CA3156352A1 - Artificially intelligent renewable energy planning using geographic information system (gis) data - Google Patents

Abstract

Novel systems and methodology employ geographic information system (GIS) databases as resources for automated planning phases of renewable energy projects, including finding an optimal location to establish a renewable power plant by considering all environmental parameters based on artificial intelligence, finding the best type of renewable energy type based on the location by considering all environmental parameters by using artificial intelligence and decision-making algorithms, sourcing the best equipment in terms of efficiency and price performance , calculating the amount of produced renewable power based on the location and type of energy and initial investment, providing a complete feasibility study for establishing a renewable power plant, calculating cryptocurrency mining profit by using produced power and its expenses and all requirements, and finding the best location to establish electric vehicle charging stations based on effective parameters such as:
distance to road, shopping mall, universities and etc.

Description

Artificially Intelligent Renewable Energy Planning Using Geographic Information System (GIS) Data FIELD OF THE INVENTION
The present invention relates generally to geographic information systems (GIS), and more particularly to a computer implemented planning tool that interfaces with one or more geographic information systems to access geographic and environmental data therefrom, and apply Artificial Intelligence (Al) methods thereto to make planning recommendations for renewable energy projects.
BACKGROUND OF THE INVENTION
In recent years, due to increased awareness, most individuals consider climate change as an emergency. As the result of public opinion impacts on the issue of climate change, many governments at federal, state and local levels implemented policies that address climate change.
One of the largest sources of greenhouse gas emissions from human activities is from burning fossil fuels for electricity. As a result, there is strong support for promoting renewable sources such as solar power and wind power. Nearly two-thirds of all new power generation capacity added in 2018 was from renewables and a third of global power capacity is now based on renewable energy.
In addition to climate change mitigation, renewable energy recourses can provide economic benefits and energy security if are implemented intelligently. There is an increased interest from private sector which their interests evolved from a strictly environmental concern into a "strategic concern driven by market forces". There are also many laws and energy policies to encourage public-private partnerships to leverage private capital and expertise to support the development of renewable energy projects.
There are massive flows of capital directed toward development of renewable generation assets and the energy sector is transforming very rapidly. One of the main challenges that individual, communities, corporations and developers face is selection of the best combination of technology types and sizes of the renewable assets to maximize the economic value and increase energy security.
Nowadays, consultation with an expert is necessary in order to identify suitable locations for establishing renewable energy power plants, and once an expert guided selection of a suitable location is made, then various other data is inputted to software applications such as RETScreen and COM FAR, which are useful in preparation of feasibility studies.
Applicant has realized that there exists a wealth of available data resources that can be exploited to massively simplify planning of renewable energy projects and ongoing management of the planned facilities once establish, using uniquely and inventively automated systems and techniques.

Date Recue/Date Received 2022-04-25 SUMMARY OF THE INVENTION
According to a first aspect of the invention, there is provided a computer-implemented method for at least partially automated planning of a renewable energy power plant project, said method comprising the following steps executed by one or more computer processors embodied in one or more computers operably connected to a communications network, said method comprising:
(a) storing in memory, for each of plurality of different power plant types, a different respective criteria-weighting scheme for use in automated evaluation and selection of an optimal geographic location for said renewable energy power plant project;
(b) collecting user input data from a user;
(c) based at least partially on said user input, identifying one or more planning constraints for said planning of said renewable energy power plant project;
(d) retrieving from one or more geographic and environmental databases, at least one of which is embodied in one or more geographic information systems, geographic information concerning a plurality of potential candidate geographic locations for said renewable energy power plant project, said retrieved geographic information including, for each candidate location, a respective dataset containing a plurality of performance values for a plurality of parameters;
(e) for at least one of said plurality of different power plant types, selecting the respective criteria-weighting scheme corresponding thereto, and applying said selected respective criteria-weighting scheme against the respective datasets of the candidate geographic locations in a computer-executed multi-criteria decision-making (MCDM) process in which at least a subset of said plurality of parameters are used as criteria of said MCDM process;
(f) based on results of said MCDM process, identifying the optimal geographic location for the renewable energy power generation plant from among said candidate geographic locations;
and (g) Communicating identification of said optimal geographic location to the user.
Preferably, said predetermined power plant types include any two or more of solar, wind, hydroelectric and biomass power plants.
In one instance, step (b) includes receiving user-identification of an intended power plant type from among different user-selectable power plant options presented to the user, each corresponding to a different one of said predetermined power plant types, and said at least one of said plurality of different power plant types in step (e) consists of said intended power plant type.
In an alternative instance:
step (e) comprises applying the respective criteria-weighting schemes of the plurality of different power plant types in said computer-executed MCDM process, and thereby identifying respective best candidate locations for said plurality of different power plant types;
step (f) comprises comparing evaluation results of those respective best candidate locations against one another, and selecting a best scoring one of said best candidate locations as the

2 Date Recue/Date Received 2022-04-25 optimal geographic location; and step (g) comprises also communicating, from among said plurality of different power plant types, identification of a recommended power plant type to which said best scoring one of the best candidate locations corresponds.
Preferably said computer-executed selection of the intended power plant type is based at least partly on said one or more other planning constraints, and said one or more other planning constraints comprise a budgetary constraint designated in said user input data.
Preferably the executed steps further include an equipment assessment step comprising:
Using the one or constraints, identifying equipment requirements for the power plant project;
and searching one or more equipment supplier databases, and identifying therefrom candidate equipment options fulfilling said equipment requirements.
Preferably the equipment assessment step further comprises:
Assessing said candidate equipment options against one another to identify optimal equipment options; and determining a total cost of the optimal equipment options.
According to a second aspect of the invention, there are provided one or non-transitory computer readable media having stored thereon executable statements and instructions for execution by one or more processors, said statements and instructions being configured to, when executed, perform a method according to the first aspect of the invention.
According to a third aspect of the invention, there is provided a system for at least partially automated planning of a renewable energy power plant project, said system comprising one or more computer processors embodied in one or more computers operably connected to a communications network by which said one or more computers are communicable with one or more geographical and environmental databases, at least one of which is embodied in one or more geographic information systems, and one or more non-transitory computer readable media according to the second embodiment of the invention, embodied in or connected to said one or more computers for execution of the statement and instructions on said one or more non-transitory computer readable media by said one or more processors of said one or more computers.
According to a fourth aspect of the invention, there is provided a computer-implemented method for finding optimal time periods for saving produced power in storage batteries, selling said produced power to a power network or consuming said power by using statistical data and a modified value iteration algorithm, said method comprising:
a. based on input data, retrieve identification of a type of renewable energy concerned and an associated capacity, power demand, produced power, and type and specifications of one or more storage batteries to be used for power storage;
b. retrieve statistical data from a database, and solve an optimal dispatch problem using a reinforcement learning approach and a dynamic programming algorithm; and c. in solving said optimal dispatch problem, using a value iteration algorithm to find an optimum answer by repeating possible answers that converges the problem to an optimum solution.

3 Date Recue/Date Received 2022-04-25 In one embodiment, the method further comprises further comprising issuing command signals to one or more control devices of a power plant to switch said control device, according to the optimal time periods, between:
a power storage state dispatching the produced power to the storage batteries;
a power consumption state dispatching the produced power to electrical loads;
and a power selling state dispatching the produced power to a power network for financial compensation.
In competitive power markets, selection of the time for selling energy is very significant. To have the highest revenue from produce electricity, the operating condition of the power plant can be optimized. In the case of an electricity power system, the total load on the system will generally be higher during the daytime and lower during the late evening, when most population is asleep.
An effective power management tool is disclosed to help users find the best way to consume or sell energy.
According to a fifth aspect of the invention, there are provided one or non-transitory computer readable media having stored thereon executable statements and instructions for execution by one or more processors, said statements and instructions being configured to, when executed, perform the method according to the fourth aspect of the invention.
According to a sixth aspect of the invention, there is provided a system for finding optimal time periods for saving produced power in storage batteries, selling said produced power to a power network or consuming said power, said system comprising one or more computer processors embodied in one or more computers, and one or more non-transitory computer readable media according to the fifth aspect of the invention, embodied in or connected to said one or more computers for execution of the statement and instructions on said one or more non-transitory computer readable media by said one or more processors of said one or more computers.
According to a seventh aspect of the invention, there is provided a computer-implemented method for finding an optimal geographic location for constructing an electric vehicle charging station, said method comprising the following steps executed by one or more computer processors embodied in one or more computers operably connected to a communications network:
(a) retrieving from one or more geographic and environmental databases, at least one of which is embodied in one or more geographic information systems, geographic information concerning a plurality of potential candidate geographic locations for said electric vehicle charging station, said retrieved geographic information including, for each candidate location, a respective dataset containing a plurality of performance values for a plurality of parameters;
(b) applying a criterion weighting scheme against the respective datasets of the candidate geographic locations in a computer-executed multi-criteria decision-making (MCDM) process in which at least a subset of said plurality of parameters are used as criteria of said MCDM
process;
(c) based on results of said MCDM process, identifying the optimal geographic location for the electric vehicle charging station from among said candidate geographic locations; and

4 Date Recue/Date Received 2022-04-25 (d) communicating identification of said optimal geographic location to a user.
According to an eighth aspect of the invention, there are provided one or non-transitory computer readable media having stored thereon executable statements and instructions for execution by one or more processors, said statements and instructions being configured to, when executed, perform a method according to the seventh aspect of the invention.
According to a ninth aspect of the invention, there is provided a system for finding an optimal geographic location for constructing an electric vehicle charging station, said system comprising one or more computer processors embodied in one or more computers, and one or more non-transitory computer readable media according to claim 15, embodied in or connected to said one or more computers for execution of the statement and instructions on said one or more non-transitory computer readable media by said one or more processors of said one or more computers.
According to a tenth aspect of the invention, there is provided a computer-implemented method for evaluating conversion of produced power to cryptocurrency and calculating associated costs of said conversion, said method comprising the following steps executed by one or more computer processors embodied in one or more computers operably connected to a communications network:
a. receiving user input on how much of the produced power should be converted to cryptocurrency;
b. calculating an amount of cryptocurrency that can be generated based on an updated price of the cryptocurrency received via said communications network;
c. identifying equipment requirements necessary to mine the cryptocurrency using produced power; and d. searching one or more equipment supplier databases for equipment fulfilling said equipment requirements;
e. tallying a cost of located equipment in the one or more equipment supplier databases that fulfill said equipment requirements.
According to an eleventh aspect of the invention, there are provided one or non-transitory computer readable media having stored thereon executable statements and instructions for execution by one or more processors, said statements and instructions being configured to, when executed, perform a method according to the tenth aspect of the invention.
According to a twelfth aspect of the invention, there is provided a system for evaluating conversion of produced power to cryptocurrency and calculating associated costs of said conversion, said system comprising one or more computer processors embodied in one or more computers, and one or more non-transitory computer readable media according to claim 18, embodied in or connected to said one or more computers for execution of the statement and instructions on said one or more non-transitory computer readable media by said one or more processors of said one or more computers.
Date Recue/Date Received 2022-04-25 Among the foregoing embodiments, and other embodiments disclosed in more detail herein further below, are several useful, novel systems, methods and machines for planning and establishing renewable energy power plants and electric vehicle charging stations, as well as strategic planning and management of power output from such renewable energy power plants.
Among these various embodiments, numerous advantages and benefits can be seen, including:
- a simple interface that allows a user to work easily for finding the best location and resources for establishing renewable energy power plant;
- efficient processes that can be run in a short time, such that the user attains final output quickly and easily;
- user cost savings resulting from a resource efficient solution that is affordable for all type of customers;
- financial loss prevention by avoiding establishment of a renewable power plant with no return, as the best and the most appropriate resources can be located based on machine learning with LI (Location Intelligence) and Data Mining;
- efficient use of existing online data resources (e.g. GIS database and NASA database) for computing all required parameter;
- distinction between different optimal time periods for saving produced renewable energy or selling to a power network, because the selling price to the network varies at different times;
- finding locations with renewable energy resources and frequently commuting traffic on those paths, denoting ideal locations for vehicle charging stations for electric and plug-in hybrid vehicles;
- digital map preparations of the calculated optimal locations using previous data and some data mining solutions, for display of the best locations for any type of renewable energy sources directly on the map;
BRIEF DESCRIPTION OF THE DRAWING FIGURES
The above and other features of this invention are described in the following Detailed Description and shown in the following drawings:
FIGS.1A-1C are flowcharts illustrating respective sequential stages of an artificially intelligent computer-implemented process for planning of a renewable energy power plant using a combination of geographic information system resources and user-inputted project constraints;
FIGS.2A-26 are flowcharts illustrating step 110 of FIG.1A in more detail, where a computer-implemented determination is made of a best power plant type for a user-specified location;
FIG.3 is a flowchart illustrating step 129 of FIG.1C in more detail, where a computer-implemented determination is made of the most appropriate equipment for the power plant project;
FIG.4 schematically illustrates contents of a geographic information system (GIS) database from which useful data is gathered for use in step 127 of FIG.1C, where a computer-implemented evaluation and identification of a best location and power plant type for the power plant project is made in instances where a user-desired location was not specified at step 106 of IFG.1A;

