Using GIS analytics and social preference data to evaluate utility-scale solar power site suitability

Abstract

a b s t r a c tDetermining socially acceptable and economically viable locations for utility-scale solar projects is a costly process that depends on many technical, economic, environmental and social factors. This paper presents a GIS-based multi-criteria solar project siting study conducted in the southwestern United States with a unique social preference component. Proximity raster layers were derived from features including roads, power lines, and rivers then overlain with 10 Â 10 m raster terrain datasets including slope and potential irradiance to produce a high resolution map showing solar energy potential from "poor" to "excellent" for high potential counties across the southwestern United States. Similar maps were produced by adding social acceptance data collected from a series of surveys showing the potential public resistance to development that can be expected in areas of high solar energy suitability. Applying social preferences to the model significantly reduced the amount of suitable area in each of the selected study areas. The methods demonstrated are expected to help reduce time, money, and resources currently allocated toward finding and assessing areas of high solar power suitability.

Energy Internet: The business perspective

“…Energy big data include not only a lot of internal data of energy system (e.g., energy use data [93], asset management data [94] and customer service data [95]), but also the abundant external data (e.g., weather data [96], GIS data [97], social media data [98] and electric vehicle data [99]), throughout the whole process of energy production and consumption [100][101][102] valuable resources for supporting the decision-makings of individuals, enterprises and government. To discovery valuable knowledge and fully realize the business potential of energy big data, various big data analytics techniques, such as data quality evaluation and modeling [103][104][105], data clustering and classification [68,[106][107][108][109], stream data processing [110][111][112], knowledge inference [113,114], statistical machine learning [115], neural networks modeling and deep learning [116,117], can be implemented on the data.…”

The Energy Transition from Plant Operators’ Perspective—A Behaviorist Approach

“…According to the spatial economic perspective, it would be only about finding out which site preferences operators of renewable energies have and how far spaces are able to satisfy these demands. This paradigm is still strongly present in planning-oriented studies [24][25][26][27]. However, these studies focus on restriction analyses and distance calculations only depict the theoretical site patterns that are obtained from profit-maximizing behavior.…”

Retail Site Selection using Machine Learning Algorithms

“…In addition, [3] utilized GIS to produce consumption maps that focus on consumer expenses, which provide significant cues in determining the optimum location for the supermarket. In the energy field, [8] used GIS site-suitability analysis to identify the solar power site through the proximity raster layers that produced a map that shows the solar energy potential in the countries. For safety planning, [13] used GIS to model the topography of a hilly region for safe site selection.…”

“…It is often perceived as an intersection between business intelligence, geographic analysis, and data visualization [1], [2]. Up to the present, geospatial analytics has retained a vital role as solution to various domains including retail business [3], [4], [5], [6] energy conservation [7], [8], [9], [10] agriculture [11], safety planning [12], [13] and road network [14]. The targeted domain that is tackled in this paper is retail site selection.…”