Multi-load equipment energy consumption management method, device and computer equipment

Abstract

The present invention relates to the technical field of power system optimization and dispatching, and discloses a multi-load equipment energy consumption management method, device and computer equipment, the method comprising: obtaining electricity price data and energy consumption data, operating status and load demand of electric equipment, and classifying the priority of electric equipment based on electricity price data, energy consumption data, operating status and load demand; using a preset multi-task learning model to predict the load demand of electric equipment in a preset time period in the future; generating a multi-objective optimization model based on the priority of electric equipment, load demand and electricity price data, and generating a dynamic power allocation plan for electric equipment based on the multi-objective optimization model; obtaining the load demand and external environment of electric equipment in real time, and adjusting the dynamic power allocation plan of electric equipment based on the load demand and external environment. The present invention allows energy consumption optimization and operating efficiency to always maintain a balance, solving the problem of failing to achieve a balance between energy consumption optimization and operating efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimization dispatching, and in particular to a method, device and computer equipment for managing energy consumption of multi-load equipment. Background Art

[0002] With the widespread application of smart grids and industrial automation, existing load management algorithms usually only target a single device, using simple timing control or direct start-stop methods. Due to the diversity of load devices and their complex energy consumption characteristics, a single scheduling method can no longer cope with the current complex scenario requirements. Especially in scenarios such as industrial parks and smart homes, the energy consumption of various devices changes frequently, and the existing scheduling algorithms lack real-time response and adaptive optimization capabilities, resulting in low overall energy consumption optimization efficiency.

[0003] At present, common dispatching algorithms (such as demand response and load peak shaving) usually focus on a certain goal (such as reducing energy consumption or reducing costs), and fail to strike a balance between energy consumption optimization and operational efficiency. At the same time, traditional centralized dispatching methods are prone to response lags due to the complexity of equipment, which reduces the dispatching efficiency of the system. Summary of the invention

[0004] In view of this, the present invention provides a method, device and computer equipment for managing energy consumption of multiple load devices to solve the problem of failing to strike a balance between energy consumption optimization and operating efficiency.

[0005] In a first aspect, the present invention provides a method for managing energy consumption of multiple load devices, the method comprising:

[0006] Obtaining electricity price data and energy consumption data, operating status and load demand of electrical equipment, and classifying the priorities of electrical equipment based on the electricity price data, energy consumption data, operating status and load demand;

[0007] Use a preset multi-task learning model to predict the load demand of electrical equipment in a preset time period in the future;

[0008] Generate a multi-objective optimization model based on power equipment priority, load demand and electricity price data, and generate a dynamic power allocation plan for power equipment based on the multi-objective optimization model;

[0009] Obtain the load demand and external environment of the power equipment in real time, and adjust the dynamic power allocation plan of the power equipment based on the load demand and external environment.

[0010] The present invention provides a multi-load equipment energy consumption management method, which generates a multi-objective optimization model based on the priority, load demand and electricity price data of the power equipment by prioritizing the power equipment and predicting the load demand, and generates a dynamic power allocation plan for the power equipment based on the multi-objective optimization model, dynamically adjusts the power allocation to ensure that high-priority equipment is always stably supplied, and low-priority equipment can be flexibly adjusted according to system scheduling. The load demand and external environment of the power equipment are obtained in real time through closed-loop feedback control, and the dynamic power allocation plan is continuously optimized through a feedback mechanism, so that the power equipment is always in the best operating state, so that energy consumption optimization and operating efficiency are always balanced, and the problem of failing to strike a balance between energy consumption optimization and operating efficiency is solved.

[0011] In an optional implementation, the operating status includes the operating time, and the priority of the power-consuming equipment is classified based on the electricity price data, the energy consumption data, the operating status and the load demand, including:

[0012] Classify electrical equipment that requires stable energy consumption data and operating status and does not allow intermittent shutdown as high-priority equipment;

[0013] Classify power-consuming equipment that needs to be operated based on operating hours and whose load demand is dynamically adjusted as medium-priority equipment;

[0014] Electrical equipment that needs to be dynamically adjusted based on fluctuations in electricity price data and load demand will be classified as low-priority equipment.

[0015] The present invention provides a multi-load equipment energy consumption management method, which divides electrical equipment into high-priority equipment, medium-priority equipment and low-priority equipment based on energy consumption data, operating status and load demand. Through the priority classification and real-time monitoring of electrical equipment, the electrical equipment can be intelligently scheduled according to actual conditions to ensure the normal operation of important electrical equipment, thereby providing conditions for the subsequent generation of a dynamic power allocation plan.

[0016] In an optional implementation, a preset multi-task learning model is used to predict the load demand of the electric equipment in a preset time period in the future, including:

[0017] Obtain multi-dimensional time series data of power-consuming equipment, which includes historical load data, historical electricity price data and historical weather data;

[0018] A preset multi-task learning model is used to extract the time series characteristics of load change trends of electrical equipment from multi-dimensional time series data;

[0019] Based on the time series characteristics of load change trends of electrical equipment, a preset loss function and a preset optimizer, a preset multi-task learning model is trained to obtain a load forecasting model;

[0020] The load demand of electrical equipment in a preset time period in the future is predicted based on the load forecasting model.

[0021] The present invention provides a multi-load equipment energy consumption management method, which adopts a preset multi-task learning model to predict the load demand of electrical equipment in a preset time period in the future, realizes the monitoring and prediction of the load state of electrical equipment, and provides conditions for the subsequent dynamic power allocation of electrical equipment.