Date Recue/Date Received 2022-04-25 FIG.5 is a hierarchical flowchart of a computer-implemented multi-criteria decision making (MCDM) process used to evaluate and identify the best location for the power plant project in step 127 of FIG.1C;
FIG.6 is a flowchart illustrating an initial computer-implemented pre-evaluation of candidate power plant types for minimum performance requirements in a geographic search area from within which the best location is to be found step 127 of FIG.1C;
FIG.7 is a flowchart illustrating a subsequent computer-implementation of the MCDM process of FIG. 5, broken down into a separate sub-process performed for each candidate power plant type that was found to fulfill the minimum performance requirements in the pre-evaluation stage of FIG.6;
FIG.8 is a flowchart illustrating the solar energy MCDM sub-process of FIG.7;
FIG.9 is a hierarchical chart showing effective parameters used in the solar v MCDM sub-process of FIG. 8;
FIG.10 is a flowchart illustrating the wind v MCDM sub-process of FIG.7;
FIG.11 is a hierarchical chart showing effective parameters used in the wind energy MCDM sub-process of FIG. 10;
FIG.12 is a flowchart illustrating the hydroelectric energy MCDM sub-process of FIG.7;
FIG.13 is a hierarchical chart showing effective parameters used in the hydroelectric energy MCDM sub-process of FIG. 12;
FIG.14 is a flowchart illustrating the biomass energy MCDM sub-process of FIG.7;
FIG.15 is a hierarchical chart showing effective parameters used in the biomass energy MCDM
sub-process of FIG. 14.
FIG.16 is a flowchart illustrating step 124 of FIG.16 in more detail, where a computer-implemented evaluation is carried out regarding mining of cryptocurrency using produced power from the planned power plant project;
FIG.17 is a flowchart illustrating a computer-implemented power management tool for evaluating optimal time windows in which to save, consume and sell produced power;
FIG.18 is a flowchart of a novel computer-implemented MCDM process for identifying the best location for establishment of an electric/hybrid vehicle charging station, in a manner similar to the power plant MCDM sub-processes of FIGS.5-15;
FIG. 19 is a hierarchical chart showing effective parameters used in the charging station MCDM
process of FIG. 18.
FIG.20 is a flowchart illustrating presentation of final results of the computer implemented processes of the preceding figures to a user, which may include, or collectively form all or part of, a comprehensive feasibility study;
FIG.21 schematically illustrates computer-executed compilation of said feasibility study;
FIG.22 is a schematic block diagram of a computer system for implementing the processes illustrated in the preceding figures.
DETAILED DESCRIPTION OF THE INVENTION

Date Recue/Date Received 2022-04-25 The following description of exemplary embodiments of the invention is not intended to limit the scope of the invention to these exemplary embodiments, but rather to enable any person skilled in the art to make and use the invention.
FIGS.1A & 1B illustrate an initial data collection stage of a computer-implemented renewal energy power plant planning process of the present invention. Executable statements and instructions stored in one or more non-transitory computer readable media are executed by one or more computer processors to carry out the described process, of which said computer readable media and computer processors may be embodied in one or more computers, which are connected to a communications network by which those one or more computers can interface with one or more geographic information system databases. For brevity, these one or more computers may be referred to herein as simply a "machine". With reference to FIG. 22, the machine of the illustrated embodiment is embodied, at least primarily, by a server 1003 and one or more "internal"
databases hosted thereby or connected thereto, and in the illustrated example including an OLDB
database 1004 and an OLAP database 1005. Reference to these databases as "internal" is meant as indication that they are hosted, owned or operated by, or on behalf of, the same operating entity as the machine specifically for the dedicated purpose of supporting and enabling the described operability thereof.
These internal databases 1004, 1005 are distinguished from other "external databases" that are also referenced herein, and from which the machine retrieves necessary information to perform the various tasks disclosed herein, yet which typically will not have been dedicated or designed for the dedicated purpose of supporting and enabling operation of the machine.
Instead, these external databases are typically hosted, owned or operated by separate outside entities other than the operating entity of the machine, and are typically also used for one or more other non-dedicated purposes, whether on a limited access basis to only a selection of authorized parties, or on a wide scale publicly accessible basis. The illustrated example includes at least three external databases, including a Geographic Information System (GIS) database 1006, a separate NASA database 1007, and one or more equipment supplier databases 1008. Users 1000 interact with the server 1003 over the internet or other wide area network, for example via a web application 1001 by which a graphical user interface (GUI) is displayed to the users 1000 on local client devices (workstation, desktop, laptop or tablet computers; smart phones, etc.), whereby the machine, at the various illustrated and described steps of the data collection stage, can query a user for input and collect the user's responses via one or more inputs of the client device (mouse, touchscreen, touchpad, keyboard, voice command, etc.).
In step 100 of FIG.1A, the machine asks the user to identify themselves as one of a selectable number of predetermined "customer types", categorized for example as:
Residential, Industrial, Asset Developer and Governmental. Next, the user is queried at step 101 whether they wish to specify a maximum budget for the project. At decision node 102, if the user did not specify a maximum budget, then the process continues on to step 103, where the user must specify a capacity requirement of the power plant, i.e. a quantity of power production (Watts) the plant Date Recue/Date Received 2022-04-25 will need to able to produce, before proceeding to step 104. On the other hand, if the user specified a maximum budget at step 101, decision node 102 bypasses step 103, and goes directly to step 104. Here, the user is asked if they want to specify a desired location for establishing power plant. At resulting decision node 105, if the user knows the desired location, the user is prompted to specify LAT (Latitude) and LONG (Longitude) for the desired location in step 106, otherwise decision node 105 leads to step 107, where instead of a specific desired location, the user must specify a geographic search region, for example by marking of same on a digital map shown in the GUI, from within which an optimal location for the power plant is to be intelligently determined by the machine.
Next, at step 108, the user is asked whether they wish to specify a power plant type for the power plant project at hand, for example being presented with a quantity of predetermined and selectable power plant types to choose from, which may include any two or more of Photovoltaic Energy, Wind Energy, Hydroelectric Energy, Geothermal Energy, Biomass and Biogas Energy, Ocean Energy. At decision node 109/109A, if the user specified a desired location at step 106, but did not specify a power plant type at step 109, then the process continues on to step 110, where the machine will follow the decision-making logic shown in FIGS. 2A & 2B, described further below, in order to determine an optimal power plant type based on the budget and capacity constraints inputted at steps 101 and 103, before proceeding to step 111. On the other hand, if the user specified a power plant type at step 108, and/or specified a geographic search region at step 107 instead of a specific desired location at step 106, then decision node 109 leads directly to step 111. Here, the user is prompted to specify consumption usage type, where the user must specify whether they want to consume the produced power or want to sell it to the network.
Turning to FIG. 1B, which is continuation of the FIG. 1A flowchart, at step 112, the user is prompted for a breakdown between a quantity of power that they want to sell to the network (step 113) and a quantity of power that the power plant entity wants available for direct consumption (step 114). Next, at decision node 115, based on the customer type specified at step 100, the machine determines which further input data is required from the user. If user was self-categorized as a residential user, then at step 116, the user must specify power consumption and number of electrical appliances (based on number of appliances, the machine can calculate how much energy is needed for consumption). If user was self-categorized as an industrial user, then in step 117, the user must specify power consumption and number of electrical equipment. If user was self-categorized as an asset developer, then in step 119, the user must specify number of houses that will be made and power consumption. If user was a governmental user, in step 118, user must specify power production capacity (if capacity wasn't already specified in step 103) that it has been required.
From each of the alternatively executable steps 116-119, next is step 120, where the user is prompted to specify whether energy storage capability is required. At decision node 121, if the user did specify a need for energy storage, the user must then specify how much energy they want to store at step 122. On the other hand, if energy storage capability was not required, the Date Recue/Date Received 2022-04-25 process bypasses step 122 and goes directly to step 123. Here, the user is asked whether they wish to dedicate any power capacity of the power plant to the task of mining cryptocurrency. If yes, then at step 124, the machine will execute the cryptocurrency related steps shown in FIG.16, and described further below.
Steps 100-124 of FIGS. 1A-16 collectively embody the initial data collection stage, where the user-inputted data at each data collection step described above denote design constraints on the power plant project being planned. After receiving all this user-inputted data, the machine, at step 125, starts to search the one more geographic information system (GIS) databases for environmental, geographical, social, urban and geological parameters. In some embodiments, including the detailed embodiment set forth below with reference to the accompanying figures, multiple databases may be queried to collectively obtain sufficient parameter data, for example communicating with the NASA POWER Project database (see https://power.larc.nasa.gov/) for environmental parameters (e.g. solar irradiance data, and climate data such as wind data and air pressure data, as is relevant to planning of solar and wind power plants), and using a separate GIS
database for other parameters (spatial, land cover, geomorphology, economic, etc.). In this example, the NASA environmental database also includes GIS functionality, and so both databases are referred to herein as GIS databases, though there could be embodiments in which the environmental parameters are retrieved from a non-GIS database. The machine searches the GIS
databases for data associated with either the specific desired location identified at step 106, if specified, or the geographic search region identified at step 107.
Turning to FIG.1C, if a geographic search region was specified at step 107, then the process skips step 126 and jumps straight to step 127, where an intelligent search for an optimal power plant location is conducted, detailed explanation of which is given herein further below, with additional reference to FIGS.4-15.0n the other hand, if a specific desired location was specified at step 106, then the machine needs to obtain GIS parameter data for the particular Latitude and Longitude of that desired location, but the GIS database(s) may not contain parameter data points for that specific geographic coordinate. So, the machine, in step 126 of FIG.1C, uses a 2D interpolation method to accurately estimate the GIS parameter data of the specific desired location.
Here, the machine uses bilinear interpolation, because there are two variables (Latitude and Longitude). Bilinear interpolation is performed using linear interpolation first in one direction, and then again in the other direction. Although each step is linear in the sampled values and in the position, the interpolation as a whole is not linear but rather quadratic in the sample location. The machine needs to determine interpolated parameter data point values (for solar irradiance, temperature, wind, speed, air pressure, spatial, land cover, etc.) for coordinate point (x, y) using the database's available parameter data point values for coordinate points(211,0 0 -0_2/ ,21, Q22 where:
Q11 = (x1, y1) Q12 = (X1, Y2) Date Recue/Date Received 2022-04-25 Q21 = (X2, Y1) Q22 = (X2, Y2) Therefore, the machine computes the following equation:
X2 ¨ X X ¨ X1 f (x , Y 1) = ____________ f (QH) + ___ f (Q21), x2 - x1 x2 - x1 x2 - x x - x1 f (x, y2) - , f (Q12) + __ , f (Q22), x2 - .,,1 x2 - .,,1 Then, the machine computes the parameter data point value of given location:
Y2 + Y Y + Yt f (x, y) = f (x, yi) + f (x, Y2) Y + Yt Y2 + Yt Y2 + Y ( x2 - x x - x1 - ______________________________ f (QH) + , f (Q20) y¨ Yt U2 - x1 X2¨ -1 Y + Yt ( ________________ x2 + x f (Q12) + x - x1 + f (Q22)) Y2- Yt X2- x1 X2- x1 - (x2 + x1) (y2 + Y1)(1. (IQ 11) (x2 - x)(Y2 - y) + f (Q21)(x - xi)(y2 - y) + f (Q12)(x2 - x)(Y - Yi) + f (Q22)(x - xi)(Y - Y1)) = 1 [x2 -x x - x11[f (QH) f (Q12)1[Y2 -y 1 (x2 - x1)(Y2 - Y 1) f (Q21) f (Q22)] I-Y

