Comprehensive energy service system oriented to distributed energy and operation method thereof

Abstract

The invention discloses a distributed energy-oriented comprehensive energy service system and an operation method thereof, and belongs to the technical field of energy services, and the system comprises a data acquisition module, an energy optimization scheduling module, a user interaction module, a prediction analysis module, a safety monitoring module and a distributed autonomous control unit. According to the system, through real-time data acquisition and optimal scheduling, the use efficiency of distributed energy equipment can be maximized, and energy waste is reduced. The multi-objective optimization scheduling module can dynamically select the most economical energy scheduling strategy through minimizing the operation cost objective function, and the overall energy expenditure is reduced. The optimization scheduling module clearly considers the minimization target of carbon emission, and the system can effectively reduce the carbon footprint in the operation process by improving the use proportion of clean energy and reducing the use of traditional energy. Wherein the user optimizes the supply and demand balance through the comfort degree deviation index, so that the comfort requirement of the user is met.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy services, and specifically relates to an integrated energy service system for distributed energy and an operation method thereof. Background Art

[0002] In today's context of growing global energy demand, distributed energy systems, as an emerging form of energy supply, are gaining more and more attention. Distributed energy systems can not only improve the efficiency of energy systems but also reduce transmission and distribution losses by producing and storing energy close to load centers. With the advancement of renewable energy technologies, such as solar photovoltaics and wind power, the potential of distributed energy systems in reducing carbon emissions and promoting sustainable development has become increasingly significant.

[0003] However, the widespread application of distributed energy systems also faces a series of technical challenges. First, the intermittent and volatile nature of distributed energy puts higher demands on the real-time scheduling of energy supply and demand balance. Traditional energy management systems often have difficulty in coping with the needs of real-time data processing and rapid response. Secondly, with the increase in distributed energy devices, the complexity of the system increases, which puts higher demands on data collection, transmission and processing capabilities. In addition, how to maximize system efficiency and economic benefits while meeting user energy needs is also an urgent problem to be solved.

[0004] In this context, integrated energy service systems have emerged. By integrating advanced data collection technology, intelligent prediction algorithms and optimized scheduling strategies, such systems aim to improve the utilization efficiency of distributed energy and achieve efficient energy management. Modern integrated energy service systems usually rely on the Internet of Things and big data analysis technologies to monitor and schedule energy production, storage and consumption processes in real time. This not only ensures efficient use of energy, but also effectively reduces operating costs and carbon emissions by optimizing scheduling strategies.

[0005] At the same time, the advancement of information and communication technology has made remote monitoring and control possible. Users can obtain real-time energy usage information through interactive interfaces and adjust energy usage strategies according to their personalized needs. In addition, the development of intelligent algorithms, such as long short-term memory networks (LSTM), provides strong support for accurate energy demand forecasting, thereby better coping with the uncertainty of energy demand.

[0006] In summary, the integrated energy service system for distributed energy has significant advantages in improving energy efficiency, reducing environmental impact and improving user satisfaction, and is expected to become an important part of future energy management. Summary of the invention

[0007] 1. Technical problems to be solved

[0008] In response to the problems existing in the prior art, the purpose of the present invention is to provide an integrated energy service system for distributed energy and an operation method thereof, which can maximize the utilization efficiency of distributed energy equipment and reduce energy waste. By increasing the proportion of clean energy use and reducing the use of traditional energy, the system can effectively reduce the carbon footprint during operation.

[0009] 2. Technical solution

[0010] To solve the above problems, the present invention adopts the following technical solutions.

[0011] Comprehensive energy service system for distributed energy, including:

[0012] 1) Data acquisition module, used to collect real-time data of distributed energy equipment, including power generation, energy storage status, load demand and environmental data;

[0013] 2) an energy optimization scheduling module, communicating with the data acquisition module, for real-time scheduling of the supply and demand of distributed energy based on a multi-objective optimization algorithm to minimize operating costs, energy loss and carbon emissions;

[0014] 3) User interaction module, used to provide a user interface to support energy usage query, personalized configuration and remote control;

[0015] 4) Prediction analysis module, used to predict future energy demand based on the long short-term memory network (LSTM) model;

[0016] 5) Safety monitoring module, which is used to monitor the operating status of distributed energy equipment in real time and issue an early warning when a fault is detected;

[0017] 6) Distributed autonomous control unit, used to independently control the operation of each distributed energy unit in the event of network loss.