[0022] In an optional implementation, a multi-objective optimization model is generated based on power consumption equipment priorities, load demands, and electricity price data, and a dynamic power allocation scheme for power consumption equipment is generated based on the multi-objective optimization model, including:

[0023] Get the number of electrical equipment;

[0024] Determine the cost objective function based on the power equipment priority, load demand, electricity price data and the number of power equipment;

[0025] Determine the peak objective function based on load demand and the number of electrical equipment;

[0026] Determine a first weight of a cost objective function and a second weight of a peak objective function based on the power equipment priority, load demand, and power price data;

[0027] generating a multi-objective optimization model based on the first weight, the second weight, the cost objective function, and the peak objective function;

[0028] Generate dynamic power allocation scheme for electrical equipment based on multi-objective optimization model.

[0029] The present invention provides a multi-load equipment energy consumption management method, which constructs a multi-objective optimization model through a cost objective function, a peak objective function and corresponding weights, and generates a dynamic power allocation plan for electrical equipment based on the multi-objective optimization model to ensure that high-priority equipment is always stably supplied and low-priority equipment can be flexibly adjusted according to system scheduling.

[0030] In an optional implementation, the cost objective function is expressed by the following formula:

[0031] ;

[0032] in, is the cost objective function value, The total duration of the optimization time period; is the total number of electrical equipment; is the power output of the electrical equipment d at time t;

[0033] The peak objective function is expressed as follows:

[0034] ;

[0035] in, is the peak objective function value, The peak target is to find the maximum value of the total load at each moment, that is, the load peak value; For the calculation of all moments within the optimization period; is the total power output of all electrical equipment at time t;

[0036] The multi-objective optimization model is expressed by the following formula:

[0037] ;

[0038] in, is the overall optimization goal, , represent the first weight and the second weight respectively.

[0039] In an optional implementation, generating a dynamic power allocation scheme for electric equipment based on a multi-objective optimization model includes:

[0040] Obtain peak electricity price hours and peak load hours;

[0041] Generate a dynamic power allocation plan based on electricity price peak hours, load peak hours and multi-objective optimization functions.

[0042] In an optional implementation, a dynamic power allocation scheme is generated based on the peak electricity price period, the peak load period and a multi-objective optimization function, including:

[0043] During peak electricity price periods, increase the first weight in the multi-objective optimization function , reduce the power output of low-priority equipment and generate an optimized control operation cost plan;

[0044] During peak load periods, increase the second weight in the multi-objective optimization function , reduce the power output of medium-priority and low-priority devices and make high-priority devices operate stably, and generate an optimized load peak solution;

[0045] The scheme for optimizing the control of operating costs and the scheme for optimizing the load peak are combined to form a dynamic power allocation scheme.

[0046] The present invention provides a method for managing energy consumption of multiple load devices. During peak electricity price periods, the first weight in the multi-objective optimization function is increased, the power output of low-priority devices is reduced, and an optimized control operation cost plan is generated; during peak load periods, the second weight in the multi-objective optimization function is increased, the power output of medium-priority devices and low-priority devices is reduced and high-priority devices are allowed to operate stably, and an optimized load peak plan is generated, thereby realizing the generation of a dynamic power allocation mechanism based on real-time load feedback, so that the power system has the ability to adaptively adjust to peak loads or electricity price fluctuations.

[0047] In an optional implementation, adjusting the dynamic power allocation scheme of the electrical equipment based on load demand and real-time feedback data from the external environment includes:

[0048] When the actual load of the power-consuming equipment is higher than the load demand, the optimized load peak solution is continued to be used by reducing the power output of the medium-priority equipment and the low-priority equipment and making the high-priority equipment operate stably;

[0049] If the photovoltaic power generation in the external environment increases, photovoltaic power generation will be used to power electrical equipment first, and the operating cost control plan will be adjusted and optimized.

[0050] The present invention provides a multi-load equipment energy consumption management method. When the actual load of the electrical equipment is higher than the load demand, the power output of the medium-priority equipment and the low-priority equipment is reduced and the high-priority equipment is allowed to operate stably, and the optimized load peak plan is continued to be used. If the photovoltaic power generation in the external environment increases, the photovoltaic power generation is used preferentially to power the electrical equipment, and the operation cost control plan is adjusted and optimized, so that the power system has the adaptive adjustment capability of the closed-loop feedback mechanism, especially the rapid response and scheduling optimization capability when dealing with sudden load changes.

[0051] In a second aspect, the present invention provides a multi-load equipment energy consumption management device, the device comprising:

[0052] The power equipment priority classification module is used to obtain electricity price data and energy consumption data, operating status and load demand of the power equipment, and classify the priority of the power equipment based on the electricity price data, energy consumption data, operating status and load demand;

[0053] A load demand prediction module is used to predict the load demand of electrical equipment in a preset time period in the future using a preset multi-task learning model;

[0054] A dynamic power allocation scheme generation module is used to generate a multi-objective optimization model based on the priority of power consumption equipment, load demand and electricity price data, and generate a dynamic power allocation scheme for power consumption equipment based on the multi-objective optimization model;

[0055] The closed-loop control module is used to obtain the load demand and external environment of the electrical equipment in real time, and adjust the dynamic power allocation plan of the electrical equipment based on the load demand and external environment.

[0056] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the multi-load device energy consumption management method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0057] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the multi-load device energy consumption management method of the first aspect or any corresponding embodiment thereof.

[0058] In a fifth aspect, the present invention provides a computer program product, including computer instructions, which are used to enable a computer to execute the multi-load device energy consumption management method of the above-mentioned first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0060] Figure 1 is a flow chart of a method for managing energy consumption of multiple load devices according to an embodiment of the present invention;

[0061] Figure 2 is a flow chart of another multi-load device energy consumption management method according to an embodiment of the present invention;

[0062] Figure 3 is a flow chart of another multi-load device energy consumption management method according to an embodiment of the present invention;

[0063] Figure 4 is a flow chart of another method for managing energy consumption of multiple load devices according to an embodiment of the present invention;

[0064] Figure 5 is a structural block diagram of a device for managing energy consumption of multiple load devices according to an embodiment of the present invention;

[0065] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0067] According to an embodiment of the present invention, an embodiment of a method for managing energy consumption of multiple load devices is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0068] In this embodiment, a multi-load device energy consumption management method is provided, which can be used in a power system. Figure 1 is a flow chart of a method for managing energy consumption of multiple load devices according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0069] Step S101 , obtaining electricity price data and energy consumption data, operating status and load demand of electrical equipment, and classifying the priorities of electrical equipment based on the electricity price data, energy consumption data, operating status and load demand.

