Comprehensive energy system optimization scheduling method and system considering user satisfaction

Abstract

The invention provides an integrated energy system optimization scheduling method and system considering user satisfaction, and relates to the technical field of environmental protection energy optimization scheduling, and the method comprises the steps: obtaining user historical load data of a set step length, and carrying out the preprocessing of the user historical load data to obtain a user daily load curve; clustering the daily load curve of the user, searching an optimal value according to a set evaluation index, and obtaining a typical energy consumption mode of the user; according to a day-ahead load prediction result, the user satisfaction is quantized based on a Pearson coefficient in combination with the typical energy consumption mode of the user; and constructing an optimal scheduling model of the user energy consumption equipment, taking the user satisfaction and the minimum economic cost as optimization targets, solving the optimal scheduling model by utilizing Q-learning, obtaining a day-ahead scheduling result, and executing a day-ahead scheduling plan. According to the method, the reasonable scheduling scheme is customized according to the user satisfaction coefficient, so that the adaptability of the system optimization scheduling scheme is improved while the economy of the system is considered.

Description

Technical Field

[0001] The present disclosure relates to the technical field of environmental protection energy optimization scheduling, and in particular to a comprehensive energy system optimization scheduling method and system taking user satisfaction into consideration. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] As the proportion of new energy continues to increase, its intermittency and volatility have brought severe challenges to the stable and reliable operation of the integrated energy system. While ensuring the efficient operation of the energy supply side, the potential of adjustable resources on the user side can be effectively tapped to smooth the fluctuations of new energy and achieve a balance between supply and demand under a high proportion of new energy penetration, thereby improving the energy-saving potential of the entire system and ensuring the stable operation of the system. However, users' energy demand is obviously personalized, and it is difficult to customize the scheduling plan that suits the user's energy habits, which can easily increase the user's energy cost and cause energy waste. Based on this, studying the user's energy consumption behavior and reasonably quantifying it, and then incorporating it into the optimization goal, is conducive to achieving mutual benefit between supply and demand, further improving the optimization effect, and improving the feasibility of the optimization scheduling plan.

[0004] At present, among the existing research methods, the invention patent CN116128262A - A low-carbon scheduling method and system for an integrated energy system proposes an optimization framework of upper-level economic scheduling and lower-level low-carbon demand-side response, thereby realizing the economic and low-carbon operation of the integrated energy system; the invention patent CN15906456A - An optimization scheduling model for hydrogen energy storage IES considering the uncertainty of demand-side response proposes an optimization scheduling model that describes the uncertainty of the integrated demand response, thereby reducing the operating cost while optimizing the load curve; the invention patent CN115641209A - A method for constructing an integrated energy optimization model taking into account carbon trading and demand response takes the economic efficiency of the integrated energy system operation as the objective function, and simultaneously constructs a carbon trading cost model and a comprehensive demand response model, thereby effectively improving the system coordination and response capabilities.

[0005] However, it was found that although the above methods all optimized the impact of demand-side response during the optimization process, they ignored the impact of user satisfaction on the degree of demand-side response, and did not incorporate energy-consuming equipment into the optimization framework. It was impossible to truly achieve effective interaction between the supply and demand sides in the scheduling plan, and it was difficult to further improve the system operation effect. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a comprehensive energy system optimization scheduling method and system taking user satisfaction into consideration. By analyzing the user's energy consumption behavior and quantifying user satisfaction based on this, user satisfaction is effectively incorporated into the system optimization goal, thereby effectively improving the economy and effectiveness of system operation.

[0007] According to some embodiments, the present disclosure adopts the following technical solutions:

[0008] A comprehensive energy system optimization scheduling method considering user satisfaction includes:

[0009] Obtain historical user load data with a set step length, and preprocess it to obtain a user daily load curve;

[0010] Clustering the user's daily load curves, and finding the optimal value according to the set evaluation index to obtain the user's typical energy consumption mode;

[0011] According to the day-ahead load forecast result, the user satisfaction is quantified based on the Pearson coefficient and the typical energy consumption pattern of the user;

[0012] Construct an optimal scheduling model for user energy-consuming equipment, take user satisfaction and minimum economic cost as optimization goals, use Q-learning to solve the optimal scheduling model, obtain the day-ahead scheduling results, and execute the day-ahead scheduling plan.