[0018] Furthermore, the energy optimization scheduling module uses the following objective function to perform scheduling optimization: minJ = αC op +βE loss +γCO2+δU dis ;

[0019] Among them, C op is the system operation cost; E loss is the system energy loss; CO2 is the carbon emission; U dis is the user comfort deviation; α, β, γ, δ are weight coefficients.

[0020] Furthermore, the data acquisition module includes:

[0021] Smart meters are used to collect real-time electricity data; environmental sensors are used to collect temperature, humidity and light intensity environmental data; edge computing nodes are used to pre-process the collected data and upload it to the server.

[0022] Furthermore, the prediction analysis module performs real-time prediction of energy demand based on a long short-term memory network (LSTM) model, and the calculation of the LSTM unit includes:

[0023] Forget gate calculation: f t =σ(W f .[h t-1 ,x t ]+b f );

[0024] Input gate calculation: it = σ(W i .[h t-1 ,x t ]+b i )

[0025] Candidate memory unit: C t’ =tanh(W c ·[h t-1 ,x t ]+b c )

[0026] Memory unit update: C t =f t ·C t-1 +i t ·C t’ ;

[0027] Output gate calculation: o t =σ(W o ·[h t-1 ,x t ]+b o )

[0028] Hide status update:h t =o t tanh(C t ).

[0029] Furthermore, the operation method of the integrated energy service system for distributed energy comprises the following steps:

[0030] 1) Data collection step: collect real-time power generation, energy storage status, load demand and environmental data of distributed energy equipment;

[0031] 2) Prediction and analysis step: Use the long short-term memory network (LSTM) model to predict future energy demand;

[0032] 3) Optimization scheduling step: Based on the multi-objective optimization algorithm, a scheduling plan is generated to meet the supply and demand balance and minimize operating costs and carbon emissions;

[0033] 4) Dispatching execution step: sending control instructions to distributed energy devices according to the optimized dispatching plan;

[0034] 5) User interaction step: providing energy usage query, personalized configuration and remote control functions through the user interface;

[0035] 6) Safety monitoring steps: monitor system status in real time, detect faults and issue early warnings.

[0036] Furthermore, in the scheduling execution step, each distributed energy unit has a distributed autonomous control function and can still operate independently and maintain local supply and demand balance when the communication network is lost.

[0037] 3. Beneficial effects

[0038] Compared with the prior art, the advantages of the present invention are:

[0039] 1) The system can maximize the utilization efficiency of distributed energy equipment and reduce energy waste through real-time data collection and optimized scheduling. The multi-objective optimization scheduling module can dynamically select the most economical energy scheduling strategy and reduce overall energy expenditure by minimizing the operating cost objective function.

[0040] 2) The optimization scheduling module explicitly considers the goal of minimizing carbon emissions. By increasing the proportion of clean energy use and reducing the use of traditional energy, the system can effectively reduce the carbon footprint during operation.

[0041] 3) The user interaction module provides personalized configuration and remote control functions, allowing users to adjust their energy use strategies according to their own needs and optimize the supply and demand balance through the comfort deviation index to meet the user's comfort requirements.

[0042] 4) The combination of the security monitoring module and the distributed autonomous control unit ensures that the system can still operate independently and maintain local supply and demand balance even in the event of network loss or equipment failure, thereby improving the stability and reliability of the overall system.

[0043] 5) The prediction and analysis module uses the long short-term memory network (LSTM) model to make real-time predictions of future energy demand, providing a scientific basis for optimizing scheduling and reducing energy shortages or surpluses caused by demand fluctuations.

[0044] 6) The modular design of the system enables it to flexibly integrate more distributed energy devices and energy storage units, while supporting the upgrade and expansion of hardware equipment and software algorithms. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present invention will be described clearly and completely below; obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments, and all other embodiments obtained by ordinary technicians in this field without making creative work based on the embodiments of the present invention are within the scope of protection of the present invention.

[0046] Embodiment 1:

[0047] Comprehensive energy service system for distributed energy, including:

[0048] 1) Data acquisition module, used to collect real-time data of distributed energy equipment, including power generation, energy storage status, load demand and environmental data; smart meter, used to collect real-time power data; environmental sensor, used to collect temperature, humidity and light intensity environmental data; edge computing node, used to pre-process the collected data and upload it to the server.