[0070] Specifically, in a large industrial park, there are multiple types of electrical equipment. The park's intelligent energy management platform collects real-time power consumption (energy consumption data), operating status, load demand and other data of the electrical equipment through smart meters, sensors and control modules installed on various electrical equipment.

[0071] Electricity price data refers to the tiered electricity price data within a day. Electricity-consuming equipment includes production equipment, air conditioning systems, lighting systems, and charging piles. The priority of electricity-consuming equipment is classified based on electricity price data, energy consumption data, operating status, and load demand. For example:

[0072] Production equipment has high requirements for energy consumption and operational stability and does not allow frequent shutdowns, so it can be defined as the highest priority electrical equipment. The air conditioning system is sensitive to operating time, but the power output can be adjusted dynamically, so it can be defined as a medium priority device. The lighting system and charging pile can flexibly adjust the operating time and power output according to the fluctuation of electricity price data and load conditions, and are flexible to use, so they can be defined as low priority equipment.

[0073] Step S102: using a preset multi-task learning model to predict the load demand of the electrical equipment in a preset time period in the future.

[0074] Specifically, the preset multi-task learning model can use LSTM (Long Short-Term Memory, long short-term memory network), and use LSTM to predict the load demand of the power equipment in the future preset time period. The future preset time period can be set according to actual conditions, and no specific restrictions are made here. In this embodiment, the future preset time period is the next 24 hours.

[0075] Step S103, generating a multi-objective optimization model based on the power consumption equipment priority, load demand and electricity price data, and generating a dynamic power allocation plan for the power consumption equipment based on the multi-objective optimization model.

[0076] Specifically, the multi-objective optimization model in this embodiment includes a load peak target and an operating cost target. Generating a dynamic power allocation plan for electrical equipment based on the multi-objective optimization model refers to controlling the load peak target and optimizing the operating cost target of the electrical equipment to achieve a power allocation plan in a dynamic balance state between the two.

[0077] Step S104, obtaining the load demand and external environment of the electrical equipment in real time, and adjusting the dynamic power allocation scheme of the electrical equipment based on the load demand and external environment.

[0078] Specifically, through closed-loop feedback control, the load demand and external environment of the power equipment are obtained in real time, and the dynamic power allocation plan of the power equipment is continuously optimized through the feedback mechanism, so that the power system is always in the best operating state.

[0079] The multi-load equipment energy consumption management method provided in this embodiment prioritizes the electrical equipment and predicts the load demand, generates a multi-objective optimization model based on the priority, load demand and electricity price data of the electrical equipment, generates a dynamic power allocation plan for the electrical equipment based on the multi-objective optimization model, dynamically adjusts the power allocation to ensure that high-priority equipment is always stably supplied, and low-priority equipment can be flexibly adjusted according to system scheduling. The load demand and external environment of the electrical equipment are obtained in real time through closed-loop feedback control, and the dynamic power allocation plan is continuously optimized through a feedback mechanism, so that the electrical equipment is always in the best operating state, so that energy consumption optimization and operating efficiency are always balanced, thereby solving the problem of failing to strike a balance between energy consumption optimization and operating efficiency.

[0080] In this embodiment, a multi-load device energy consumption management method is provided, which can be used in a power system. Figure 2 is a flow chart of a method for managing energy consumption of multiple load devices according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0081] Step S201 , obtaining electricity price data and energy consumption data, operating status and load demand of electrical equipment, and classifying the priorities of electrical equipment based on the electricity price data, energy consumption data, operating status and load demand.

[0082] Specifically, the above step S201 includes:

[0083] Step S2011: Classify the electrical equipment whose energy consumption data and operating status need to be kept stable and whose intermittent shutdown is not allowed as high-priority equipment.

[0084] For example, production equipment has high requirements on energy consumption and operation stability, and frequent shutdowns are not allowed. To ensure the normal operation of production equipment, the production equipment needs to be powered uninterruptedly. Therefore, production equipment can be classified as high-priority equipment.

[0085] Step S2012: Classify the electrical equipment that needs to be operated based on the operating time and whose load demand needs to be dynamically adjusted as medium priority equipment.

[0086] For example, the air conditioning system is sensitive to the operating time, but its power output can be adjusted dynamically. It only needs to ensure that the air conditioning system is powered uninterruptedly during the operating time of the air conditioning system. Therefore, the air conditioning system can be classified as a medium priority device.

[0087] Step S2013: classify the electrical equipment that needs to be dynamically adjusted based on electricity price data fluctuations and load demand as low priority equipment.

[0088] For example, lighting systems and charging piles can flexibly adjust operating hours and power output according to electricity price fluctuations and load conditions. There is no rigid limit on operating hours and they can be flexibly controlled. In order to achieve cost control, they can be used during low-peak electricity price periods. Therefore, lighting systems and charging piles can be classified as low-priority devices.

[0089] Step S202: Use a preset multi-task learning model to predict the load demand of the electrical equipment in a preset time period in the future.

[0090] Specifically, the above step S202 includes:

[0091] Step S2021, obtaining multi-dimensional time series data of electrical equipment, the multi-dimensional time series data including historical load data, historical electricity price data and historical weather data.