[0013] According to some embodiments, the present disclosure adopts the following technical solutions:

[0014] An integrated energy system optimization dispatching system considering user satisfaction, comprising:

[0015] A data acquisition module is used to acquire historical user load data of a set step length and pre-process it to obtain a user daily load curve;

[0016] An energy consumption mode selection module is used to cluster the user's daily load curve and find the optimal value according to the set evaluation index to obtain the user's typical energy consumption mode;

[0017] A satisfaction quantification module is used to quantify user satisfaction based on the day-ahead load forecast result and the Pearson coefficient in combination with the user's typical energy consumption pattern;

[0018] The model building and solving module is used to build an optimal scheduling model for user energy-consuming equipment, taking user satisfaction and minimum economic cost as optimization goals, using Q-learning to solve the optimal scheduling model, obtaining the day-ahead scheduling results, and executing the day-ahead scheduling plan.

[0019] According to some embodiments, the present disclosure adopts the following technical solutions:

[0020] An electronic device comprises: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device implements the integrated energy system optimization scheduling method considering user satisfaction.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] The present invention discloses an integrated energy system optimization scheduling method considering user satisfaction, which applies the integrated energy system optimization scheduling method based on k-means++ and Q-Learning. First, k-means++ is used to cluster the user's historical daily energy load to obtain the user's typical energy consumption pattern; then, based on the Pearson coefficient and the user's typical energy consumption pattern, the user satisfaction is quantified; finally, the energy-consuming equipment is incorporated into the scheduling framework and solved using Q-Learning to obtain the day-ahead optimization scheduling result of the integrated energy system. By analyzing the user's energy consumption behavior and quantifying the user's satisfaction based on it, the user satisfaction is effectively incorporated into the system optimization goal, and a reasonable scheduling plan is customized according to the user satisfaction coefficient to fit the user's energy consumption habit, thereby improving the adaptability of the system optimization scheduling plan while taking into account the system economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0024] Figure 1 This is a diagram of the architecture of a comprehensive energy system including energy-consuming equipment according to an embodiment of the present disclosure;

[0025] Figure 2 This is a flowchart of the integrated energy system optimization scheduling method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0027] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0028] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0029] Example 1

[0030] In one embodiment of the present disclosure, a comprehensive energy system optimization scheduling method considering user satisfaction is provided, including:

[0031] Step 1: Obtain historical user load data with a set step length, and preprocess it to obtain the user daily load curve;

[0032] Step 2: clustering the user's daily load curve, and finding the optimal value according to the set evaluation index to obtain the user's typical energy consumption mode;

[0033] Step 3: According to the day-ahead load forecast result, the user satisfaction is quantified based on the Pearson coefficient and the typical energy consumption pattern of the user;

[0034] Step 4: Build an optimal scheduling model for user energy-consuming equipment, take user satisfaction and minimum economic cost as optimization goals, use Q-learning to solve the optimal scheduling model, obtain the day-ahead scheduling results, and execute the day-ahead scheduling plan.

[0035] As an example, Figure 2 As shown in the figure, the specific implementation process of an integrated energy system optimization scheduling method considering user satisfaction is as follows:

[0036] Step 1: Obtain historical load data with a step length of 1 hour, and divide it into different user daily load curves by day as cluster data;

[0037] Then, the user energy consumption behavior is clustered: k-means++ is used to cluster the user's daily load curve, and the DBI parameter is used as an evaluation index to find the optimal K value, obtain the user's typical energy consumption pattern, and establish a typical energy consumption pattern classifier.

[0038] Specifically, (1) find the optimal k value

[0039] The calculation rule of DBI is to select clustering results with close distance within clusters and far distance between clusters. The definition is shown in formula (1):

[0040]

[0041] Among them, I DBIis the DBI of the clustering result, n is the number of clusters, S i With S j are the average distances from the sample to the center of the cluster, M ij is the distance between the center of the i-th cluster and the center of the j-th cluster. DBI emphasizes both intra-cluster similarity and inter-cluster dissimilarity. The larger the DBI, the better the clustering effect.

[0042] Based on the above two clustering result evaluation indicators, the optimal K value is determined by the following criteria:

[0043] min(1-I SC +I DBI )(2) Select the k that minimizes equation (2) as the optimal K value.

[0044] (2) Cluster center initialization

[0045] Randomly select a point in the sample set as the first cluster center, calculate the shortest distance between each sample and the current center, and select the next cluster center using the roulette method based on the principle that the greater the distance, the greater the probability of being selected as the next cluster center. Repeat the above steps until k centers are selected.

[0046] (3) Sample classification

[0047] For each sample, the distance from it to the k centers is calculated and assigned to the cluster with the shortest distance (highest similarity).