Continuing with the scenario in which a specific desired location was specified, and having now attained a dataset composed of interpolated parameter data point values for the specific desired location, step 127 is bypassed. Next, at step 128, the machine calculates all needed equipment based on budget, efficiency and energy type, and connects to one or more supplier databases via a suitable WEB Service to find that needed equipment, as outlined in more detail below in relation to FIG.3. Finally, at step 129, the machine calculates key performance indicators (KPI) to compile into a feasibility study. After all such calculation, the machine, at step 130 saves all computed results and generated feasibility study reports, for immediate or later display, or electronic transmission, to the user, thus completing the overall process.
FIGS. 2A & 2B illustrate step 110 of FIG.1A in greater detail. In step 200 budget status will be determined: if budget was not specified and capacity was instead specified, the process proceeds to step 201 and retrieves the previously specified budget; otherwise, the process proceeds to step 202 to check if capacity was already specified, and if not, then collects user-specified budget at step 201 before continuing on to step 203, where the machine computes annual solar energy production. In step 204 if the budget is less than budget threshold for wind energy (because for a Date Recue/Date Received 2022-04-25 given amount of power capacity, it is known how much budget is needed based on data that stored in the local database(s) for wind energy), then the machine proceeds to compute hydro energy annual production in step 207 based on required power capacity. If the budget exceeds the wind energy threshold, then the machine computes wind energy annual production in step 205 based on required power capacity.
After that, in step 206,the machine checks if the budget is less than budget threshold for hydro energy (because for a given amount of power capacity, it is known how much budget is needed based on data stored in the local database(s) for hydro energy), or if the specified location is beyond a threshold distance from the nearest river. If yes, then the process proceeds to step 209 for computing biomass energy annual production; if no, then the process proceeds to step 207 for computing hydro energy annual production. After that in step 208, the machine checks if the budget is less than a budget threshold for biomass energy (because for a given amount of power capacity, it is known how much budget is needed based on data stored in the local database(s) for biomass energy), or if the location is beyond a distance threshold from the nearest city (because close proximity to a city is most suitable for biomass energy due to availability of municipal waste as biofuel). If yes, then the process proceeds to step 219, where the machine displays solar capacity and selects a photovoltaic power plant as the final plant type decision (based on the logic that establishing a wind farm, hydro power plant or biomass power plant usually costs more and requires a certain minimum cost, and this minimum cost may vary at different times). Otherwise, the process proceeds to step 209 for computing biomass energy annual production.
Next, in step 210 of FIG.26, the machine compares the capacity of solar and wind energy annual production, and if the wind capacity is less than solar capacity, the machine, in step 212, compares solar capacity with hydro capacity; otherwise the process proceeds to step 211 for comparing wind capacity and hydro capacity.
In step 211, the machine compares wind capacity with hydro capacity, and if solar capacity is greater than hydro capacity, then in step 218 the machine compares solar capacity with biomass capacity, and if solar capacity is greater than biomass capacity. then in step 219 the machine selects a photovoltaic solar power plant as the final plant type decision.
In step 211, if wind capacity is less than hydro capacity, then the process proceeds to step 214 for comparing hydro capacity and biomass capacity; otherwise the process proceeds to step 213 for comparing wind capacity and biomass capacity. If wind capacity is greater than biomass capacity, then in step 215, the machine selects wind energy as the final plant type decision; otherwise, the process proceeds to step 217, where the machine selects biomass energy type as the final plant type decision.
In step 212, if solar capacity is greater than hydro capacity, then the process jumps to step 218, where the machine compares solar capacity with biomass capacity, and if solar capacity is greater than biomass capacity, then in step 219 the machine selects a photovoltaic solar power plant is the final plant type decision; otherwise, the process proceeds to step 217, where biomass energy is selected as the final plant type decision.
In step 212, if solar capacity is less than hydro capacity, then the process proceeds to step 214 for comparing hydro capacity and biomass capacity, and if hydro capacity is greater than biomass Date Recue/Date Received 2022-04-25 capacity, then in step 216, the machine selects hydroelectricity as the final plant type decision;
otherwise, in step 217, the machine selects biomass energy as the final plant type decision.
The algorithm of main idea of choosing the best source is shown in below. Note that, as mentioned above, there are many limitations for establishing solar, wind, hydro and biomass power plant. Constructing a wind farm requires a certain minimum cost x1 and it is not possible to establish a wind farm for a capacity lower than a certain number y2. And also, it is not possible to establish a solar power plant for a capacity greater than a certain number yi. Constructing a hydro power plant requires a certain minimum cost x2and it is not possible to establish a hydro power plant for a capacity lower than a certain number y3. Constructing a biomass power plant requires a certain minimum cost x3and it is not possible to establish a biomass power plant for a capacity lower than a certain number y4.
INITIALIZE;
IF Budget is given AND Capacity is given THEN
IF Budget <x1 or Capacity <Y2 THEN
Wind will be removed from the list ELSE
COMPUTE annual wind energy production END IF
IF Budget <x2 or Capacity <y3 THEN
Hydro will be removed from the list ELSE
COMPUTE annual hydro energy production END IF
IF Budget <x3 or Capacity <y4 THEN
Biomass will be removed from the list ELSE
COMPUTE annual biomass energy production END IF
IF Capacity < yi THEN
COMPUTE annual solar energy production END IF

Date Recue/Date Received 2022-04-25 END IF
IF Budget is given AND Capacity is not given;
IF Budget <x1 THEN
Wind will be removed from the list ELSE
COMPUTE annual wind energy production END IF
IF Budget <x2 THEN
Hydro will be removed from the list ELSE
COMPUTE annual hydro energy production END IF
IF Budget <x3 THEN
Biomass will be removed from the list ELSE
COMPUTE annual biomass energy production END IF
COMPUTE annual solar energy production END IF
IF Budget is not given AND Capacity is given;
IF Capacity > yi THEN
Solar will be removed from the list ELSE
COMPUTE annual solar energy production END IF
IF Capacity < y2 THEN

Date Recue/Date Received 2022-04-25 Wind will be removed from the list ELSE
COMPUTE annual wind energy production END IF
IF Capacity < y3 THEN
Hydro will be removed from the list ELSE
COMPUTE annual hydro energy production END IF
IF Capacity < h THEN
Biomass will be removed from the list ELSE
COMPUTE annual Biomass energy production END IF
END IF
FIG.3 is a more detailed illustration of step 129 from FIG.1C, where the machine searches and chooses optimal equipment for the renewable power plant being planned. For establishing a renewable power plant and calculating its capacity, daily and yearly power production, system efficiency, initial cost, maintenance cost and preparing feasibility study reports, it is useful to find all the required equipment in detail, where after this equipment data can be presented to the user and/or used for various computations. Finding appropriate equipment is a complex problem and can be done by searching in one or more equipment supplier databases and computing its efficiency and final price for establishing a power plant. Obviously, this process can't be done by individuals, and needs a calculation loop for doing query and calculating required data. Referring back to steps 101-103 of FIG.1A, there are two different perspectives from which the equipment problem can be approached: from a specified budget perspective, or from a capacity requirement perspective. In the scenario where a budget has been specified at step 101, the machine computes and allocates a budget share of the overall specified budget to each piece of required equipment for the particular type of power plant concerned (as previously specified at step 108, or determined at step 110 or 127). The necessary equipment breakdown criteria for each predetermined power plant type is known, and stored in a manner accessible to the machine, for example in a reference database hosted thereby or connected therewith, to enables these searches on the equipment supplier database(s) based on these criteria. This equipment search process is accordingly based on each renewable power plant type cost breakdown and calculates an estimate of how much money should be spent for each equipment need. In the second scenario, where power plant capacity has been specified at step 103, the machine computes the Date Recue/Date Received 2022-04-25 required quantity and quality (i.e. production capacity) of each piece of required equipment to achieve the specified capacity requirement of the power plant, then searches out the price of each piece of required equipment for the next computation. All of above computation will be done by searching in supplier's database for an optimal solution.
So, with reference to FIG. 3, the machine first checks at decision node 300 whether budget or capacity was specified earlier on at step 101 or 103. If budget was specified, the process continues to step 301, or if capacity requirement was specified, the process bypasses step 301 and proceeds straight to step section 302. In step 301, an attainable capacity achievable within the specified budget is calculated, and then the machine calculates an estimated budget share price of each equipment according to the stored cost breakdown criteria of the power plant type concerned.
These estimates are used to subsequently guide an assessment of accurate true costs by searching in equipment supplier database(s) in section 303.
The calculations at step 301 can be represented by the following formulas:
P=
= [P:11 Pni A = BP
Bpi]
A= [ :
Bpn I
Or we can consider:
tat = Bpi , a2 = Bp2 Where: pn is the percentage budget share of equipment n, 13 is the specified budget and an is the estimated price of equipment n.
In step 302, the machine computes required equipment based on power capacity that the machine will compute based on the budget to achieve the ability of producing demand power that has been specified by the user. The calculation of this section can be represented by the following formulas:
Pn = Mn Where: Pn is nominal power capacity (subscript n in Pn represents nominal power), M is power production capacity of main equipment to produce power such as: solar panel, turbine, etc. and n is quantity of main equipment.
In section 303, machine searches on the equipment supplier database(s) to find equipment based on and the results of step 302. For the scenario in which budget was specified, searching in database is based on the estimated budget share price of the required equipment, determined at earlier step 301, and so the machine searches for equipment of the required type whose supplier-listed cost is less than the estimated budget share price. In the scenario where capacity was Date Recue/Date Received 2022-04-25 specified instead of budget, searching in database is based on required equipment to achieve the specified capacity requirement. In section 304, having identified candidate equipment options in search step 303, the machine evaluates each candidate equipment option based on a combination and price and efficiency, and compares the different candidate equipment options against one another to determine an optimal candidate equipment option with the best price/ efficiency result.
One possible algorithm for executing step 304 is given below, where if the budget, but not the capacity requirement, was specified, then the attainable capacity (that can be produced based on the specified budget and the power plant type concerned) is first calculated.
Then based on the specified or calculated attainable capacity, the machine searches the reference database to find all required equipment types for power plan type concerned, then searches on equipment supplier database(s) (via implemented web service(s)) and finds all candidate equipment options for each required equipment type, and then calculates price/efficiency for every candidate equipment option. Since the capacity of every candidate equipment option is known, the machine will find the optimal candidate equipment option that has the best price/efficiency and the best capacity capability relative to the user's required capacity, and selects this as the recommended equipment option for the given equipment type.
INITIALIZE;
IF Budget is specified THEN
Calculate the capacity based on energy type and budget END IF
FOR i in n /*finding all required equipment based on energy type and capacity*/
FOR j in k /*finding an equipment in all supplier's database*/
CREATE a list of all equipment for ei,j CALCULATE price/ efficiency of each equipment ei,j END LOOP
END LOOP
FOR i in n FOR j ink COMPARE price/ efficiency of each equipment COMPARE Capacity of each equipment IF price/ efficiency eii > ei+1,1 AND Capacity eii >
RETURN ei,j ELSE IF price/ efficiency e1 > ei+1,1 AND Capacity e1 <