[0092] Specifically, historical load data of electric equipment, historical electricity price data, and historical weather data corresponding to the operation period of the electric equipment can be obtained from a database in the power system.

[0093] Step S2022: Use a preset multi-task learning model to extract the time series characteristics of the load change trend of the electrical equipment from the multi-dimensional time series data.

[0094] Specifically, in this embodiment, the preset multi-task learning model adopts LSTM, which includes an input layer, a shared hidden layer and a task-specific output layer. Electricity price data, load demand data, etc. are input into the input layer, and the time series characteristics of the load change trend are extracted in the shared hidden layer, and the load demand for future time periods is independently predicted through the task-specific output layer.

[0095] Step S2023, training the preset multi-task learning model based on the time series characteristics of the load change trend of the electrical equipment, the preset loss function and the preset optimizer to obtain a load forecasting model.

[0096] Specifically, the weighted mean squared error (MSE) is used as the preset loss function to balance the importance of tasks. During the training process, the optimizer is Adam, which is used to accelerate convergence. The specific training process is a mature related technology and will not be repeated here.

[0097] Step S2024: predicting the load demand of the electrical equipment in a preset time period in the future based on the load prediction model.

[0098] Specifically, the current load data of the electrical equipment is obtained, and the current load data of the electrical equipment is input into the load prediction model to obtain the load demand of the electrical equipment in the future preset time period. For example, the load demand prediction results of each electrical equipment are as follows:

[0099] Production equipment: Since its operating time and load are relatively stable, the system predicts that the load will remain at a high level during the daytime in the future working days.

[0100] Air conditioning system: By combining weather forecasts and historical usage data, it is predicted that load will peak during the midday period.

[0101] Charging stations: The power system predicts peak charging demand to be concentrated in the morning and evening. Based on historical usage patterns, the load will be higher in the evening.

[0102] Lighting system: Based on ambient light and historical data, it is predicted that the peak lighting demand in the evening will occur between 18:00 and 21:00.

[0103] Step S203: Generate a multi-objective optimization model based on the power equipment priority, load demand and electricity price data, and generate a dynamic power allocation plan for the power equipment based on the multi-objective optimization model. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0104] Step S204, acquiring the load demand and external environment of the electrical equipment in real time, and adjusting the dynamic power allocation scheme of the electrical equipment based on the load demand and external environment.

[0105] The multi-load equipment energy consumption management method provided in this embodiment divides the electrical equipment into high-priority equipment, medium-priority equipment and low-priority equipment based on energy consumption data, operating status and load demand. Through the priority classification and real-time monitoring of the electrical equipment, the electrical equipment can be intelligently scheduled according to the actual situation to ensure the normal operation of important electrical equipment. The preset multi-task learning model is used to predict the load demand of the electrical equipment in the future preset time period, thereby realizing the monitoring and prediction of the load status of the electrical equipment and providing conditions for the subsequent dynamic power allocation of the electrical equipment.

[0106] In this embodiment, a multi-load device energy consumption management method is provided, which can be used in a power system. Figure 3 is a flow chart of a method for managing energy consumption of multiple load devices according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0107] Step S301, obtain electricity price data and energy consumption data, operating status and load demand of electrical equipment, and classify the priorities of electrical equipment based on electricity price data, energy consumption data, operating status and load demand. Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0108] Step S302: Use a preset multi-task learning model to predict the load demand of the power equipment in a preset time period in the future. Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0109] Step S303: generating a multi-objective optimization model based on the power consumption equipment priority, load demand and electricity price data, and generating a dynamic power allocation plan for the power consumption equipment based on the multi-objective optimization model.

[0110] Specifically, the above step S303 includes:

[0111] Step S3031, obtaining the number of electrical devices.

[0112] For example, in a large industrial park, obtain the number of all electrical equipment in the park, including all production equipment, air-conditioning systems, lighting systems and charging piles.

[0113] Step S3032, determining the cost objective function based on the power consumption equipment priority, load demand, electricity price data and the number of power consumption equipment.

[0114] Specifically, Figure 4 As shown, the cost objective function is expressed by the following formula:

[0115] (1);

[0116] in, is the cost objective function value, The total duration of the optimization time period, such as 24 hours in a day; is the total number of electrical equipment; is the power output of the electrical equipment d at time t, It is a key variable in power system regulation, which determines the power distribution of each power-consuming device at different time points; The electricity price data at time t. The electricity price will fluctuate during the day. For example, the electricity price is higher during the peak period in the evening and lower at night.

[0117] The purpose of the cost objective function is to calculate the total electricity cost. , which can reduce the consumption of expensive electricity and thus reduce operating costs.

[0118] For example, the electricity price is higher between 5pm and 9pm, when the power demand of charging piles and lighting systems is relatively high. The cost objective function value is calculated according to formula (1), and the power output of low-priority equipment is automatically reduced, so that high-priority production equipment can obtain stable power supply first, thereby reducing unnecessary high electricity price expenditures.

[0119] Step S3033, determining the peak objective function based on the load demand and the number of electrical equipment.

[0120] Specifically, Figure 4 As shown, the peak objective function is expressed by the following formula:

[0121] (2);

[0122] in, is the peak objective function value, The goal of formula (2) is to find the maximum value of the total load at each moment, that is, the load peak value; For the calculation of all moments within the optimization period; is the total power output of all electrical devices at time t.

[0123] The peak objective function is used to control the load peak of the entire park to ensure that the total load is not too high and to avoid overloading the power system. The power system keeps the load peak within a reasonable range by reducing the power output of low-priority equipment.

[0124] For example, during the noon period, when the air conditioning system, charging piles, and lighting system are turned on at the same time, the total load may exceed the carrying capacity of the entire park. According to formula (2), the power output of the charging piles and lighting system is automatically reduced to prioritize the stable operation of production equipment and avoid exceeding the load limit of the entire park.

