significantly more useful and practical solution. Additionally, the proposed charging algorithm ensures that the energy storage system imports energy from the grid during off‐peak hours and maximises power generation from the DC subgrid. The efficacy of the proposed strategy is validated using a modified IEEE‐33 bus system as a test case for a hybrid AC/DC microgrid. Simulation results demonstrate the effectiveness of the MILP‐based load curtailment approach in maintaining system stability and preventing blackouts during unforeseen events.

Research on Power Load Data Acquisition and Integrated Transmission Systems in Electric Energy Calculation and Detection

This paper presents the crucial area of power load data acquisition with an integrated transmission system for precise calculation and detection of electric energy. With the advances in technology, management and optimization of energy has become critical for sustainability and economic reasons. Thus, we have targeted the cutting-edge methods for data gathering of power load along with its efficient transmission previously reviewed. We scrutinized the current methods and technologies used in power load data acquisition and identified their limitations along with areas of improvements. We followed advanced sensors and measuring devices for data collection employed an integrated transmission system with up-to-the-minute communication protocols and data processing algorithms. These were experimentally verified to improve the accuracy and reliability of the electric energy calculations. The real-world case studies were included for its practical implementations to provide an insight into its impacts. The results of this study provide a maturing outlook along with valuable analysis for electric energy calculation and detection. The system due to its potential for enhancing the energy management and efficiency can have a real-life and profound significance in sustainable and economic handling of the increasing load of energy.

Influence of AR injection on shielding layer properties and surface protection from transient high heat loads under the QSPA plasma exposures

The paper presents experimental studies of a shielding plasma layer formation in front of a tungsten surface exposed with hydrogen plasma in the QSPA-M test-bed facility under the conditions of additional seeding of argon (Ar) along the target surface into the zone of plasma-surface interaction. A pulsed gas injector on the base of a fast electromagnetic valve has been developed for the local injection of Ar. The injector is capable of generating a homogeneous argon gas flow with a maximum concentration above n Ar = 6 × 1023 m−3 and a pulse duration of 0.5 ms. It is shown that the increase in the argon gas density in front of the surface leads to an essential decrease (in 1.5–2 times) in the energy load delivered to the target surface. In the presence of a strong magnetic field (up to 1 T), both the thickness of the shielding layer and the fraction of energy dissipated by the shield increase further. Even for moderate energy densities of the QSPA plasma streams in the experiments with Ar gas injection, less than 40% of the impacting plasma load is absorbed by the tungsten surface. The results demonstrate that this additional shielding attributed to the formation of a dense Ar plasma layer in front of the exposed W surface would be favourable for the divertor armour performance, causing the decreasing erosion of plasma-facing components in the course of transient events in a fusion reactor.

Research on data center computing resources and energy load Co-optimization considering spatial-temporal allocation

Research on data center computing resources and energy load Co-optimization considering spatial-temporal allocation

Feasibility and performance analysis of a net-zero energy residential building in tropical climates: A case of Congo-Brazzaville

Current building techniques in developing countries have become extremely critical. The net-zero energy concept has emerged as an essential strategy for minimising energy consumption and greenhouse gas emissions. However, its implementation, particularly in developing countries, remains a critical challenge. The purpose of this work is to assess the feasibility of achieving a net-zero energy building by combining energy-efficient design practices and renewable energy systems under the climatic conditions of the Republic of Congo. To achieve the stipulated objectives, DesignBuilder software was utilised for building modelling, energy load assessment and multiobjective optimisation of building energy efficiency measures, and the multicriteria energy optimisation was carried out using the HOMER tool. The optimisation results showed that the implementation of energy efficiency measures resulted in 39.15% energy savings, 43.45% thermal load savings and 55.68% discomfort hours reduction. Furthermore, the renewable energy system can provide 100% of the building’s energy load and a total savings of 3341.84 kgCO2eq/year. The system’s levelised cost of energy was estimated at 0.256 $/kWh, with a net present cost of $20,231, while the overall life cycle cost was calculated at 188.91 $/m2.

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

In smart grid, energy consumption has grown exponentially in residential houses, which necessitates the adoption of demand response management. To alleviate and handle the energy management in residential houses, an efficient residential energy management (REM) system can be employed to regulate the energy consumption of appliances for several energy loads such as non-shiftable, shiftable, and controllable loads. Many researchers have focused on the REM using machine learning and deep learning techniques which is not able to provide secure and optimal energy management procedure. Thus, in this paper, a multi-agent-based decentralized REM, i.e., MD-REM approach is proposed using Deep Reinforcement Learning (DRL) with the utilization of blockchain. Furthermore, The combinatorial model DQN, i.e., Q-learning and deep neural network (DNN) is employed, to gain the optimal price based on the reduced energy consumption by appliances associated with different energy loads utilizing the Markov Decision Process (MDP). Here, multiple agents are designed to handle different energy loads and consumption is controlled by the DQN agent, then reduced consumption data is securely shared among all stakeholders using blockchain-based smart contract. The performance evaluation of the proposed MD-REM approach seems to be efficient in terms of reduced energy consumption, optimal energy price, reward, and total profit analysis. Moreover, blockchain-based result is evaluated for the proposed MD-REM approach considering the performance metrics such as transaction efficiency, Interplanetary File System (IPFS) bandwidth utilization, and data storage cost comparison.