Date Recue/Date Received 2022-04-25 RETURN eij ELSE
RETURN ei+1,j END IF
END LOOP
END LOOP
And finally in section 305, and after full searching of the equipment supplier database(s), the machine prepares a list of the recommended equipment option for each required equipment type (for example, using the above algorithm). Once identified, these recommended equipment options may be used in other future machine executed computations, for example in generation of one or more various reports, and are shown to the user, and/or stored in computer-readable memory of the machine for future retrieval and display. Examples of the required equipment types for the different power plant types may include, for instance, solar panels and inverters for photovoltaic solar power plants; blades, gearboxes and generators for wind turbine power plants;
hydraulic turbines and hydroelectric generators for hydroelectric power plants; biomass furnaces, boilers and steam turbines for biomass power plants. Note that, for establishment of a power plant under a certain circumstance, required main equipment may be the same as previously calculated, so the stored data and their technical and economic results can be advantageous.
FIGS.4-15 elaborate on the details of step 127 for determining the best location for establishing the power plant when a specifically desired location was not specified by the user. The novel methodology employed for these purposes denotes a significantly valuable aspect of the present invention. In the following detailed embodiment of this methodology, all effective parameters for planning a renewable energy power plant are considered, in an artificially intelligent evaluation and decision-making process that cannot be implemented as a mental or pen-and-paper exercise, at least in part owing to its use of such an extensive breadth of parameters. There are a vast variety of significant parameters falling into such categories as:
Spatial considerations, Land Cover classification, Geomorphology and Economic considerations, which individually and collectively have considerable impact on power production and other aspects of a renewable energy power plant. In the following methodology, these parameters and their effects on the best location for establishing a renewal energy power plant are considered.
Renewable energy sources are inextricably tied to their location and the geographical parameters associated therewith, and so producing electricity is directly connected with geographical location.
The process of finding the best locations for the setting up of renewable power plants requires the gathering of data with regards to relevant factors of influence. The use of Geographical Information System (GIS) has gained a lot of popularity as a site suitability analysis tool involving the assimilation of spatially referenced data in a problem-solving environment.
In this problem, a great deal of factors plays a significant role in the assessment of suitable locations, and as mentioned above, can be categorized into such categories as spatial Date Recue/Date Received 2022-04-25 considerations, land cover classification, geomorphology, economic considerations, etc. By employing one or more Geographical Information System (GIS) databases as a data resource, and applying a Multi-Criteria Decision-Making (MCDM) based approach for analyzing said data, an effective computer-implemented method for selecting optimal locations for renewable power plants is derived. The MCDM analytical approach provides a substantial means to handle the shortages of GIS in analyzing cases involving complex criteria and objectives.
The GIS serves as a valuable tool in the MCDM problem addressed herein, in which geo-referenced information plays a crucial role. The employed GIS approach has the capabilities of data storage, data management, calculations, analysis, and visualization of the raw georeferenced data in a meaningful manner.
The MCDM approach is particularly well suited for solutions to complex problems where multiple factors affect a single goal. The MCDM approach provides a suitable option through the evaluation and comparison of the characteristic properties of the alternatives. Thus, by combining GIS
resources with an MCDM analytical approach, a unique and cohesive framework is possible that can handle the complex spatial planning problem addressed by the present invention.
GIS can be generally defined as tools for consulting, analyzing and editing data, maps and spatial information in general. GIS are systems that embody geographic information databases in association with a digital map, from which the geographic coordinates of each point within the mapped geographical area can be obtained. This means that it is possible to search in both directions, obtaining information on the map, or performing the search directly from the database. One of the most significant features of GIS is it can represent an area by using many layers, of which each layer represents a different factor. In the presently faced problem of selecting the best location for renewable power plant, there are plenty of relevant and parameters, and as a result, each parameter can be represented by a layer (FIG.4). These parameters may have different effects on different types of power plants, and so the weight of these parameters should be varied among the different types of renewable energy power plants being considered.
MCDM is a computer-implemented procedure that consists in finding the best alternative among a set of feasible alternatives. The main hierarchical flow chart of Multiple-criteria decision-making (MCDM) is given in the FIG.5. In the context of the present invention, the alternatives are different candidate locations for the power plant project being planned, and from among which the best candidate location is to be identified.
An MCDM problem with m alternatives and n criteria can be expressed in matrix format as:
C= [C1 ... Ci,1 Z = [zn === Z1 n Zni: 1 :==== Zni: n W = [1411 = = = Wn 1 Date Recue/Date Received 2022-04-25 M= AxZ
Cn A1 z11 =
Ami[Zmi = = = Znini W1 = = = Wn Where Al; A2; ...; Ant are feasible alternatives; C1; C2; ...; Cn are evaluation criteria; Zi1 is the performance value of alternative Ai under criterion Ci; and wi is the weight of criterion C1. The decision matrix can be represented by the following table:
Objective Criterion 1 (C1) Criterion 2 (C2) Criterion n (Ca) Alternative 1 (A1) Z11 Z12 = = = Z1n Alternative 2 (A2) Z21 Z22 = = = Z2n . . . . . . . . .
Alternative m (Am) Zm1 Zn12 . . . Zmn Weight (W1) W1 W2 = = = Wn To properly determine the weight of each criterion or factor involved in the final outcome of the resulting layers, the Analytic Hierarchy Process AHP method, proposed by Saaty, is used within the MCDM. It is a pair-wise comparison procedure of the criteria that is based on a square matrix in which the number of rows and columns is defined by the number of criteria to weigh. This method bases its operation in the calculation of the distances to the ideal point and the anti-ideal point. This methodology was chosen because it does not require an assessment by a knowledgeable expert for each of the alternatives; they can be evaluated directly from the database provided by the GIS assessment of each criterion for each alternative. Basically, AHP has three underlying concepts: structuring the complex decision problem as a hierarchy of goal, criteria and alternatives, pair-wise comparison of elements at each level of the hierarchy with respect to each criterion on the preceding level, and finally vertically synthesizing the judgements over the different levels of the hierarchy.
Here, it is assumed that there are n different and independent alternatives Ai (i = 1, n) and that they have the weights wj (j = 1, n), respectively. Also, it is assumed that the quantified judgements on pairs of alternatives (Ai, Aj) are represented in an nxn matrix as follows:
A1 ... An A1 an === aln A = [aid =
nxn an1 = = = ann Date Recue/Date Received 2022-04-25 Where: alternatives are Ai (i = 1, n), while the weight ratio of pairs is given in each element ai of matrix A, which can be expressed by the following expression:
wi aij = ¨
Wj Where: wi and wi are local weights of elements i and j in relation to another element. The values assigned to ai according to the Saaty scale are usually in the interval of 1-9 or their reciprocals.
The following table presents Saaty's scale of preferences in the pair-wise comparison process.
Definition Intensity of Importance Ai is equally important to Ai 1 Ai is slightly more important than Ai 3 Ai is strongly more important than Ai 5 Ai is very strongly more important than Ai 7 Ai is extremely more important than Ai 9 Intermediate values 2, 4, 6, 8 The process consists of decomposing a complex problem into a hierarchy, keeping the goal at the highest position of the hierarchy, criteria and sub- criteria at intermediate levels and sub-levels of the hierarchy, and decision alternatives at the lowest level of the hierarchy.
A pairwise comparison of the elements at a given hierarchy against the elements in the next higher level is conducted in order to evaluate their relative preference with respect to each other. A rating scale of 1-9 is used to grade the preference between two elements. In this scale the lowest value 1 implies less importance and the highest value 9 implies strong importance. The other values (2-8) imply intensities of importance graded between 1 and 9. The scale is used to attribute weight coefficients for the quantifiable and no quantifiable elements which are obtained in the form of a weight coefficients vector, reflecting the intensity of importance of each option relative to the goal stated at the highest position of the hierarchy. On this basis, pairwise comparison matrices are constructed considering the following principles: "a given element of the matrix is equivalent to itself, i.e., equal to 1 and the value of element a with respect to element b is the reciprocal of the value of element b with respect to element a".
The following equation gives the values of the normalized entries (aii) of matrix M:
ail = ,f or i = 1, 2, ..., n E7-1 aii and the following equation is used to compute the local weights of criteria Date Recue/Date Received 2022-04-25 ril=1 w= = f or i = 1, 2, ... , n n Before using Multi-Criteria Decision-Making (MCDM) to find the optimal location for establishing renewable energy power plants, for best results, the points on the GIS map selected as candidate locations for the power plant should meet a set of minimum requirements for establishing a power plant. By this, it is meant that it is not economical to set up power plants in geographic locations that do not meet the minimum requirements, and there is no need to include such unsuitable locations in the MCDM analysis. These unsuitable locations are thus pre-emptively excluded from the alternatives list. To pre-emptively filter out such unsuitable locations from the pool of potential candidate locations, it is necessary to define a minimum number of super effective parameters and check whether predefined thresholds for those super effective parameters are met for each of the potential alternatives.
These super effective parameters for each potential candidate location are checked and controlled by checking the relevant GIS layers, and if they do not meet the minimum requirements, the GIS data points for that potential candidate location stored in a new exclusion GIS layer as unusable points and are not checked as an alternative in the MCDM
process, having been pre-emptively excluded therefrom.
FIG.6 illustrates this pre-emptive filtering out of unsuitable locations from the alternatives list so that only suitable candidate locations populate the final set of alternatives for the MCDM analysis.
At step 400, the machine identifies a geographic search region, for example based on user selection thereof on a digital map thereof in the GUI, or retrieval from memory of a user-selected search region already specified at step 107. In step 401, the machine retrieves defined minimum requirement values of the super effective parameters for the predetermined power plant types, which as mentioned previously may include some or all of the following non-exhaustive examples:
= Solar Energy = Wind Energy = Hydropower Energy = Biomass Energy for which the super effective parameters are, respectively:
= Solar Irradiance (GHI) = Average Wind Velocity = Rivers average flow rate = Distance to Urban Area The minimum required values of above parameters are predefined values stored in memory for retrieval by the machine, and exemplary examples of which are given in the following table. In step 402, based on the machine's identification of the super effective parameters (or restriction factors), the machine prepares a related GIS layer for each super effective parameter by using the Date Recue/Date Received 2022-04-25 geographic search area defined in step 401. Non-limiting examples of possible minimum requirement values for the different power plant types are given in the following table:
Solar Wind Hydroelectric Biomass Solar Irradiance (GHI) >4.5 kWh/m2/day Average Wind Velocity > 5 m/s Rivers Average Flow Rate > 2.07 m3/s Distance to Urban Area <10 km At step 403, the machine is now ready to start checking the minimum requirement for each energy type, for example shown as four separate steps 404, 405, 406 and 407 for four different power plant types: solar, wind, hydroelectric and biomass. In step 404, machine uses the GIS layer of solar Global Horizontal Irradiance GHI (kWh/m2/day) in raster mode, then machine reads GHI data and compares it with the associated threshold of that restriction factor, and if any point does not meet the threshold, machine add this raster point to a new exclusion GIS
layer. The following algorithm shows the method of this computation:
INITIALIZE;
FOR i in all raster points IF raster Gilli <4.5 kWh/m2/day:
ADD this raster point to exclusion layer END IF
END LOOP
In step 405, in similar fashion to step 404, the machine prepares a GIS layer of Average Wind Velocity (m/s) in raster mode, then the machine reads the Average Wind Velocity data and compares it with the associated threshold of that restriction factor, and if any point does not meet the threshold, the machine adds this raster point to another new exclusion GIS
layer. The following algorithm shows the method of this computation:
INITIALIZE;
FOR i in all raster points Date Recue/Date Received 2022-04-25 IF raster Average Wind Velocity i <5 m/s:
ADD this raster point to exclusion layer END IF
END LOOP
In step 406, in similar fashion to step 405, the machine prepares a GIS layer of Rivers Average Flow Rate (m3/s) in raster mode, then the machine reads the Rivers Average Flow Rate data and compares it with the associated threshold of that restriction factor and if any point does not meet the restriction factor, machine add this raster point to another new exclusion GIS layer. The following algorithm shows the method of this computation:
INITIALIZE;
FOR i in all raster points IF raster Rivers Average Flow Rater <2.07 m3/s:
ADD this raster point to exclusion layer END IF
END LOOP
And finally in step 407, in similar fashion to steps 404-406, the machine prepares a GIS layer of Distance to Urban Area (km) in raster mode, then the machine reads the Distance to Urban Area data and compares it with the associated threshold of that restriction factor, and if any point does not meet the threshold, the machine adds this raster point to another new exclusion GIS layer.
The following algorithm shows the method of this computation:
INITIALIZE;
FOR i in all raster points IF raster Distance to Urban Area > 10 km:
ADD this raster point to exclusion layer END IF
END LOOP
In step 408, the machine gathers and combines all of the forgoing exclusion layers into a new Combined Exclusion Layer in a raster map. The points specified in this combined exclusion layer are not suitable for use in the MCDM analysis, and are thus prohibited points specifically excluded therefrom. At step 409, pre-emptive exclusion of unsuitable locations for the power plant is complete, whereby the scope of candidate locations within the geographic search region has been effectively narrowed for more efficient processing in the MCDM analysis that follows in FIG.7.