[0125] Step S3034: determine a first weight of the cost objective function and a second weight of the peak objective function based on the electrical equipment priority, load demand and electricity price data.

[0126] Specifically, the first weight of the cost objective function is Indicates that the second weight of the peak objective function is Indicates that the first weight Control the power system's focus on cost targets, the second weight Control the power system's focus on load peak targets.

[0127] In order to optimize the cost target and the load peak target and achieve a balance between the two, the first weight should be adjusted according to the actual situation. and the second weight For example, during peak load periods (such as noon), the system will increase the second weight value, giving priority to optimizing load peaks to prevent overloading of electrical equipment.

[0128] For the first weight and the second weight Dynamic adjustment enables the power system to flexibly respond to different operating conditions and ensure optimal cost control and load management in different time periods.

[0129] Step S3035, generating a multi-objective optimization model based on the first weight, the second weight, the cost objective function and the peak objective function.

[0130] Specifically, the multi-objective optimization model is expressed by the following formula:

[0131] (3);

[0132] in, is the overall optimization goal, and formula (3) represents the overall optimization goal of the power system, combined with the cost objective function and peak objective function , while optimizing operating costs and load peak control. and the second weight Determines the focus of the power system during optimization.

[0133] Step S3036: Generate a dynamic power allocation plan for the electrical equipment based on the multi-objective optimization model.

[0134] In some optional implementations, the above step S3036 includes:

[0135] Step b1, obtaining the peak electricity price period and the peak load period.

[0136] Peak electricity price hours are from 5pm to 9pm every day.

[0137] The peak load period is, for example, 12 noon every day.

[0138] Step b2, generating a dynamic power allocation plan based on the electricity price peak period, load peak period and a multi-objective optimization function.

[0139] In some optional embodiments, step b2 includes:

[0140] Step b21, during the peak electricity price period, increase the first weight in the multi-objective optimization function, reduce the power output of low-priority equipment, and generate an optimized control operation cost plan.

[0141] For example, during peak electricity prices (such as 5pm to 9pm): If set higher, operating costs will be prioritized, reducing electricity bills by reducing the power output of low-priority devices, such as charging stations and lighting systems.

[0142] Step b22, during the load peak period, increase the second weight in the multi-objective optimization function, reduce the power output of medium priority devices and low priority devices and make the high priority devices run stably, and generate an optimized load peak solution.

[0143] For example, during peak load periods (such as noon), the second weight Set it higher to control the load peak and give priority to reducing the medium-priority and low-priority equipment, that is, reduce the power output of the air-conditioning system, lighting system and charging piles to ensure that the total load is within the carrying capacity.

[0144] Step b23, combining the optimization control operation cost scheme and the optimization load peak scheme to form a dynamic power allocation scheme.

[0145] The above steps realize the adaptive distributed dispatching mechanism of the power system, and dynamically allocate the power output of each power-consuming device:

[0146] Power is always allocated to production equipment first to ensure that normal production tasks are not affected.

[0147] The power allocation of the air conditioning system is dynamically adjusted based on the forecast results and actual operation conditions. When the overall load of the park is high (such as during the noon period), the output power of the air conditioning system will be reduced as needed to reduce energy consumption.

[0148] During the peak electricity consumption in the evening, the system prioritizes allocating photovoltaic power to charging piles, reducing the expenditure on purchasing electricity from the power grid.

[0149] The multi-load equipment energy consumption management method provided in this embodiment increases the first weight in the multi-objective optimization function during the peak electricity price period, reduces the power output of low-priority equipment, and generates an optimized control operation cost plan; during the peak load period, increases the second weight in the multi-objective optimization function, reduces the power output of medium-priority equipment and low-priority equipment and enables high-priority equipment to operate stably, generates an optimized load peak plan, and realizes the generation of a dynamic power allocation mechanism based on real-time load feedback, so that the power system has the ability to adaptively adjust to load peaks or electricity price fluctuations.

[0150] Step S304, obtaining the load demand and external environment of the electrical equipment in real time, and adjusting the dynamic power allocation scheme of the electrical equipment based on the load demand and external environment.

[0151] Specifically, the external environment includes weather data and electricity price data, as well as photovoltaic power generation data.

[0152] The above step S304 includes:

[0153] Step S3041, when the actual load of the electrical equipment is higher than the load demand, the load peak optimization scheme is continued to be used by reducing the power output of the medium priority equipment and the low priority equipment and making the high priority equipment run stably.

[0154] Specifically, when the actual load is higher than predicted (for example, a production line suddenly increases its load demand), the power system will ensure the normal operation of production equipment by lowering the output power of medium-priority and low-priority equipment, that is, lowering the output power of the air-conditioning system and lighting system.

[0155] Step S3042: if the photovoltaic power generation in the external environment increases, the photovoltaic power generation is used preferentially to supply power to the electrical equipment, and the operation cost control scheme is adjusted and optimized.

[0156] Specifically, if the amount of photovoltaic power generation increases, the system will prioritize using it to meet the peak load of the park, reducing the amount of electricity purchased from the grid, thereby saving costs.

[0157] The multi-load equipment energy consumption management method provided in this embodiment constructs a multi-objective optimization model through the cost objective function and the peak objective function and the corresponding weights, and generates a dynamic power allocation plan for the power-consuming equipment based on the multi-objective optimization model to ensure that high-priority equipment is always stably supplied and low-priority equipment can be flexibly adjusted according to system scheduling. Through closed-loop feedback control, the power system has the adaptive adjustment capability of the closed-loop feedback mechanism, especially the rapid response and scheduling optimization capability when dealing with sudden load changes.