[0048] (4) Cluster center update

[0049] Calculate the average value of the sample data in each cluster and update it as the new center of the cluster.

[0050] (5) Repeat steps (3) and (4) until the cluster center no longer changes.

[0051] The SI k-means++ algorithm is used to cluster the daily energy consumption curve of each energy-consuming subsystem into different behavior patterns. The input is shown in formula (3), and the clustering result output is formula (4):

[0052]

[0053] Where n is the subsystem number, s is the number of clustering days, is the representative parameter sequence of subsystem n on day d, is the clustering result on the dth day, and i is the type of behavior pattern.

[0054] Step 2: Use the load forecast curve as the input of the classifier obtained in step 1 to obtain the typical energy consumption pattern of the user in the future day, and quantify the user satisfaction based on the Pearson coefficient combined with the typical energy consumption pattern of the user, including: calculating the similarity between the daily load curve and the future energy consumption pattern through the Pearson coefficient, and quantifying the user satisfaction parameter:

[0055]

[0056] Among them, γ i ∈[-1,1] represents the similarity between the user's energy consumption behavior and the energy consumption curve after scheduling, γ i The larger the value, the higher the similarity, and the more it conforms to the user's daily energy usage habits, which means the higher the user satisfaction. is the energy consumption behavior of the user at time t for the dispatchable load i, is the average value of energy consumption behavior; is the dispatch result of adjustable load i at time t, is the scheduling average value.

[0057] Step 3: Construct an optimal dispatch model for user energy-consuming equipment, such as Figure 1 As shown, it includes energy supply side equipment modeling and user side equipment modeling, and the energy supply side equipment modeling includes: internal combustion generator, battery, waste heat recovery device, gas boiler and absorption chiller modeling on the energy supply side.

[0058] Among them, the modeling of the internal combustion generator, battery, waste heat recovery device, gas boiler and absorption chiller on the energy supply side uses the existing model, and the modeling of the user-side equipment includes power adjustable load modeling, time variable load modeling and transferable load modeling. The modeling method of the present disclosure is as follows:

[0059] a) Power adjustable load

[0060] Power-adjustable loads refer to equipment whose output power can be controlled in stages, generally including air conditioners, water heaters, lighting, etc. When optimizing system operation, the gear position of such energy-consuming equipment can be adjusted to control the energy consumption of the equipment. Its output power is related to the gear setting:

[0061]

[0062] in, is the output power of energy-consuming device n at time t, is the rated power of the jth level of energy-consuming equipment n, is the maximum output power of energy-consuming device n.

[0063] b) Time variable load

[0064] Time-variable loads refer to energy-consuming equipment that can adjust the start time according to operating requirements, such as washing machines, dishwashers, etc. The characteristics of this type of load are that once turned on, it must run a complete working cycle without interruption. Since its output power is not adjustable, the constraints are mainly based on time-related variables.

[0065] P ti (t) = R ti S(t) (8)

[0066]

[0067] Among them, P ti (t) is the power of device m at time t, R ti is the rated power of equipment m; is the time when the energy-consuming device m starts to operate, T m is the operating time of the energy-consuming device m; S(t) is the start / stop state of the device m, when S(t)=1, the device is on, and when S(t)=0, the device is off.

[0068] c) Transferable load

[0069] Different from time-variable loads, transferable loads are time-variable and interruptible loads, mainly electric vehicles and other new energy vehicles. Due to their flexible adjustability, this type of load is the primary dispatch target for demand-side response. In a sense, it can be regarded as a form of energy storage without a discharge process.

[0070]

[0071] Among them, E EV (t) is the power of the electric vehicle at time t, For charging efficiency, is the battery capacity, is the rated power, M EV is the charging state, M EV =1 for charging; It is the lower limit of the power of electric vehicles.

[0072] In order to ensure the power of electric vehicles, the charging amount is set to reach the expected value in each control cycle, and the constraints are defined as shown in formula (12):

[0073]

[0074] Among them, T is the control period, M EV (t) is the charging state at time t, T EV It is the total charging time of the electric vehicle within the control cycle.

[0075] Step 4: Solve the scheduling plan using Q-Learning to obtain the optimal scheduling result of the integrated energy system.