Date Recue/Date Received 2022-04-25 FIG.7 presents the MCDM analysis, broken down into four sub-processes each dedicated to a respective one of the predetermined power plant types, and which are listed below:
= Solar Energy Multi-Criteria Decision-Making sub process in step 410 = Wind Energy Multi-Criteria Decision-Making sub process in step 411 = Hydropower Energy Multi-Criteria Decision-Making sub process in step 412 = Biomass Energy Multi-Criteria Decision-Making sub process in step 413 The four decision-making sub-processes are performed separately using the relevant GIS layers and effective parameters for the given power plant type, and the best respective location to establish a solar power plant, wind power plant, hydroelectric power plant and biomass power plant is determined separately, and the corresponding score will be calculated for each for evaluation of the different location/plant-type combinations against one another. In step 414, the overall results are reviewed and merged, and in step 415, the best location/plant-type in the geographic search area will be selected and displayed to the user, and/or stored in memory for later retrieval and display. Steps 414 and 415 will be explained in more detail further below, after first elaborating on the details of the plant-specific MCDM sub processes 410, 411, 412 and 413.
Firstly, the solar energy MCDM sub process is shown in FIG.8, wherein in step 416, the alternatives, which are the raster pixels in the GIS layer of solar irradiance (GHI), are determined and prepared in raster mode for the computations. In step 417, criteria and sub-criteria of effective parameters for establishing photovoltaic power plant, as shown in FIG.9, are identified by the machine, based on stored instructions in memory, for use in subsequent steps and calculations.
In this detailed but non-limiting example, there are five main criteria and nineteen sub-criteria for the solar energy power plant type. In step 418, the weights of the criteria and sub-criteria related to the solar energy criteria and sub-criteria identified in step 417, having been predetermined, and calculated in accordance with the Saaty method mentioned earlier, either by, or with the aid or guidance of a knowledgeable expert, and then stored in computer-readable memory of the machine as normalized Saaty pairwise comparison matrices, are now retrieved from memory for use of this predetermined solar-specific weighting scheme in the solar MCDM
sub process. The sub-criteria comparison with calculated local weight for each type of parameters are shown below.
Spatial sub-criteria pairwise comparison matrix with local weights Sub-Criteria Road Railway Power Grid Settlements Weight Road an a12 a13 a14 wsi Railway an a22 a23 a24 14152 Power Grid a31 a32 a33 a34 14/53 Settlements a41 a42 a43 a44 14/54 Date Recue/Date Received 2022-04-25 Land cover sub-criteria pairwise comparison matrix with local weights Sub- Barren Grass- Bush- Emerging Farm Pastures Forest Wetland Weight Criteria Lands land land Forests Land Barren vvi,1 Lands an a12 a13 a14 als a16 a17 als Grassland an a22 a23 a24 azs a26 a27 a28 WL2 Bushland a31 a32 a33 a34 a35 a36 a37 a38 WL

Pastures a41 a42 a43 a44 a45 a46 a47 a48 WL

Emerging Forests a51 a52 a53 a54 ass a56 a57 a58 WLs Farm Land a61 a62 a63 a64 a65 a66 a67 a68 WL

Forest a71 a72 a73 a74 a75 a76 a77 am WL

Wetland a81 a82 a83 a84 a85 a86 a87 a88 WL8 Geomorphology sub-criteria pairwise comparison matrix with local weights Sub-Criteria Slope Orientation Elevation Weight Slope an a12 a13 WC' Orientation an a22 a23 WG 2 Elevation a31 a32 a33 WG 3 Economic sub-criteria pairwise comparison matrix with local weights Power Sub-Criteria Population Tourist Night Unemployment Weight Consumption Population an a12 a13 a14 WEI_ Tourist Night an a22 a23 a24 WE 2 Power Consumption a31 a32 a33 a34 WE 3 Unemployment a41 a42 a43 a44 WE 4 Date Recue/Date Received 2022-04-25 The predetermined expert-derived weights may be periodically updated to account for changing circumstances. In the weights of the sub-criteria factors, the alphabetic subscript in the weight w is shorthand for the the sub-criteria name. So, in the term wsi the "S"
represents "Spatial" and the "1" represents the first factor in the matrix. Likewise, "L" in wLi represents "Land Cover", "G"
in wG, represents "Geomorphology", "E" in wEi represents "Economic".
Main criteria pairwise comparison matrix with local weights Main-Criteria GHI Spatial Land Cover Geomorphology Economic Weight GHI a11 a12 a13 a14 als Spatial a21 a22 a23 a24 a25 1412 Land Cover a31 a32 a33 a34 a35 Geomorphology a41 a42 a43 a44 a45 14/4 Economic a41 a52 a53 a54 ass ws It should be noted that in this case that there is a problem with a hierarchical structure including some criteria and sub-criteria (due to the range and variety of effective parameters, it is better to classify them hierarchically), and so the machine calculates the average weights of criteria and sub-criteria first, as per the formula given above for iv1, and saves these as local weights. Later on, in a ranking function detailed herein further below, global weighting of the sub-criteria will be applied by multiplying the averaged local weights of the sub-criteria by the average weights of their upper-level criterion.
Referring again to Figure 8, in step 419, the machine uses the GIS layer for completing a performance matrix of each alternative. Every pixel in the raster map is an alternative (a candidate location for a solar power plant) and its performance value for a given criteria must be collected from GIS by using the related layer. The following equation presents performance value of each alternative for related criteria:
Z11 === Z1n Z=
Zini ... Zinn Objective Criterion 1 (C1) Criterion 2 (C2) Criterion n (Ca) Alternative 1 (A1) Z11 Z12 = = = Z1n Alternative 2 (A2) Z21 Z22 = = = Z2n " = = =
Alternative m (Am) Zm1 Zin2 Zinn Weight (wi) W1 W2 = = = Wn Date Recue/Date Received 2022-04-25 In Step 420, the machine computes the normalized weight of the performance matrix (which may alternatively be referred to as a "decision matrix"). The machine first applies vector normalization to normalize the performance matrix values:
zii r.i = _____________ for i = 1, 2, ... , n and j = 1, 2, ... , m JL=t 1 ,2 ij Where rii is normalized value and zii is the performance value of the alternative i for the criterion j.
Though not necessarily calculated by the machine at this stage, but in supportive illustration of the calculation of ranking score functions below, a weighted normalized decision matrix can be computed by multiplying the weight of each decision criterion (w1) by each already normalized performance value of the decision matrix for that criterion, as presented in the following equation:
V. = w1 x r. for i = 1, 2, ... , n and j = 1, 2, ... , m ti ==== Vln V=
Vin So, in step 421, the machine calculates a ranking score for each alternative (candidate location) using a predetermined solar-specific ranking function. The calculated ranking scores of the candidate locations for a solar power plant are then compared to identify the best candidate location for a solar power plant. The equation of the solar-specific ranking function in this specific example is given below:
F = W1R1 +
W2 (WsiR2 Ws2R3 Ws3R4 W54R5) W3 (WL1R6 WL2R7 3R8 WL4R9 sRio WL6R11 7R12 WL8R13) W4 (WG1R14 WG2R15 W G 3R16) W (VI E 1R17 + WE 2R18 + WE 3R19 + WE 4R20) Where w1, 14/2, w3, w4 and ws are the local weights of main criteria:
: weight of GHI criterion w2 : weight of Spatial criterion w3 : weight of Land Cover criterion w4 : weight of Geomorphology criterion ws : weight of Economic criterion 14/52, w53 and w54 are the local weights of Spatial sub-criteria:

Date Recue/Date Received 2022-04-25 wsi : weight of Road criterion ws2 : weight of Railway criterion ws3 : weight of Power Grid criterion ws4 : weight of Settlements criterion WL4, WLs, WL6, WL7 and wi,8 are the local weights of Land Cover sub-criteria:
wLi : weight of Barren Lands criterion : weight of Grassland criterion : weight of Bushland criterion wL4 : weight of Pastures criterion wLs : weight of Emerging Forests criterion : weight of Farm Land criterion wL7 : weight of Forest criterion : weight of Wetland criterion wG2 and wG3 are the local weights of Geomorphology sub-criteria:
wG, : weight of Slope criterion wG2 : weight of Orientation criterion wG3 : weight of Elevation criterion wE2, wE3 and wE4 are the local weights of Economic sub-criteria:
wEi : weight of Population criterion wE2 : weight of Tourist Night criterion wE3 : weight of Power Consumption criterion wE4 : weight of Unemployment criterion And also, term "Ri" represents normalized performance value of each alternative:
: performance value of GHI raster R2 : performance value of Road raster R3 : performance value of Railway raster R4: performance value of Power Grid raster Rs : performance value of Settlements raster R6 : performance value of Barren Lands raster R7 : performance value of Grassland raster R8 : performance value of Bushland raster R9 : performance value of Pastures raster Rlo : performance value of Emerging Forests raster R11 : performance value of Farm Land raster R12 : performance value of Forest raster R13 : performance value of Wetland raster Date Recue/Date Received 2022-04-25 R14 : performance value of Slope raster R15 : performance value of Orientation raster R16 : performance value of Elevation raster R17 : performance value of Population raster R18 : performance value of Tourist Night raster R19 : performance value of Power Consumption raster R20 : performance value of Unemployment raster Using this solar-specific ranking function, the machine calculates a respective solar-specific ranking score for each of the alternatives by using the relevant GIS layers in raster mode.
Accordingly, each pixel of the specific geographic search region in the GIS
map, except for those in the combined exclusion layer, has its own solar-specific ranking score. In step 422, the computed ranking score values of the pixels are compared, and at final step 423, the pixel with the highest value is selected as the best solar-specific power plant location.
The Best Location for Solar PV Power Plant = Max (Pi), for i = 1, 2, ... , n Like the solar energy shown in FIG.8, the procedure is the same for wind energy in FIG.10. In step 424, the alternatives, which are the raster pixels in the GIS layer of wind velocity, are determined and prepared in raster mode for the computations. In step 425, criteria and sub-criteria of effective parameters for establishing wind energy power plant as shown in the FIG.11 are listed for future calculations:
There are five main criteria and 19 sub-criteria for wind energy power plant.
The whole process of determining the best location to build wind energy is similar to solar energy with different parameters, weights and values. The sub-criteria are the same, but the main criterion is different, which is given below.
Main criteria pairwise comparison matrix with local weights Wind Land Main-Criteria Spatial Geomorphology Economic Weight Velocity Cover Wind Velocity a11 a12 a13 a14 als Spatial a21 a22 a23 a24 a25 w2 Land Cover a31 a32 a33 a34 a35 W3 Geomorphology a41 a42 a43 a44 a45 W4 Economic a41 a52 a53 a54 ass ws Like the solar and wind energy shown in FIG.8 and FIG.10, the procedure is the same for hydroelectric energy in FIG.12. In step 432, the alternatives, which are the raster pixels in the GIS
layer of rivers average flows, are determined and prepared in raster mode for the computations.
Date Recue/Date Received 2022-04-25 In step 433, criteria and sub-criteria of effective parameters for establishing hydroelectric energy power plant as shown in the FIG.13 are listed for future calculations:
There are five main criteria and 19 sub-criteria for hydroelectric energy power plant. The whole process of determining the best location to build hydroelectric energy is similar to solar and wind energy with different parameters, weights and values. The sub-criteria are the same, but the main criterion is different, which is given below.
Main criteria pairwise comparison matrix with local weights Rivers Main-Criteria Spatial Land Cover Geomorphology Economic Weight Flows Rivers Flows an a12 a13 a14 als w1 Spatial an a22 a23 a24 a25 W2 Land Cover a31 a32 a33 a34 a35 VV3 Geomorphology a41 a42 a43 a44 a45 W4 Economic a41 a52 a53 a54 ass ws Like the other energy types that mentioned in FIG.8, FIG.10 and FIG.12, the procedure is the same for biomass energy in FIG.14. In step 440. In step 441, criteria and sub-criteria of effective parameters for establishing biomass energy power plant as shown in the FIG.15 are listed for future calculations.
There are four main criteria and 19 sub-criteria for biomass energy power plant. The whole process of determining the best location to build biomass energy is similar to the energy types examined before. With different parameters, weights and values. The sub-criteria are the same, but the main criterion is different, which is given below.
Main criteria pairwise comparison matrix with local weights Main-Criteria Spatial Land Cover Geomorphology Economic Weight Spatial an a12 a13 a14 w1 Land Cover an a22 a23 a24 W2 Geomorphology a31 a32 a33 a34 VV3 Economic a41 a42 a43 a44 W4 Referring back to Figure 7, the power specific MCDM sub-processes 410-413 are now complete, from which the machine has separately determined a respective four best geographic locations for solar, wind, hydropower and biomass power plants. In step 414, the ranking scores of these four best geographic locations from the power specific MCDM sub-processes in FIG.8, FIG.10, Date Recue/Date Received 2022-04-25 FIG.12 and FIG.14, are compared. This comparison is possible because the sub-criteria of the four energy-specific sub-processes are the same as one another, and the values of the main criteria are normalized. Finally, in step 415 machine identifies which of these four best energy-specific locations has the best ranking score, and selects this location and plant type as the optimal location and power plant type to display to the user, and/or store in memory for future retrieval and display.
This can be expressed as follows:
Ls = Max (Pi), for i = 1, 2, ..., n Lw = Max (Pi), for i = 1, 2, ..., n Lh = Max (Pi), for i = 1, 2, ..., n Lb = Max (Pi), for i = 1, 2, ..., n Lail = Max (La, Lw, Lh, Lb) Where Ls is the best location for solar PV power plant, Lw is the best location for wind power plant, Lh is the best location for hydropower power plant, Lb is the best location for biomass power plant and Lau is the final optimal and energy-specific location.
Turning now from the best-location determination to another novel aspect of the invention, FIG.16 illustrates a series of computations executed by the machine at step 124 of FIG.16 if mining of cryptocurrency by produced power was specified by the user. Mining of cryptocurrency requires electricity for to operate the mining equipment and cooling systems.
of the machine surveys the user about potential mining cryptocurrency with electricity generated from renewable sources, and can also determine the required mining equipment, cooling systems and their costs. As with the resultant data from all other processes described herein, the computational results from this cryptocurrency mining evaluation be used to populate a final feasibility study. All of these steps are complex and required accurate computation. To calculate the amount of cryptocurrency that can be generated, the updated price of the cryptocurrency is received through an API. The user can decide how much electricity should be converted to cryptocurrency, and the machine performs the relevant calculations. In step 500, the user is queried as to whether available power should be dedicated solely to cryptocurrency mining, or to a combination of cryptocurrency mining and other general consumption. This amount of available power may be the same user-specified power capacity inputted at step 103 of FIG.1A or step 201 of FIG. 2A, or the budget-constrained capacity determined at step 301 of FIG.3. If the user decides to convert some of the available power to cryptocurrency and a balance of the available for general consumption, the process continues to step 501.
Alternatively, if the use opts to convert all of the available power to cryptocurrency mining, the process bypasses step 501 and proceeds directly to step 502. In step 501, the machine determines the relative split of available power between cryptocurrency mining and general consumption based on user choice, Date Recue/Date Received 2022-04-25 for example based on a percentage split or specified wattage. The equations of this part are given below:
Wcr = Wn(Scr) Scr = 100 Sco Where:
Wcr = Amount of power conversion to cryptocurrency (W) Scr = Share of power conversion to cryptocurrency (%) Sco = Share of power for general consumption (%) In step 502, the machine computes and determines cryptocurrency mining equipment requirements from a mining equipment database, which may or may not be embodied by, or found among, the one more equipment supplier databases used in FIG. 3 to search for power plant equipment. This section uses W cr as a key for finding required equipment by using the following algorithm:
INITIALIZE;
FOR i in n CREATE a list of all mining equipment END LOOP
FOR i in [mining equipment quantity]
COMPARE Watts of each mining equipment (Wei) with Wcr :
IF Wcr = Wei RETURN Wei ELSE IF Wcr < Wei RETURN min(Wei) ELSE IF Wcr > Wei RETURN max(Wei)*Quantity Wei END IF
END LOOP