[0158] As one or more specific application embodiments of the embodiments of the present invention, the multi-load device energy consumption management method provided by the present invention is further described in detail as follows:

[0159] This embodiment focuses on the needs of an industrial park. In a large industrial park, there are multiple types of electrical equipment, including production equipment, air conditioning systems, lighting equipment, and charging piles. Each type of equipment has different energy consumption characteristics, operating requirements, and load changes. In order to maximize energy efficiency and reduce electricity expenses during peak hours, the park adopts the multi-load equipment energy consumption management method of the present invention.

[0160] The core load equipment is as follows:

[0161] Production equipment: Constant operating power of 100 kW, stable operation throughout the day is required.

[0162] Air conditioning system: The power can be flexibly adjusted, ranging from 50-100 kW, and operates from 8:00 to 20:00 daily.

[0163] Lighting system: fixed power 20 kW, lit from 18:00 to 6:00 the next day.

[0164] Charging piles: Maximum load 50 kW, with peak usage between 7:00–9:00 and 17:00–20:00.

[0165] Electricity price difference: During peak hours (17:00–21:00), the electricity fee is 1.5 yuan / kWh, and during other periods, it is 0.8 yuan / kWh.

[0166] The total load limit of the park is set at 200 kW.

[0167] The operation process is as follows:

[0168] 1. Data collection and priority classification: Real-time collection of data such as energy consumption and operating status of equipment in the park, and classification based on importance:

[0169] High priority equipment: production equipment.

[0170] Medium priority equipment: air conditioning systems.

[0171] Low priority equipment: lighting systems and charging stations.

[0172] 2. Load forecast: Combine historical records with real-time status to estimate the load demand in the next 24 hours:

[0173] Production equipment: Stable throughout the day, with a constant load of 100 kW.

[0174] Air conditioning system: peaks at 100 kW at 12:00 and 16:00 respectively.

[0175] Lighting system: Nighttime demand from 18:00 to 21:00 is 20 kW.

[0176] Charging piles: Peak demands in the morning and evening are 30 kW and 50 kW respectively.

[0177] 3. Dynamic scheduling optimization: Use multi-objective algorithms to flexibly adjust equipment power allocation:

[0178] Peak electricity price period (17:00–21:00):

[0179] The production equipment maintains 100 kW.

[0180] The air conditioning system is turned down to 80 kW.

[0181] The lighting system remains at 20 kW.

[0182] The charging stations will be delayed until after 21:00 to avoid peak electricity charges.

[0183] Low electricity price period:

[0184] The air conditioning system was restored to 100 kW.

[0185] The charging station operates at full capacity from 22:00 to 6:00 the next day, with a power of 50 kW.

[0186] 4. Closed-loop feedback and real-time adjustment: The system continuously monitors the actual load and makes dynamic adjustments based on changes:

[0187] If the air conditioning demand increases to 110 kW, the charging pile power will be reduced to 40 kW to ensure that the total load does not exceed 200 kW.

[0188] If the increase in photovoltaic power generation reaches 30 kW, it will be supplied to air-conditioning systems and charging piles first, reducing dependence on the external power grid.

[0189] Implementation results:

[0190] Cost reduction: By adjusting the operating hours of charging piles, electricity bills can be saved by about 300 yuan per day.

[0191] Load peak control: The maximum load was successfully controlled below 200 kW, effectively preventing system overload.

[0192] The multi-load equipment energy consumption management method provided in this embodiment has a dynamic power allocation function. It dynamically adjusts the power allocation according to the real-time load demand and priority of the equipment to ensure that high-priority equipment is always stably supplied, and low-priority equipment can be flexibly adjusted according to the power system scheduling. Through closed-loop feedback control, the energy consumption data and load demand of electrical equipment are collected in real time, and the scheduling decisions are continuously optimized through the feedback mechanism, so that the power system is always in the best operating state. The dynamic power allocation mechanism of this embodiment can be applied to multi-load equipment systems, such as charging pile management, electrical appliance scheduling in smart homes, and other scenarios to ensure the optimal energy efficiency of the overall system. The closed-loop control of this embodiment is particularly suitable for dynamic load management scenarios, such as energy consumption optimization of industrial equipment, load scheduling of smart microgrids, etc.

[0193] In this embodiment, a multi-load equipment energy consumption management device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0194] This embodiment provides a multi-load equipment energy consumption management device, such as Figure 5 As shown, including:

[0195] The power equipment priority classification module 501 is used to obtain electricity price data and energy consumption data, operating status and load demand of the power equipment, and classify the priority of the power equipment based on the electricity price data, energy consumption data, operating status and load demand.

[0196] The load demand prediction module 502 is used to predict the load demand of the electrical equipment in a preset time period in the future by using a preset multi-task learning model.

[0197] The dynamic power allocation scheme generating module 503 is used to generate a multi-objective optimization model based on the power consumption equipment priority, load demand and electricity price data, and to generate a dynamic power allocation scheme for the power consumption equipment based on the multi-objective optimization model.

[0198] The closed-loop control module 504 is used to obtain the load demand and external environment of the electrical equipment in real time, and adjust the dynamic power allocation scheme of the electrical equipment based on the load demand and external environment.

[0199] In some optional implementations, the electric device priority classification module 501 includes:

[0200] The high-priority equipment classification unit is used to classify electrical equipment, which requires energy consumption data and operating status to be kept stable and does not allow intermittent shutdown, as high-priority equipment.

[0201] The medium priority classification unit is used to classify the power-consuming equipment that needs to be operated based on the operating time and whose load demand is dynamically adjusted as medium priority equipment.

[0202] The low priority classification unit is used to classify the power-consuming equipment that needs to be dynamically adjusted based on the fluctuation of electricity price data and load demand as low priority equipment.

[0203] In some optional implementations, the load demand forecasting module 502 includes:

[0204] The multi-dimensional time series data acquisition unit is used to acquire multi-dimensional time series data of power-consuming equipment, and the multi-dimensional time series data includes historical load data, historical electricity price data and historical weather data.