[0049] 2) Energy optimization scheduling module, which communicates with the data acquisition module and is used to perform real-time scheduling of the supply and demand of distributed energy based on a multi-objective optimization algorithm to minimize operating costs, energy loss and carbon emissions; the energy optimization scheduling module uses the following objective function for scheduling optimization:

[0050] minJ=αC op +βE loss +γCO2+δU dis ;

[0051] Among them, C op is the system operation cost; E loss is the system energy loss; CO2 is the carbon emission; U dis is the user comfort deviation; α, β, γ, δ are weight coefficients.

[0052] 3) User interaction module, used to provide a user interface to support energy usage query, personalized configuration and remote control;

[0053] 4) Prediction and analysis module, used to predict future energy demand based on the long short-term memory network (LSTM) model; The prediction and analysis module makes real-time predictions on energy demand based on the long short-term memory network (LSTM) model. The calculation of its LSTM unit includes:

[0054] Forget gate calculation: f t =σ(W f .[h t-1 ,x t ]+b f );

[0055] Input gate calculation: it = σ(Wi .[h t-1 ,x t ]+b i )

[0056] Candidate memory unit: C t’ =tanh(W c ·[h t-1 ,x t ]+b c )

[0057] Memory unit update: C t =f t ·C t-1 +i t ·C t’ ;

[0058] Output gate calculation: o t =σ(W o ·[h t-1 ,x t ]+b o )

[0059] Hide status update:h t =o t tanh(C t ).

[0060] 5) Safety monitoring module, which is used to monitor the operating status of distributed energy equipment in real time and issue an early warning when a fault is detected;

[0061] 6) Distributed autonomous control unit, used to independently control the operation of each distributed energy unit in the event of network loss.

[0062] The method for operating an integrated energy service system for distributed energy includes the following steps:

[0063] 1) Data collection step: collect real-time power generation, energy storage status, load demand and environmental data of distributed energy equipment;

[0064] 2) Prediction and analysis step: Use the long short-term memory network (LSTM) model to predict future energy demand;

[0065] 3) Optimization scheduling step: Based on the multi-objective optimization algorithm, a scheduling plan is generated to meet the supply and demand balance and minimize operating costs and carbon emissions;

[0066] 4) Dispatching execution steps: According to the optimized dispatching plan, control instructions are sent to distributed energy equipment; each distributed energy unit has distributed autonomous control functions, and can still operate independently and maintain local supply and demand balance when the communication network is lost.

[0067] 5) User interaction step: providing energy usage query, personalized configuration and remote control functions through the user interface;

[0068] 6) Safety monitoring steps: monitor system status in real time, detect faults and issue early warnings.

[0069] Hardware Configuration

[0070] 1. Data acquisition equipment

[0071] Smart meter: supports Modbus protocol, with accuracy of 0.5.

[0072] Sensors: used to collect environmental data such as temperature, humidity, and light intensity.

[0073] Edge computing nodes:

[0074] Processor: ARM Cortex-A72 (quad-core)

[0075] Memory: 4GB RAM

[0076] Storage: 32GB eMMC

[0077] Interface: RS485, Ethernet, Wi-Fi, 4G module.

[0078] 2. Energy storage system

[0079] Lithium-ion battery pack:

[0080] Capacity: 50kWh (expandable according to demand)

[0081] Rated voltage: 400V

[0082] Charge and discharge efficiency: 95%

[0083] BMS (Battery Management System): Real-time monitoring of voltage, temperature and SOC.

[0084] 3. Computing Server

[0085] Server Configuration:

[0086] Processor: Intel Xeon E5-2690 v4

[0087] Memory: 128GB DDR4

[0088] Storage: 2TB SSD

[0089] GPU: NVIDIA Tesla V100 (for LSTM training and prediction)

[0090] Operating system: Ubuntu 20.04LTS.

[0091] 4. User Terminal

[0092] Smart Control Panel:

[0093] Touch screen: 10-inch LCD

[0094] Operating system: Android

[0095] Communication protocol: MQTT, HTTP

[0096] LSTM energy demand forecasting model implementation This model is used to predict future energy demand and train the LSTM neural network through historical data. Dependency library installation

[0097] pip install numpypandas tensorflow matplotlib scikit-learn;

[0098] Code Implementation

[0099]

[0100]

[0101]

[0102] illustrate

[0103] load_data function: loads the CSV file and normalizes the data.