[0076] Taking user satisfaction and system economy (minimum economic cost) as optimization goals, Q-learning is used to solve the scheduling plan. The Markov process is constructed as follows:

[0077] (1) State space

[0078] The agent needs to observe the current state of the environment to make decisions. The external environment refers to a set of variables that the agent cannot change but will interfere with the overall decision. The state space needs to accurately describe the characteristics of the external environment. The state space is defined as:

[0079] s(t)={λ EL (t),λ GAS (t),P PV (t),E EV (t-1),E SOC (t-1)} (13)

[0080] Among them, λ EL (t) is the electricity price of the power grid at time t, λ GAS (t) is the gas price of the power grid at time t, P PV (t) is the photovoltaic output at time t, E EV (t-1) and E SOC (t-1) are the electric vehicle power and battery power at the previous moment.

[0081] (2) Action Space

[0082] The action space is the set of decisions that the agent can make after observing the current environment. However, too many actions are not conducive to solving the problem. Therefore, the variables that can be calculated by the energy balance equation are reduced. The energy supply side selects the input of the generator set and the gas boiler and the charging and discharging state of the energy storage device. The energy consumption side includes the output power of the power-adjustable load, the switching state of the time-variable load and the transferable load, which is defined as the action space:

[0083]

[0084] (3) Reward Function

[0085] Reward is the reward value fed back by the environment after the agent takes an action. It is an important part of driving the agent to persist in or change its decision. When it receives a positive reward, the agent tends to learn the action, and when it receives a negative reward, it will abandon the action. In the process of continuously taking actions to obtain reward feedback, the agent gradually learns the action decision that tends to maximize the reward. Select system operating cost and user satisfaction as the reward function:

[0086] r(t)=C EL (t)+C GAS (t)+γ i (t)+Z SOC (t)+Z EV (t) (15)

[0087] Among them, C EL (t) and C GAS (t) is the cost of purchasing electricity and gas at time t, Z SOC (t) is the constraint penalty of the power storage device, Z EV (t) is the constraint penalty for electric vehicles.

[0088]

[0089]

[0090] In the formula, α SOC are the penalty coefficients for overcharging and overdischarging of the energy storage system, β SOC is the penalty coefficient for not meeting the expected amount of storage capacity at the end of the control period; α EV are the penalty coefficients for overcharging and overdischarging of electric vehicles, β EV It is the penalty coefficient for the electric vehicle charging amount not meeting the expectation at the end of the control cycle. Usually, such coefficients are set to an absolutely large value to avoid over-limit situations.

[0091] (4) State-Action-Value Function

[0092] The goal of the Markov decision process is to select a policy π so that the sum of the discounted rewards is Maximize, for the convenience of solving, define the state-action value function Q π (s,a) is the expected total reward value when starting from s and taking action a under strategy π, then the problem is transformed into solving the problem that makes Q π (s,a) is the largest π. It is defined by the Bellman equation:

[0093]

[0094] In the formula, a′ represents the actions that can be taken in state s.

[0095] Implementation process of q-learning

[0096] Using Q-Learning as the learning framework of the intelligent agent, according to the strategy exploration, the state is updated after each action is completed, and the actions taken in different states and all the Q values ​​obtained are recorded in a Q-table. The Q value is updated through the continuous interaction between the intelligent agent and the environment until it finally converges. The update method is as shown in formula (19):

[0097]

[0098] Among them, Q(s(t), a(t)) is the long-term return obtained by taking action a(t) in state s(t), r(t+1) is the reward for action a(t) in state s(t), is the maximum reward obtained by taking action a' in the current state s(t+1) in the Q-table, ζ is the refraction factor, the meaning of which is to strengthen the recent return and weaken the long-term return. Its convergence proof is that when When it gradually approaches Q(s(t), a(t)) and the difference approaches zero, Q is no longer updated and the training is completed.

[0099] The present disclosure forms an intelligent agent, takes the load forecast curve as a baseline, takes the future behavior pattern as an input, and obtains a scheduling plan based on the Markov process.

[0100] Example 2

[0101] In one embodiment of the present disclosure, a comprehensive energy system optimization scheduling system considering user satisfaction is provided, including:

[0102] A data acquisition module is used to acquire historical user load data of a set step length and pre-process it to obtain a user daily load curve;

[0103] An energy consumption mode selection module is used to cluster the user's daily load curve and find the optimal value according to the set evaluation index to obtain the user's typical energy consumption mode;

[0104] A satisfaction quantification module is used to quantify user satisfaction based on the day-ahead load forecast result and the Pearson coefficient in combination with the user's typical energy consumption pattern;

[0105] The model building and solving module is used to build an optimal scheduling model for user energy-consuming equipment, taking user satisfaction and minimum economic cost as optimization goals, using Q-learning to solve the optimal scheduling model, obtaining the day-ahead scheduling results, and executing the day-ahead scheduling plan.