[0205] The load change trend time series feature extraction unit is used to extract the load change trend time series features of the electrical equipment from the multi-dimensional time series data using a preset multi-task learning model.

[0206] The model training unit is used to train the preset multi-task learning model based on the time series characteristics of the load change trend of the power equipment, the preset loss function and the preset optimizer to obtain the load forecasting model.

[0207] The load demand prediction unit is used to predict the load demand of the power equipment in a preset time period in the future based on the load prediction model.

[0208] In some optional implementations, the dynamic power allocation scheme generating module 503 includes:

[0209] The power-consuming device quantity acquisition unit is used to acquire the power-consuming device quantity.

[0210] The cost objective function determination unit is used to determine the cost objective function based on the power consumption equipment priority, load demand, electricity price data and the number of power consumption equipment.

[0211] The peak target function determination unit is used to determine the peak target function based on load demand and the number of electrical equipment.

[0212] A weight determination unit is used to determine a first weight of a cost objective function and a second weight of a peak objective function based on power consumption equipment priority, load demand and electricity price data.

[0213] The multi-objective optimization model generating unit is used to generate the multi-objective optimization model based on the first weight, the second weight, the cost objective function and the peak objective function.

[0214] The dynamic power allocation scheme generating unit is used to generate a dynamic power allocation scheme for electrical equipment based on a multi-objective optimization model.

[0215] Among them, the cost objective function is expressed by the following formula:

[0216] ;

[0217] in, is the cost objective function value, The total duration of the optimization time period; is the total number of electrical equipment; is the power output of the electrical equipment d at time t;

[0218] The peak objective function is expressed as follows:

[0219] ;

[0220] in, is the peak objective function value, The peak target is to find the maximum value of the total load at each moment, that is, the load peak value; For the calculation of all moments within the optimization period; is the total power output of all electrical equipment at time t;

[0221] The multi-objective optimization model is expressed by the following formula:

[0222] ;

[0223] in, is the overall optimization goal, , represent the first weight and the second weight respectively.

[0224] In some optional implementations, the dynamic power allocation scheme generating unit includes:

[0225] The electricity price peak time period and the load peak time period acquisition subunit is used to acquire the electricity price peak time period and the load peak time period;

[0226] The dynamic power allocation scheme generation subunit is used to generate a dynamic power allocation scheme based on the peak electricity price period, the peak load period and the multi-objective optimization function, wherein, during the peak electricity price period, the first weight in the multi-objective optimization function is increased, the power output of the low-priority equipment is reduced, and an optimized control operation cost scheme is generated; during the peak load period, the second weight in the multi-objective optimization function is increased, the power output of the medium-priority equipment and the low-priority equipment is reduced and the high-priority equipment is allowed to operate stably, and an optimized load peak scheme is generated; the optimized control operation cost scheme and the optimized load peak scheme are combined to form a dynamic power allocation scheme.

[0227] In some optional implementations, the closed-loop control module 504 includes:

[0228] The first closed-loop control unit is used to continue to use the optimized load peak solution by reducing the power output of the medium-priority device and the low-priority device and making the high-priority device run stably when the actual load of the electrical device is higher than the load demand.

[0229] The second closed-loop control unit is used to give priority to using photovoltaic power generation to supply power to electrical equipment if the photovoltaic power generation in the external environment increases, and to adjust and optimize the control operation cost plan.

[0230] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0231] The multi-load equipment energy consumption management device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0232] The embodiment of the present invention also provides a computer device having the above Figure 5 The energy consumption management device for multiple load devices is shown.

[0233] See also Figure 6 , Figure 6 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 6 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0234] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0235] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0236] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0237] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0238] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0239] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, an indicator rod, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device may be a touch screen. The embodiment of the present invention also provides a computer-readable storage medium, and the method according to the embodiment of the present invention described above can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or is implemented by downloading through a network and originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor or programmable or dedicated hardware. The storage medium may be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid state drive, etc.; further, the storage medium may also include a combination of the above-mentioned types of memories. It is understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by the computer, processor or hardware, the method shown in the above embodiment is implemented.

[0240] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0241] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for managing energy consumption of multiple load devices, characterized in that: The method comprises: Obtaining electricity price data and energy consumption data, operating status and load demand of electrical equipment, and classifying the priorities of electrical equipment based on the electricity price data, energy consumption data, operating status and load demand; Use a preset multi-task learning model to predict the load demand of electrical equipment in a preset time period in the future; Generate a multi-objective optimization model based on power consumption equipment priority, load demand and electricity price data, and generate a dynamic power allocation plan for the power consumption equipment based on the multi-objective optimization model; Obtain the load demand and external environment of the power equipment in real time, and adjust the dynamic power allocation plan of the power equipment based on the load demand and external environment; The method of generating a multi-objective optimization model based on the power consumption equipment priority, load demand and electricity price data, and generating a dynamic power allocation scheme for the power consumption equipment based on the multi-objective optimization model includes: Get the number of electrical equipment; Determine the cost objective function based on the priority of power equipment, load demand, electricity price data and the number of power equipment; the cost objective function is used to calculate the total electricity cost, and reduce the consumption of high-priced electricity and reduce operating costs by reducing the power of power equipment during high-price periods; Determine the peak objective function based on load demand and the number of electrical equipment; the peak objective function is used to control the load peak to ensure that the total load does not exceed the power system load; Determine a first weight of a cost objective function and a second weight of a peak objective function based on the power equipment priority, load demand, and power price data; generating a multi-objective optimization model based on the first weight, the second weight, the cost objective function, and the peak objective function; Generate a dynamic power allocation plan for electrical equipment based on the multi-objective optimization model; The generating a dynamic power allocation scheme for electric equipment based on the multi-objective optimization model comprises: Obtain peak electricity price hours and peak load hours; Generate dynamic power allocation scheme based on peak electricity price period, peak load period and multi-objective optimization function; The generating of a dynamic power allocation scheme based on the peak period of electricity price, the peak period of load and the multi-objective optimization function includes: During peak electricity price periods, increase the first weight in the multi-objective optimization function , reduce the power output of low-priority equipment and generate an optimized control operation cost plan; During peak load periods, increase the second weight in the multi-objective optimization function , reduce the power output of medium-priority and low-priority devices and make high-priority devices operate stably, and generate an optimized load peak solution; The scheme for optimizing the control of operating costs and the scheme for optimizing the load peak are combined to form a dynamic power allocation scheme.