Date Recue/Date Received 2022-04-25 In step 503, the machine calculates cryptocurrency mining profit based on selected mining equipment and an electricity price that is calculated by a function by using an electricity price API, that may also be used in the earlier processes described above . These calculations make use of a "total network hash rate" that is obtained by the API, and a "mining device hash rate", "block reward", and "block time" that are in the mining equipment database.
The equation of cryptocurrency mining profit is given below:
Pbhcard Wcardcpower $
Cryptocurrency Mining Profit = 3600 hnettblock 1000 (hour) Where:
$
P = Price of cryptocurrency (seconds) b = Block reward hashes hcard = Mining device hash rate (seconds) ( hashes hnet = Total network hash rate sseconds) second tblock = Block time ( block ) (Watts) Wcard = Power consumption of mining device hour ) $
cpower = Price of produced power (kWh) In step 504, the machine calculates the cost of all cryptocurrency mining equipment based on the selected items in the mining equipment database, and then machine computes required cooling system componentry for a mining system composed of that selected mining equipment, and calculates the added costs of that cooling system componentry. For calculating required cooling system, the following equation may be used:
(BTU
1 ¨) = 3.4129 (Watts) hour Date Recue/Date Received 2022-04-25 I
1 (Tonne) ¨hour) = 1/12000 0.2844W
¨ card Tcr = 1000 (Tonne) Where:
Tcr = Tonne of generated heat by mining device (Tonne) (Watts) Wcard Power consumption of mining device hour ) Then machine calculates required cooling system costs by its capability for removing generated heat of the mining equipment. And finally, the machine calculates the total cost of mining and cooling equipment that was selected from the mining equipment database by using the following equation:
Cost-rota/ = Cost equipment Cost cooling Where:
Cost -equipment = Costs of each equipment Cost -equipment = Costs of each cooling devices In step 505, the machine sends the calculated cryptocurrency financial data for using in feasibility study calculations. Such data preferably includes at least anticipated revenue from mining cryptocurrency, and the cost the proposed mining and cooling systems to be assembled from the selected mining equipment and cooling componentry.
FIG.17 illustrates a power management tool implemented via executable software of the machine. This feature helps users to determine the best time for saving produced power, selling the produced power to a power network, or consuming the produced power. For this purpose, the machine employs statistical data concerning the cost of electricity, and by using an iteration algorithm, the machine predicts the best times for storage/sale/consumption of power, and displays the determined scheduling to the user. The machine takes the type of renewable energy concerned and its capacity, power demand, produced power, type and specifications of the storage battery/batteries that are used for saving power for determined storage periods, related statistical data from one or more of the internal databases (e.g. OLAP
database 1005) and then solves the optimal dispatch problem using a reinforcement learning approach and a dynamic programming algorithm. Experience has shown that the value iteration algorithm finds optimum answer by repeating possible answers that converges the problem to a good optimum solution.
Date Recue/Date Received 2022-04-25 The machine uses a modified value iteration algorithm to solve this optimal dispatch problem and makes the best possible decision for storing/selling/consuming produced electricity.
In the following non-limiting example, starting at step 600 of FIG.17, a photovoltaic solar power plant is considered. At any given hour (h) the value of energy produced by the power plant is obtained by following equation:
C * (P ¨ F) Where, C is output in MW, P is price of electricity in $/MWh and F is photovoltaic power plant's hourly operating costs. In step 601, the machine assumes that the power plant unit does not have any operating constraints, in which case the optimal dispatch problem represented in the following form:
Selling where P > F
C=
Saving where P <F
If the price of electricity in $/MWh is greater than the photovoltaic solar power plant's current operating costs per hour, the machine proceeds to step 602, and records a general profit-motivated preference for sale of generated power, but if the price of electricity in $/MWh is less than the photovoltaic solar power plant's current operating costs per hour, the machine instead proceeds to step 603, and records a general profit-motivated preference for sale of generated power for storage of generated power.
From either of step 602 or 603, the process proceeds to step 604, where the value of generated power is computed using the following equation:
Unit Capacity * I Max{ P(h) ¨ F (h) , 0 }
h However, in reality the power plant has many operating constraints which make the generation optimal dispatch very challenging. Here are some of the constraints:
There is variable operating management cost which we call Von-i.
There is a limitation for saving power in the batteries So in step 605, final income can be found by the following equation:
R(h) = P(h) ¨ F (h) ¨ V om Where, P(h) is power price at hour "h", F(h) is photovoltaic power plant current costs per hour and Vom is variable operating and management cost.

Date Recue/Date Received 2022-04-25 Then, the machine computes the decision d(h) per hour in the step 606 by the following form:
1 if unit is in selling mode d(h) =
0 if unit is in saving mode Where, d(h) is decision of power unit condition. Therefore, number of switching is:
1 Id(h + 1) ¨ d(h)I
If d(h) = 1 machine decides for selling and goes to step 608. If d(h) = 0 machine decides for saving and goes to step 609.
Then in step 609 machine defines optimal dispatch problem as the following equation:
Max Id(h)R(h) ¨ Switching Cost *Ild(h + 1) ¨ d(h) I
where:
1 I d(h + 1) ¨ d(h)I < Max Switching and:
d(2) D = , d(h) E OM
\d(N)1 Where feasible switching space is the space of all acceptable switching, and min runtime and downtime are not violated.
The term "Dynamic Programming" (DP) refers to a collection of algorithms that can be used to compute optimal policies given a perfect model of environment as a Markov decision process (MDP). Classical DP algorithm are of limited utility in reinforcement learning both because of their assumption of a perfect model and because of their great computational expense, it is assumed that the environment is a finite MDP, i.e. that its state and action sets, S
and A(s), for s E S, are finite, and that its dynamics are given by a set of transition probabilities as the following form:
Pa(s, sr) = Pr(st-Ft = si Ist = s, at = a) Expected immediate rewards is obtained by the following form:
Ra(s, sr) = Etrt-Ft iat = a, st = s, st+1 = sl, for ails E S,a E A(s) Date Recue/Date Received 2022-04-25 The key idea of DP is the use of value function to organize and structure the search for good policies. Optimal policies can be easily attained once the optimal value function ( V*) is found, which satisfy the bellman optimality equation:
V* (s) = max Etrt+c, + yV* ( ..st+ 0 ist = s, at = a}
a = MaX 1 Pa (S, Sf)[Ra (s, sr) + yV*(s1)1 for ails ES,a E A (s) a s' An approach to solve dynamic programming problem is value iteration algorithm.
Value iteration is similar to backward dynamic programming for finite horizon problems.
The basic version of value iteration algorithm is given as follow:
initialize V(s) arbitrarily loop until policy good enough loop for s E S
loop for a E A
Q(s, a) := R(s, a) + y EsiEs T (s, a, s')V (sr) V (s) := max Q (s, a) a end loop end loop Value iteration algorithm is similar to the backward dynamic programming algorithm. Rather than using a sub script t, which is decremented from T back to 0, an iteration counter n is used that starts at 0 and increases until we satisfy a convergence criterion. The decision for condition of the generators is a decision between "turn on" and "turn off", and this decision depends on the decision we made prior to that hour. For example, the generator is turned on at hour "X" with "U" as minimum runtime, then no decision can be made at hour X+1, X+2,..., X+U-1. Due to minimum runtime constraint, the same is true when the generator is turned off:
assuming "0"
represents minimum downtime, no decision can be made in hour X+1, X+2,..., X+0-1. Therefore, the state of generator is defined as the following equation:
/d(h) S(h) = DT
UT
where:
1 if generator is on at hour h d(h) =
0 if generator is off at hour h and, DT (down time) E (1,2, === , 0) means number of consecutive hours that unit was off before hours, and UT(up time) E (1,2, == = , U) means number of consecutive hours that unit was on before hours, therefore the value function for any given state is defined as the following equation:

Date Recue/Date Received 2022-04-25 17(.5(h)) And number of states is equal to:
2xUx0xHxS
Where, 2 represent decision (CI) 1, U is uptime, 0 is downtime, H is number of hours and S is maximum number of switching. To approximate the value function as following equation:
17(.5(h)) = V (h, d(h), DT , UT) Using V (h) were:
d E
(h) = Max(V (h, d(h), DT, UT)), DT E [1,2, 0}
UT E [1,2, Now if -V (h) is known for all hours, decision vector D can be calculated as:
d(1) D= d(.2) .
\d(N)1 If d(h ¨ 1) = 1 then:
(h) = Max (9. (h + 1) + R(h), V (h + 0)) and if d(h ¨ 1) = 0 then:

(h) = Max -V (h + 1) ,1R(h + i) V (h + U) i The dynamic programming problem is solved in environment of Markov decision process using value iteration algorithm. Therefore, value iteration algorithm for optimal dispatch problem can be defined as follow:
Initialization 1 : Initialize (h) for all h 2 : set d(t)=1 for te{1,...,U}
And h U+1 If EY_,R(i) + (U + 1) > (2) Date Recue/Date Received 2022-04-25 Otherwise Set d(t)=0 And h 2 If d(h-1)=1 then Set d(t)=0 for tefh,h+1,...,h+0-11 If (h + 0) > (h + 1) + R(h) And set h h+0 Otherwise set d(h)=1 And h h+1 If d(h-1)=0 then Set d(t)=1 for tefh,h+1,...,h+U-11 If (h + U) + Erol R(h + i) > (h + 1) And set h h+U
Otherwise set d(h)=0 And h h+1 Update Value Function using V (h) = D (i) R (i) V given decision vector DIci(1) (N) Set d(0) = 0 an go to step (1) If updated V is different from prior V
By solving this problem, the machine can prepare a time table and schedule for managing produced power. This schedule contains time to consume, store or sell produced power, this time table can be used by one or more control devices of an existing and operational power plant that manages the dispatch of electricity to the storage battery/batteries, to the power network or to power consuming loads based on input commands from the machine.
In step 610, the machine prepares read only raw data into a human readable schedule/time-table for users, for their informed knowledge of the best time for using, saving or selling electricity, and may simultaneously prepare a command signal schedule for automated operation of the control device(s) for practical usage of this scheduling data.
In step 612, using the generated schedule data, the control device(s) is/are operated according to the transmitted control signals at any given time, on the computed schedule data.
If the decision at any given time is to saving produced power in the storage batteries, in step 613 control device saves power, and again this power storage period continues until a decision to instead consume the produced power is made. If such decision to consume produced power occurs, then in step 614, the control device(s) dispatch (es) produced power for consumption by electrical loads. And finally, if the decision to sell produced power occurs, then in step 615, the control device(s) dispatch (es) produced power for selling to the network.
FIG.18 illustrates a computer-implemented method for finding an optimal location for establishing an electric/hybrid vehicle charging station, which can be executed using similar methodology to that disclosed above for finding the optimal location for a renewable energy power plant.
Date Recue/Date Received 2022-04-25 In view of increasing greenhouse gas emissions, use of electric/hybrid vehicles has become more popular as an appropriate way to reducing greenhouse gas emissions and air pollution.
Nevertheless, a crucial consideration for the wide adoption of electric vehicles is charging stations.
Finding the best location for establishing electric car charging station is a tough problem and depends on numerous parameters. This problem resembles the foregoing problem of finding the best location for establishing renewable energy power plants, as addressed above with reference to FIG.4 to FIG.15. The strategy employed herein for establishing electric car charging stations is based on renewable energy sources, particularly solar energy using photovoltaic solutions. There are plenty of important parameters such as: Spatial, Geomorphology and Economic that have high impact on final result, power production and customer base when considering establishment of electric vehicle charging stations. In the detailed embodiment that follows, these parameters and their effects on finding the best location for electric vehicle charging stations are computed.
In step 700 of FIG. 18, the machine collects input from the data, which may include at least a subset of the same inputted data described above in relation to FIG.1, and in the illustrated example includes user-specification of a geographic search region within which the user wants to find an optimal geographic location for a charging station. in step 701, the alternatives, which are the raster pixels in the GIS layer of solar irradiance (GHI) of selected area, are determined and prepared in raster mode for the computations. then, criteria and sub-criteria of effective parameters for establishing charging station, these parameters can be divided into the categories of: Spatial considerations, Geomorphology and Economic considerations. these parameters contain many items that are given in the FIG.19 and identified by the machine, based on stored instructions in memory, for use in subsequent steps and calculations. In this detailed but non-limiting example, there are four main criteria and nine sub-criteria for the solar energy electric car charging station. In step 702, the weights of the criteria and sub-criteria related to the solar energy electric car charging station criteria and sub-criteria identified in step 701, having been predetermined, and calculated in accordance with the Saaty method mentioned earlier related to finding the best location for establishing renewable power plant, either by, or with the aid or guidance of a knowledgeable expert, and then stored in computer-readable memory of the machine as normalized Saaty pairwise comparison matrices, are now retrieved from memory for use of this predetermined solar energy charging station weighting scheme. It should be noted that since the construction of a solar charging station is very similar to a solar power plant, the process is similar, with the difference that the amounts of weights will be different.
The sub-criteria comparison with calculated local weight for each type of parameters are shown below:
Spatial sub-criteria pairwise comparison matrix with local weights Sub-Criteria Existing Charging Car Public Weight Station Parking Transport Existing an a12 a13 wsi Charging Station Car Parking an a22 a23 14/52 Public Transport a31 a32 a33 w53 Date Recue/Date Received 2022-04-25 Geomorphology sub-criteria pairwise comparison matrix with local weights Sub-Criteria Slope Orientation Elevation Weight Slope an a12 a13 WC' Orientation an a22 a23 WG2 Elevation a31 a32 a33 WG3 Economic sub-criteria pairwise comparison matrix with local weights Sub-Criteria Production Attraction Population Weight Production an a12 a13 WEI_ Attraction an a22 a23 wE2 Population a31 a32 a33 WE3 The predetermined expert-derived weights may be periodically updated to account for changing circumstances. In the weights of the sub-criteria factors, the alphabetic subscript in the weight w is shorthand for the the sub-criteria name. So, in the term w51 the "S"
represents "Spatial" and the "1" represents the first factor in the matrix. Likewise, "G" in wG, represents "Geomorphology", "E" in wEi represents "Economic".
Main criteria pairwise comparison matrix with local weights Main-Criteria GHI Spatial Geomorphology Economic Weight GHI an a12 a13 a14 14/1 Spatial an a22 a23 a24 W2 Geomorphology a31 a32 a33 a34 W3 Economic a41 a42 a43 a44 W4 As mentioned earlier, due to the similarity of the construction of the solar charging station with the solar power plant, other MCDM calculations are similar to the previous ones, which are given in the descriptions of FIG.8. Steps 419, 420, 421 and 422 of FIG.8 are included in step 703, and similar to the same steps, the calculation operation is performed according to the weights of this problem.

Date Recue/Date Received 2022-04-25 The calculated ranking scores of the candidate locations for a solar charging station are then compared to identify the best candidate location for a solar charging station.
The equation of the solar charging station-specific ranking function is given below:
F = w1R1 +
W2(Ws1R2 W s 2R3 + Ws 3R4) W4(WG iRs WG 2R6 WG 3R7) Ws(wE 1R8 W E 2R9 WE3R10) Where w1, w2, w3 and w4 are the local weights of main criteria:
: weight of GHI criterion w2 : weight of Spatial criterion w3 : weight of Economic criterion w4 : weight of Geomorphology criterion 111/52 and w53 are the local weights of Spatial sub-criteria:
wsi : weight of Existing Charging Station criterion 111/52 : weight of Car Parking criterion 111/53 : weight of Public Transport criterion wG2 and wG 3 are the local weights of Geomorphology sub-criteria:
wG, : weight of Slope criterion wG2 : weight of Orientation criterion wG 3 : weight of Elevation criterion wE2 and wE 3 are the local weights of Economic sub-criteria:
wEi : weight of Production criterion wE2 : weight of Attraction criterion wE 3 : weight of Population criterion And also, term "Ri" represents normalized performance value of each alternative:
: performance value of GHI raster R2 : performance value of Existing Charging Station raster R3 : performance value of Car Parking raster R4: performance value of Public Transport raster Rs : performance value of Slope raster R6 : performance value of Orientation raster R7 : performance value of Elevation raster Date Recue/Date Received 2022-04-25 R8 : performance value of Production raster R9 : performance value of Attraction raster R10 : performance value of Population raster Using this solar charging station-specific ranking function, the machine calculates a respective solar charging station-specific ranking score for each of the alternatives by using the relevant GIS
layers in raster mode. Accordingly, each pixel of the specific geographic search region in the GIS
map, except for those in the combined exclusion layer, has its own solar charging station-specific ranking score. These weights can be different in various situations and the above equation will likely or definitely change over time, and thus require period update in the software. And finally, in step 704, the machine identifies the optimal location for establishing an electric/hybrid vehicle charging station using solar energy sources according to the candidate location with the greatest ranking score value, and displays same to the user, and/or stores same in memory for later retrieval and display.
The Best Location for Solar Charging Station = Max (Fi), for i = 1, 2, ...
, n FIG.20 illustrates computer-implemented formulation of a feasibility study, before establishing a power plant, so that the user can estimate the financial, technological, working capital and cash flow projections resources that will be needed to ensure the successful launching of the power plant.
First, at the step 800, system will check whether a desired location has for the power plant has been specified by user or not. If the location has been specified by user, then the process bypasses step 801 and jumps ahead to step 802.If no user-desired location was specified, then in step 801 the machine will calculate the best location using Machine learning algorithms with the Location Intelligence described above in relation to FIG.4 to FIG.15. At step 802, the user's specified location or the machine's calculated best location will be shown to user in a map. Next, at step 804 generated diagrams are displayed such as: cash Flow Diagram, Payback Period, etc. have been made.
In step 805 the system shows all numeric data such as: Net Percent Value (NPV), Payback Period, Internal Rate of Return (IRR), Benefit-Cost Ratio (BCR), Levelized Cost of Energy (LCOE), etc.
In step 806 some useful charts are shown. These charts are based on Feasibility Study's data. The machine computes Net Percent Value (NPV) by the following equation:
C2 Ct NPV = ¨Co +¨+ _____________________ +===+ __ 1+r (1+r)2 (1 + r)t Where: ¨00 represents Initial Investment, C represents cash flow, r represents discount rate and T is time.
PPBThen the machine calculates Payback Period by the following equation:
Cost of Project (Investment) = ________________________________ Annual Cash inflows Date Recue/Date Received 2022-04-25 The machine computes Internal Rate of Return (IRR) by the following equation:
t NPV = V ________ Ct Co t-1 Where: Ct is net cash inflow during the period t, r is discount rate, t is number of time periods and Co is total initial investment cost.
The machine computes Benefit-Cost Ratio (BCR) by the following form:
rN ICFt[BenefitslI
IPV BCR ____ [Benefits11 + jot ¨ IPV [Costll ¨vN It [COStil L,t=0 (1 + jot Then the machine computes Levelized Cost of Energy (LCOE) by the following equation:
vN It + Mt + Ft L't=l LCOE ¨ (1 + r)t vN Et 't=1 (1 + r)t Where: It is investment expenditures in the year t, Mt is operations and maintenance expenditures in the year t, Ft is fuel expenditures in the year t, Et is electricity generation in the year t, r is discount rate and n represent economic life of the system. Then, the machine computes annual investment depreciation by the following equation:
A = P(1¨ r)t Where: A is amount, P is original value, r is discount rate and t is time (in year). The machine calculates the working capital by this form:
Working Capital = Current Assets ¨ Current Liabilities Then the machine calculates production costs by the following form:
Production Cost = Direct Labor + Direct Material + Overhead Costs on Manufacturing Then the machine calculates Profitability index by this form:
Percent Value of Future Cash Flows Profitability index ¨ ______________________________ Initial Investment After that, the machine computes rate of internal return by the following equation:
Date Recue/Date Received 2022-04-25 NPVõ
IRR = ra + ____________________ (rb ¨ ra) NPVõ ¨ NPVb Where: T., is lower discount rate and rb is higher discount rate.
Then the machine calculates other financial data by the following equations:
Total Debt Financial Leverage ¨ ___________________ Shareholder' sEquity Net Sales Fixed Invesment = ____________________ Average Fixed Assets Working Capital = Current Assets ¨ Current Liabilities Production Cost = Direct Labor + Direct Materials + Overhead costs Net Sales Fixed Invesment ¨ ____________________ Average Fixed Assets Cost Price = Direct Labor + Direct Materials + Overhead costs + Marketing Costs + Tools t Discounted Cash Flow = V _______ Ct Li (1 + r)t t-1 Percent Value of Future Cash Flow Profitability index = ______________________________ Initial Invesment In step 807 the machine displays many figures to help for constructing Renewable power plant such as: Process Flow Diagram (PFD) of the power plant, etc. In step 808 some practical reports are displayed. These reports are based on Location Data, Geographical Data, and Feasibility Study Data, and so on.
FIG.21 schematically illustrates the machine's automated compilation of the feasibility study's detailed reports. This is the main core of the feasibility study computation that will generate useful data to show to the users. The many inputs may include direct user data entry, and/or retrieval of other computed data. Among these inputs, at Section 900 machine gets Time planning, in Section 901 machine gets Products (Electricity), in Section 902 machine gets Currency unit, in Section 903 machine gets Inflation rate, in Section 904 machine gets Participants, in Section 905 machine gets Discount rate, in Section 906 machine gets Fixed and Initial costs, in Section 607 machine gets Pre-Operation costs, in Section 908 machine gets Production costs, etc.
In Section 909 Machine searches and picks required data from the internal, GIS
and NASA
databases, and optionally other data sources. In Section 910 Machine takes these inputs and computes feasibility study output by some Numerical Calculation methods and gives feasibility Date Recue/Date Received 2022-04-25 study outputs. In Section 911 Machine gives Financial review, In Section 912 Machine gives Estimation of fixed investment, In Section 913 Machine gives Estimation of working capital, In Section 914 Machine gives Estimation of production costs, In Section 915 Machine gives Estimation of annual investment depreciation, In Section 916 Machine gives Estimation of the total capital required for the project, In Section 917 Machine gives Estimation of the cost price by costs, In Section 918 Machine gives Determining the sources of financing the project and its financial cost, In Section 919 Machine gives Analysis of project revenues and costs, In Section 920 Machine gives Determine the profit and loss performance of the plan for the entire investment and the stock brought, In Section 921 Machine gives Economic studies, In Section 922 Machine gives Determine the net cash flow of the entire investment, In Section 923 Machine gives Analysis of discounted cash flow, In Section 924 Machine gives Internal rate of return, In Section 925 Machine gives Determination of the net present value, In Section 926 Machine gives Determination of the rate and period of internal return, In Section 927 Machine gives Determining the payback period, In Section 928 Machine gives Profitability index, In Section 929 Machine gives Perform project sensitivity analysis, In Section 930 Machine gives Risk analysis, In Section 931 Machine gives Analysis of financial ratios, In Section 932 Machine gives Preparation of financial statements, In Section 933 Machine produces Cash flow diagram, In Section 934 Machine produces Payback period diagram, In Section 935 Machine produces Process flow diagram and finally In Section 936 Machine produces required equipment.
In at least some embodiments contemplated herein, users with any level of knowledge can plan a renewable energy power plant by entering minimal input data, such as:
latitude and longitude of a desired location or geographical search area, budget or electricity generation capacity.
The described methodologies generate valuable output data, for example the best location for establishing the power plant (if not user-specified), the best type of energy in that area based on the angle of radiation, temperature, wind speed and other influential parameters. The wide scope of parameters cannot be calculated mentally or manually, and at least some of them are extracted from NASA and GIS databases that without an effective hardware and software combination, cannot be extracted and used in a meaningful way to fulfill the same ends as the disclosed invention.
In particularly preferable embodiments, after calculating the effective parameters for selection of a type of energy and geographical location, the system begins to calculate the required equipment with the best rate based on the type of energy and the amount of energy production needed, or attainable within a user-allotted budget. Again, this step cannot be done manually to any degree of comparable scope and efficiency as the machine automated solution proposed herein. Through a unique web service implemented by the equipment suppliers, the equipment data and characteristics are made available to the system, and the best equipment can be found based on the customer's budget and equipment efficiency. This selection may be based on machine learning so that the system selects the best choice based on the previous data.
In preferred embodiments, the machine also calculates the amount of energy that can be produced, which is done based on artificial intelligence mechanisms, and then an economic Date Recue/Date Received 2022-04-25 feasibility study can be performed, which includes calculations of IRR, NPV, NCF and diagrams. It is related to cash flow and profitability in the coming years.
Preferred embodiments also implement optimal power management of consumption time, to manage consumption of produced power to achieve the best economic benefits.
This feature offers the best time for consuming power, saving power in storage batteries or selling power to the network, and also it can connect with a power management device and send commands for optimally managing produced power.
Preferred embodiments also include calculation of the benefits of converting the produced power into a cryptocurrency by considering the cryptocurrency equipment requirements for such capability.
In at least one embodiment, the best locations to build charging stations for electric vehicles is calculated on the basis of renewable energy, with consideration to other parameters such as urban details and cost-effective renewable energy based on geographical features.
Since various modifications can be made in the invention as herein above described, and many apparently widely different embodiments of same made, it is intended that all matter contained in the foregoing specification shall be interpreted as illustrative only and not in a limiting sense.