[0104] LSTM model: Contains 50-unit LSTM layer and 1 fully connected layer, using Adam optimizer and mean square error (MSE) loss function.

[0105] Training and prediction: Divide the data into training and test sets, train the model and predict future energy demand.

[0106] Implementation of multi-objective optimization scheduling algorithm

[0107] Dependency library installation

[0108] pip install numpy scipy

[0109] Code Implementation

[0110]

[0111]

[0112]

[0113] illustrate

[0114] Objective function: Combining the distributed energy generation cost and the grid power purchase cost, simplified carbon emission calculation.

[0115] Supply and demand balance constraint: The sum of power generation and power purchase must meet the load demand.

[0116] Power limit: Set the maximum power boundary of distributed energy and grid power supply.

[0117] Optimization: Use scipy.optimize.minimize to solve nonlinear optimization problems.

[0118] The above is only a preferred specific implementation of the present invention; however, the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solution and its improved conception within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An integrated energy service system for distributed energy, characterized by: include: 1) Data acquisition module, used to collect real-time data of distributed energy equipment, including power generation, energy storage status, load demand and environmental data; 2) an energy optimization scheduling module, communicating with the data acquisition module, for real-time scheduling of the supply and demand of distributed energy based on a multi-objective optimization algorithm to minimize operating costs, energy loss and carbon emissions; 3) User interaction module, used to provide a user interface to support energy usage query, personalized configuration and remote control; 4) Prediction analysis module, used to predict future energy demand based on the long short-term memory network (LSTM) model; 5) Safety monitoring module, which is used to monitor the operating status of distributed energy equipment in real time and issue an early warning when a fault is detected; 6) Distributed autonomous control unit, used to independently control the operation of each distributed energy unit in the event of network loss.

2. The integrated energy service system for distributed energy according to claim 1, characterized in that: The energy optimization scheduling module uses the following objective function for scheduling optimization: minJ=αC op +βE loss +γCO2+δU dis ; Among them, C op is the system operation cost; E loss is the system energy loss; CO2 is the carbon emission; U dis is the user comfort deviation; α, β, γ, δ are weight coefficients.

3. The integrated energy service system for distributed energy according to claim 1, characterized in that: The data acquisition module comprises: Smart meters are used to collect real-time electricity data; environmental sensors are used to collect temperature, humidity and light intensity environmental data; edge computing nodes are used to pre-process the collected data and upload it to the server.

4. The integrated energy service system for distributed energy according to claim 1, characterized in that: The prediction analysis module performs real-time prediction of energy demand based on the long short-term memory network (LSTM) model. The calculation of the LSTM unit includes: Forget gate calculation: f t =σ(W f .[h t-1 ,x t ]+b f ); Input gate calculation: it = σ(W i .[h t-1 ,x t ]+b i ) Candidate memory unit: C t’ =tanh(W c ·[h t-1 ,x t ]+b c ) Memory unit update: C t =f t ·C t-1 +i t ·C t’ ; Output gate calculation: o t =σ(W o ·[h t-1 ,x t ]+b o ) Hide status update:h t =o t tanh(C t ).

5. The method for operating a comprehensive energy service system for distributed energy according to claim 1, characterized in that: The following steps are involved: 1) Data collection step: collect real-time power generation, energy storage status, load demand and environmental data of distributed energy equipment; 2) Prediction and analysis step: Use the long short-term memory network (LSTM) model to predict future energy demand; 3) Optimization scheduling step: Based on the multi-objective optimization algorithm, a scheduling plan is generated to meet the supply and demand balance and minimize operating costs and carbon emissions; 4) Dispatching execution step: sending control instructions to distributed energy devices according to the optimized dispatching plan; 5) User interaction step: providing energy usage query, personalized configuration and remote control functions through the user interface; 6) Safety monitoring steps: monitor system status in real time, detect faults and issue early warnings.

6. The method for operating a comprehensive energy service system for distributed energy according to claim 5, characterized in that: In the scheduling execution step, each distributed energy unit has a distributed autonomous control function and can still operate independently and maintain local supply and demand balance when the communication network is lost.

Images