2. The multi-load equipment energy consumption management method according to claim 1, characterized in that: The operating status includes the operating time, and the priority of the electrical equipment is classified based on the electricity price data, energy consumption data, operating status and load demand, including: Classify electrical equipment that requires stable energy consumption data and operating status and does not allow intermittent shutdown as high-priority equipment; Classify power-consuming equipment that needs to be operated based on operating hours and whose load demand is dynamically adjusted as medium-priority equipment; Electrical equipment that needs to be dynamically adjusted based on fluctuations in electricity price data and load demand will be classified as low-priority equipment.

3. The multi-load equipment energy consumption management method according to claim 1, characterized in that: The method of using a preset multi-task learning model to predict the load demand of the electrical equipment in a preset time period in the future includes: Acquire multi-dimensional time series data of electric equipment, wherein the multi-dimensional time series data includes historical load data, historical electricity price data and historical weather data; Using a preset multi-task learning model to extract the time series characteristics of load change trends of electrical equipment from the multi-dimensional time series data; Based on the time series characteristics of load change trends of electrical equipment, a preset loss function and a preset optimizer, a preset multi-task learning model is trained to obtain a load forecasting model; The load demand of electrical equipment in a preset time period in the future is predicted based on the load forecasting model.

4. The multi-load equipment energy consumption management method according to claim 1, characterized in that: The cost objective function is expressed by the following formula: ； in, is the cost objective function value, The total duration of the optimization time period; is the total number of electrical equipment; is the power output of the electrical equipment d at time t; is the electricity price data at time t; The peak objective function is expressed by the following formula: ； in, is the peak objective function value, The peak target is to find the maximum value of the total load at each moment, that is, the load peak value; For the calculation of all moments within the optimization period; is the total power output of all electrical equipment at time t; The multi-objective optimization model is expressed by the following formula: ； in, is the overall optimization goal, , represent the first weight and the second weight respectively.

5. The multi-load equipment energy consumption management method according to claim 1, characterized in that: The dynamic power allocation scheme for adjusting the electrical equipment based on load demand and external environment includes: When the actual load of the power-consuming equipment is higher than the load demand, the optimized load peak solution is continued to be used by reducing the power output of the medium-priority equipment and the low-priority equipment and making the high-priority equipment operate stably; If the photovoltaic power generation in the external environment increases, photovoltaic power generation will be used to power electrical equipment first, and the operating cost control plan will be adjusted and optimized.

6. A multi-load equipment energy consumption management device, characterized in that: The device comprises: The power equipment priority classification module is used to obtain electricity price data and energy consumption data, operating status and load demand of the power equipment, and classify the priority of the power equipment based on the electricity price data, energy consumption data, operating status and load demand; A load demand prediction module is used to predict the load demand of electrical equipment in a preset time period in the future using a preset multi-task learning model; A dynamic power allocation scheme generation module, used to generate a multi-objective optimization model based on power equipment priority, load demand and electricity price data, and generate a dynamic power allocation scheme for the power equipment based on the multi-objective optimization model; A closed-loop control module is used to obtain the load demand and external environment of the power-consuming equipment in real time, and adjust the dynamic power allocation plan of the power-consuming equipment based on the load demand and external environment; The method of generating a multi-objective optimization model based on the power consumption equipment priority, load demand and electricity price data, and generating a dynamic power allocation scheme for the power consumption equipment based on the multi-objective optimization model includes: Get the number of electrical equipment; Determine the cost objective function based on the priority of power equipment, load demand, electricity price data and the number of power equipment; the cost objective function is used to calculate the total electricity cost, and reduce the consumption of high-priced electricity and reduce operating costs by reducing the power of power equipment during high-price periods; Determine the peak objective function based on load demand and the number of electrical equipment; the peak objective function is used to control the load peak to ensure that the total load does not exceed the power system load; Determine a first weight of a cost objective function and a second weight of a peak objective function based on the power equipment priority, load demand, and power price data; generating a multi-objective optimization model based on the first weight, the second weight, the cost objective function, and the peak objective function; Generate a dynamic power allocation plan for electrical equipment based on the multi-objective optimization model; The generating a dynamic power allocation scheme for electric equipment based on the multi-objective optimization model comprises: Obtain peak electricity price hours and peak load hours; Generate dynamic power allocation scheme based on peak electricity price period, peak load period and multi-objective optimization function; The generating of a dynamic power allocation scheme based on the peak electricity price period, the peak load period and the multi-objective optimization function includes: During peak electricity price periods, increase the first weight in the multi-objective optimization function , reduce the power output of low-priority equipment and generate an optimized control operation cost plan; During peak load periods, increase the second weight in the multi-objective optimization function , reduce the power output of medium-priority and low-priority devices and make high-priority devices operate stably, and generate an optimized load peak solution; The scheme for optimizing the control of operating costs and the scheme for optimizing the load peak are combined to form a dynamic power allocation scheme.

7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the multi-load equipment energy consumption management method according to any one of claims 1 to 5 by executing the computer instructions.

Images