Date Recue/Date Received 2022-04-25

Claims (19)

Claims

1. A computer-implemented method for at least partially automated planning of a renewable energy power plant project, said method comprising the following steps executed by one or more computer processors embodied in one or more computers operably connected to a communications network:
(a) storing in memory, for each of plurality of different power plant types, a different respective criteria-weighting scheme for use in automated evaluation and selection of an optimal geographic location for said renewable energy power plant project;
(b) collecting user input data from a user;
(c) based at least partially on said user input, identifying one or more planning constraints for said planning of said renewable energy power plant project;
(d) retrieving from one or more geographic and environmental databases, at least one of which is embodied in one or more geographic information systems, geographic information concerning a plurality of potential candidate geographic locations for said renewable energy power plant project, said retrieved geographic information including, for each candidate location, a respective dataset containing a plurality of performance values for a plurality of parameters;
(e) for at least one of said plurality of different power plant types, selecting the respective criteria-weighting scheme corresponding thereto, and applying said selected respective criteria-weighting scheme against the respective datasets of the candidate geographic locations in a computer-executed multi-criteria decision-making (MCDM) process in which at least a subset of said plurality of parameters are used as criteria of said MCDM process;
(f) based on results of said MCDM process, identifying the optimal geographic location for the renewable energy power generation plant from among said candidate geographic locations;
and (g) communicating identification of said optimal geographic location to the user.

2. The method of claim 1 wherein said predetermined power plant types include any two or more of solar, wind, hydroelectric and biomass power plants.

3.
The method of claim 1 or 2 comprising, in step (b), receiving user-identification of an intended power plant type from among different user-selectable power plant options presented to the user, each corresponding to a different one of said predetermined power plant types, and said at least one of said plurality of different power plant types in step (e) consists of said intended power plant type.

4. The method of claim 1 or 2 wherein step (e) comprises applying the respective criteria-weighting schemes of the plurality of different power plant types in said computer-executed MCDM process, and thereby identifying respective best candidate locations for said plurality of different power plant types;
step (f) comprises comparing evaluation results of those respective best candidate locations against one another, and selecting a best scoring one of said best candidate locations as the optimal geographic location; and step (g) comprises also communicating, from among said plurality of different power plant types, identification of a recommended power plant type to which said best scoring one of the best candidate locations corresponds.

5. The method of claim 4 wherein said computer-executed selection of the intended power plant type is based at least partly on said one or more other planning constraints, and said one or more other planning constraints comprise a budgetary constraint designated in said user input data.

6. The method of any preceding claim wherein the executed steps further include an equipment assessment step comprising:
using the one or constraints, identifying equipment requirements for the power plant project;
and searching one or more equipment supplier databases, and identifying therefrom candidate equipment options fulfilling said equipment requirements.

7. The method of claim 6 wherein the equipment assessment step further comprises:
assessing said candidate equipment options against one another to identify optimal equipment options; and determining a total cost of the optimal equipment options.

8. One or non-transitory computer readable media having stored thereon executable statements and instructions for execution by one or more processors, said statements and instructions being configured to, when executed, perform the method of any one of claims 1 to 7.

9. A system for at least partially automated planning of a renewable energy power plant project, said system comprising one or more computer processors embodied in one or more computers operably connected to a communications network by which said one or more computers are communicable with one or more geographic and environmental databases, at least one of which is embodied in one or more geographic information systems, and the one or more non-transitory computer readable media of claim 8, embodied in or connected to said one or more computers for execution of the statement and instructions on said one or more non-transitory computer readable media by said one or more processors of said one or more computers.

10. A computer-implemented method for finding optimal time periods for saving produced power in storage batteries, selling said produced power to a power network or consuming said power by using statistical data and a modified value iteration algorithm, said method comprising:
a. based on input data, retrieve identification of a type of renewable energy concerned and an associated capacity, power demand, produced power, and type and specifications of one or more storage batteries to be used for power storage;
b. retrieve statistical data from a database, and solve an optimal dispatch problem using a reinforcement learning approach and a dynamic programming algorithm;
c. in solving said optimal dispatch problem, using a value iteration algorithm to find an optimum answer by repeating possible answers that converges the problem to an optimum solution.

11. The method of claim, further comprising issuing command signals to one or more control devices of a power plant to switch said control device, according to the optimal time periods, between:
a power storage state dispatching the produced power to the storage batteries;
a power consumption state dispatching the produced power to electrical loads;
and a power selling state dispatching the produced power to a power network for financial compensation.

12. One or non-transitory computer readable media having stored thereon executable statements and instructions for execution by one or more processors, said statements and instructions being configured to, when executed, perform the method of claim 10 or 11.

13. A system for finding optimal time periods for saving produced power in storage batteries, selling said produced power to a power network or consuming said power, said system comprising one or more computer processors embodied in one or more computers, and one or more non-transitory computer readable media according to claim 12, embodied in or connected to said one or more computers for execution of the statement and instructions on said one or more non-transitory computer readable media by said one or more processors of said one or more computers.

14. A computer-implemented method for finding an optimal geographic location for constructing an electric vehicle charging station, said method comprising the following steps executed by one or more computer processors embodied in one or more computers operably connected to a communications network:
(a) retrieving from one or more geographic and environmental databases, at least one of which is embodied in one or more geographic information systems, geographic information concerning a plurality of potential candidate geographic locations for said electric vehicle charging station, said retrieved geographic information including, for each candidate location, a respective dataset containing a plurality of performance values for a plurality of parameters;
(b) applying a criteria weighting scheme against the respective datasets of the candidate geographic locations in a computer-executed multi-criteria decision-making (MCDM) process in which at least a subset of said plurality of parameters are used as criteria of said MCDM
process;
(c) based on results of said MCDM process, identifying the optimal geographic location for the electric vehicle charging station from among said candidate geographic locations; and (d) communicating identification of said optimal geographic location to a user.

15. One or non-transitory computer readable media having stored thereon executable statements and instructions for execution by one or more processors, said statements and instructions being configured to, when executed, perform the method of claim 14.

16. A system for finding an optimal geographic location for constructing an electric vehicle charging station, said system comprising one or more computer processors embodied in one or more computers, and one or more non-transitory computer readable media according to claim 15, embodied in or connected to said one or more computers for execution of the statement and instructions on said one or more non-transitory computer readable media by said one or more processors of said one or more computers.

17. A computer-implemented method for evaluating conversion of produced power to cryptocurrency and calculating associated costs of said conversion, said method comprising the following steps executed by one or more computer processors embodied in one or more computers operably connected to a communications network:
a. receiving user input on how much of the produced power should be converted to cryptocurrency;
b. calculating an amount of cryptocurrency that can be generated based on an updated price of the cryptocurrency received via said communications network;
c. identifying equipment requirements necessary to mine the cryptocurrency using produced power; and d. searching one or more equipment supplier databases for equipment fulfilling said equipment requirements;
e. tallying a cost of located equipment in the one or more equipment supplier databases that fulfill said equipment requirements.

18. One or non-transitory computer readable media having stored thereon executable statements and instructions for execution by one or more processors, said statements and instructions being configured to, when executed, perform the method of claim 17.

19. A system for evaluating conversion of produced power to cryptocurrency and calculating associated costs of said conversion, said system comprising one or more computer processors embodied in one or more computers, and one or more non-transitory computer readable media according to claim 18, embodied in or connected to said one or more computers for execution of the statement and instructions on said one or more non-transitory computer readable media by said one or more processors of said one or more computers.