[0106] Example 3

[0107] In one embodiment of the present disclosure, an electronic device is provided, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the method for optimizing and scheduling an integrated energy system taking into account user satisfaction.

[0108] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0110] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. A comprehensive energy system optimization scheduling method considering user satisfaction, characterized in that: include: Obtain historical user load data with a set step length, and preprocess it to obtain a user daily load curve; Clustering the user's daily load curves, and finding the optimal value according to the set evaluation index to obtain the user's typical energy consumption mode; According to the day-ahead load forecast result, the user satisfaction is quantified based on the Pearson coefficient and the typical energy consumption pattern of the user; Construct an optimal scheduling model for user energy-consuming equipment, take user satisfaction and minimum economic cost as optimization goals, use Q-learning to solve the optimal scheduling model, obtain the day-ahead scheduling results, and execute the day-ahead scheduling plan.

2. The method for optimizing and dispatching an integrated energy system considering user satisfaction as claimed in claim 1, characterized in that: The historical load data with a step length of 1 hour is obtained and divided into different user daily load curves on a daily basis.

3. The method for optimizing and dispatching an integrated energy system considering user satisfaction as claimed in claim 1, characterized in that: The k-means++ clustering algorithm is used to cluster the user's daily load curves, and the DBI parameter is used as an evaluation index to find the optimal K value and obtain the user's typical energy consumption pattern.

4. The method for optimizing and dispatching an integrated energy system considering user satisfaction as claimed in claim 1, characterized in that: The typical energy consumption pattern of the user in the future day is obtained by using the load forecast curve, and the user satisfaction is quantified based on the Pearson coefficient and the typical energy consumption pattern of the user, including: quantifying the user satisfaction parameter by calculating the similarity between the user's daily load curve after scheduling and the future typical energy consumption pattern: Among them, γ i ∈[-1,1] represents the similarity between the user's energy consumption behavior and the energy consumption curve after scheduling, γ i The larger the value, the higher the similarity, and the more it conforms to the user's daily energy usage habits, the higher the user satisfaction. is the energy consumption behavior of the user at time t for the dispatchable load i, is the average value of energy consumption behavior; is the dispatch result of adjustable load i at time t, is the scheduling average value.

5. The method for optimizing and dispatching a comprehensive energy system considering user satisfaction as claimed in claim 1, characterized in that: Constructing an optimal scheduling model for user energy-consuming equipment includes energy supply side equipment modeling and user side equipment modeling. The energy supply side equipment modeling includes: internal combustion generators, batteries, waste heat recovery devices, gas boilers and absorption chillers on the energy supply side.

6. A comprehensive energy system optimization scheduling method considering user satisfaction as claimed in claim 5, characterized in that: The user side equipment modeling includes power adjustable load modeling, time variable load modeling and transferable load modeling.

7. A method for optimizing and dispatching an integrated energy system taking into account user satisfaction as claimed in claim 6, characterized in that: Power-adjustable load refers to the output power of the equipment controlled by grading. Power-adjustable load energy-consuming equipment includes air conditioners, water heaters and lighting equipment. During operation optimization, the gear of the power-adjustable load energy-consuming equipment is adjusted to control the energy consumption of the equipment. Its output power is related to the gear setting.

8. The method for optimizing and dispatching an integrated energy system taking into account user satisfaction as claimed in claim 6, characterized in that: Energy-consuming equipment with time-variable loads refers to energy-consuming equipment that adjusts its start-up time according to operating requirements, including washing machines and dishwashers. The characteristic of time-variable loads is that once turned on, they must run a complete working cycle and cannot be interrupted. Since their output power is not adjustable, the constraints are mainly based on time-related variables.

9. An integrated energy system optimization scheduling system considering user satisfaction, characterized in that: include: A data acquisition module is used to acquire historical user load data of a set step length and pre-process it to obtain a user daily load curve; An energy consumption mode selection module is used to cluster the user's daily load curve and find the optimal value according to the set evaluation index to obtain the user's typical energy consumption mode; A satisfaction quantification module is used to quantify user satisfaction based on the day-ahead load forecast result and the Pearson coefficient in combination with the user's typical energy consumption pattern; The model building and solving module is used to build an optimal scheduling model for user energy-consuming equipment, taking user satisfaction and minimum economic cost as optimization goals, using Q-learning to solve the optimal scheduling model, obtaining the day-ahead scheduling results, and executing the day-ahead scheduling plan.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes a method for optimizing and scheduling an integrated energy system taking into account user satisfaction as described in any one of claims 1 to 8.

Images